1
|
Tanaka SC, Kasai K, Okamoto Y, Koike S, Hayashi T, Yamashita A, Yamashita O, Johnstone T, Pestilli F, Doya K, Okada G, Shinzato H, Itai E, Takahara Y, Takamiya A, Nakamura M, Itahashi T, Aoki R, Koizumi Y, Shimizu M, Miyata J, Son S, Aki M, Okada N, Morita S, Sawamoto N, Abe M, Oi Y, Sajima K, Kamagata K, Hirose M, Aoshima Y, Hamatani S, Nohara N, Funaba M, Noda T, Inoue K, Hirano J, Mimura M, Takahashi H, Hattori N, Sekiguchi A, Kawato M, Hanakawa T. The status of MRI databases across the world focused on psychiatric and neurological disorders. Psychiatry Clin Neurosci 2024; 78:563-579. [PMID: 39162256 DOI: 10.1111/pcn.13717] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/22/2024] [Revised: 05/13/2024] [Accepted: 07/02/2024] [Indexed: 08/21/2024]
Abstract
Neuroimaging databases for neuro-psychiatric disorders enable researchers to implement data-driven research approaches by providing access to rich data that can be used to study disease, build and validate machine learning models, and even redefine disease spectra. The importance of sharing large, multi-center, multi-disorder databases has gradually been recognized in order to truly translate brain imaging knowledge into real-world clinical practice. Here, we review MRI databases that share data globally to serve multiple psychiatric or neurological disorders. We found 42 datasets consisting of 23,293 samples from patients with psychiatry and neurological disorders and healthy controls; 1245 samples from mood disorders (major depressive disorder and bipolar disorder), 2015 samples from developmental disorders (autism spectrum disorder, attention-deficit hyperactivity disorder), 675 samples from schizophrenia, 1194 samples from Parkinson's disease, 5865 samples from dementia (including Alzheimer's disease), We recognize that large, multi-center databases should include governance processes that allow data to be shared across national boundaries. Addressing technical and regulatory issues of existing databases can lead to better design and implementation and improve data access for the research community. The current trend toward the development of shareable MRI databases will contribute to a better understanding of the pathophysiology, diagnosis and assessment, and development of early interventions for neuropsychiatric disorders.
Collapse
Affiliation(s)
- Saori C Tanaka
- Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institutes International, Kyoto, Japan
- Division of Information Science, Nara Institute of Science and Technology, Nara, Japan
| | - Kiyoto Kasai
- Department of Neuropsychiatry, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
- The International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo Institutes for Advanced Study (UTIAS), Tokyo, Japan
- University of Tokyo Institute for Diversity & Adaptation of Human Mind (UTIDAHM), Tokyo, Japan
- Center for Brain Imaging in Health and Diseases (CBHD), The University of Tokyo Hospital, Tokyo, Japan
| | - Yasumasa Okamoto
- Department of Psychiatry and Neurosciences, Graduate School of Biomedical and Health Science, Hiroshima University, Hiroshima, Japan
| | - Shinsuke Koike
- The International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo Institutes for Advanced Study (UTIAS), Tokyo, Japan
- University of Tokyo Institute for Diversity & Adaptation of Human Mind (UTIDAHM), Tokyo, Japan
- Center for Evolutionary Cognitive Sciences, Graduate School of Art and Sciences, The University of Tokyo, Tokyo, Japan
| | - Takuya Hayashi
- Laboratory for Brain Connectomics Imaging, RIKEN Center for Biosystems Dynamics Research, Hyogo, Japan
- Department of Brain Connectomics, Kyoto University Graduate School of Medicine, Kyoto, Japan
| | - Ayumu Yamashita
- Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institutes International, Kyoto, Japan
- Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan
| | - Okito Yamashita
- Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institutes International, Kyoto, Japan
- Center for Advanced Intelligence Project, RIKEN, Tokyo, Japan
| | - Tom Johnstone
- School of Health Sciences, Swinburne University of Technology, Melbourne, Victoria, Australia
| | - Franco Pestilli
- Department of Psychology, Department of Neuroscience, Center for Perceptual Systems, Center for Learning and Memory, The University of Texas at Austin, Austin, Texas, USA
| | - Kenji Doya
- Neural Computation Unit, Okinawa Institute of Science and Technology Graduate University, Okinawa, Japan
| | - Go Okada
- Department of Psychiatry and Neurosciences, Graduate School of Biomedical and Health Science, Hiroshima University, Hiroshima, Japan
| | - Hotaka Shinzato
- Department of Psychiatry and Neurosciences, Graduate School of Biomedical and Health Science, Hiroshima University, Hiroshima, Japan
- Department of Neuropsychiatry, Graduate School of Medicine, University of the Ryukyus, Okinawa, Japan
| | - Eri Itai
- Department of Psychiatry and Neurosciences, Graduate School of Biomedical and Health Science, Hiroshima University, Hiroshima, Japan
| | - Yuji Takahara
- Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institutes International, Kyoto, Japan
- Biomarker R&D department, SHIONOGI & CO., Ltd, Osaka, Japan
| | - Akihiro Takamiya
- Department of Neuropsychiatry, Keio University School of Medicine, Tokyo, Japan
- Hills Joint Research Laboratory for Future Preventive Medicine and Wellness, Keio University School of Medicine, Tokyo, Japan
- Neuropsychiatry, Department of Neurosciences, Leuven Brain Institute, KU Leuven, Leuven, Belgium
- Geriatric Psychiatry, University Psychiatric Center KU Leuven, Leuven, Belgium
| | - Motoaki Nakamura
- Medical Institute of Developmental Disabilities Research, Showa University, Tokyo, Japan
| | - Takashi Itahashi
- Medical Institute of Developmental Disabilities Research, Showa University, Tokyo, Japan
| | - Ryuta Aoki
- Medical Institute of Developmental Disabilities Research, Showa University, Tokyo, Japan
- Graduate School of Humanities, Tokyo Metropolitan University, Tokyo, Japan
| | - Yukiaki Koizumi
- Department of Psychiatry and Behavioral Sciences, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan
- Department of Psychiatry, Haryugaoka Hospital, Fukushima, Japan
| | - Masaaki Shimizu
- Department of Psychiatry and Behavioral Sciences, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan
| | - Jun Miyata
- Department of Psychiatry, Aichi Medical University, Aichi, Japan
- Department of Psychiatry, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| | - Shuraku Son
- Department of Psychiatry, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| | - Morio Aki
- Department of Psychiatry, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| | - Naohiro Okada
- Department of Neuropsychiatry, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
- The International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo Institutes for Advanced Study (UTIAS), Tokyo, Japan
| | - Susumu Morita
- Department of Neuropsychiatry, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Nobukatsu Sawamoto
- Department of Human Health Sciences, Kyoto University Graduate School of Medicine, Kyoto, Japan
| | - Mitsunari Abe
- Integrative Brain Imaging Center, National Center of Neurology and Psychiatry, Tokyo, Japan
| | - Yuki Oi
- Department of Neurology, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| | - Kazuaki Sajima
- Integrative Brain Imaging Center, National Center of Neurology and Psychiatry, Tokyo, Japan
| | - Koji Kamagata
- Department of Radiology, Juntendo University School of Medicine, Tokyo, Japan
| | - Masakazu Hirose
- Department of Integrated Neuroanatomy and Neuroimaging, Kyoto University Graduate School of Medicine, Kyoto, Japan
| | - Yohei Aoshima
- Integrative Brain Imaging Center, National Center of Neurology and Psychiatry, Tokyo, Japan
| | - Sayo Hamatani
- Research Center for Child Mental Development, Chiba University, Chiba, Japan
- Research Center for Child Mental Development, University of Fukui, Fukui, Japan
| | - Nobuhiro Nohara
- Department of Stress Sciences and Psychosomatic Medicine, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan
| | - Misako Funaba
- Department of Behavioral Medicine, National Institute of Mental Health, National Center of Neurology and Psychiatry, Tokyo, Japan
- Student Counseling Center, Meiji Gakuin University, Tokyo, Japan
| | - Tomomi Noda
- Department of Psychiatry, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| | - Kana Inoue
- Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institutes International, Kyoto, Japan
| | - Jinichi Hirano
- Department of Neuropsychiatry, Keio University School of Medicine, Tokyo, Japan
| | - Masaru Mimura
- Department of Neuropsychiatry, Keio University School of Medicine, Tokyo, Japan
| | - Hidehiko Takahashi
- Department of Psychiatry and Behavioral Sciences, Graduate School of Medical and Dental Sciences, Tokyo Medical and Dental University, Tokyo, Japan
- Center for Brain Integration Research, Tokyo Medical and Dental University, Tokyo, Japan
| | - Nobutaka Hattori
- Department of Neurology, Juntendo University Graduate School of Medicine, Tokyo, Japan
- Neurodegenerative Disorders Collaborative Laboratory, RIKEN Center for Brain Science, Saitama, Japan
| | - Atsushi Sekiguchi
- Department of Behavioral Medicine, National Institute of Mental Health, National Center of Neurology and Psychiatry, Tokyo, Japan
| | - Mitsuo Kawato
- Brain Information Communication Research Laboratory Group, Advanced Telecommunications Research Institutes International, Kyoto, Japan
| | - Takashi Hanakawa
- Integrative Brain Imaging Center, National Center of Neurology and Psychiatry, Tokyo, Japan
- Department of Integrated Neuroanatomy and Neuroimaging, Kyoto University Graduate School of Medicine, Kyoto, Japan
| |
Collapse
|
2
|
Patel J, Schöttner M, Tarun A, Tourbier S, Alemán-Gómez Y, Hagmann P, Bolton TAW. Modeling the impact of MRI acquisition bias on structural connectomes: Harmonizing structural connectomes. Netw Neurosci 2024; 8:623-652. [PMID: 39355442 PMCID: PMC11340995 DOI: 10.1162/netn_a_00368] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Accepted: 02/26/2024] [Indexed: 10/03/2024] Open
Abstract
One way to increase the statistical power and generalizability of neuroimaging studies is to collect data at multiple sites or merge multiple cohorts. However, this usually comes with site-related biases due to the heterogeneity of scanners and acquisition parameters, negatively impacting sensitivity. Brain structural connectomes are not an exception: Being derived from T1-weighted and diffusion-weighted magnetic resonance images, structural connectivity is impacted by differences in imaging protocol. Beyond minimizing acquisition parameter differences, removing bias with postprocessing is essential. In this work we create, from the exhaustive Human Connectome Project Young Adult dataset, a resampled dataset of different b-values and spatial resolutions, modeling a cohort scanned across multiple sites. After demonstrating the statistical impact of acquisition parameters on connectivity, we propose a linear regression with explicit modeling of b-value and spatial resolution, and validate its performance on separate datasets. We show that b-value and spatial resolution affect connectivity in different ways and that acquisition bias can be reduced using a linear regression informed by the acquisition parameters while retaining interindividual differences and hence boosting fingerprinting performance. We also demonstrate the generative potential of our model, and its generalization capability in an independent dataset reflective of typical acquisition practices in clinical settings.
Collapse
Affiliation(s)
- Jagruti Patel
- Department of Radiology, Lausanne University Hospital and University of Lausanne (CHUV-UNIL), Lausanne, Switzerland
| | - Mikkel Schöttner
- Department of Radiology, Lausanne University Hospital and University of Lausanne (CHUV-UNIL), Lausanne, Switzerland
| | - Anjali Tarun
- Department of Radiology, Lausanne University Hospital and University of Lausanne (CHUV-UNIL), Lausanne, Switzerland
| | - Sebastien Tourbier
- Department of Radiology, Lausanne University Hospital and University of Lausanne (CHUV-UNIL), Lausanne, Switzerland
| | - Yasser Alemán-Gómez
- Department of Radiology, Lausanne University Hospital and University of Lausanne (CHUV-UNIL), Lausanne, Switzerland
| | - Patric Hagmann
- Department of Radiology, Lausanne University Hospital and University of Lausanne (CHUV-UNIL), Lausanne, Switzerland
| | - Thomas A W Bolton
- Department of Radiology, Lausanne University Hospital and University of Lausanne (CHUV-UNIL), Lausanne, Switzerland
| |
Collapse
|
3
|
Zhou Z, Fischl B, Aganj I. Harmonization of Structural Brain Connectivity through Distribution Matching. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.09.05.611489. [PMID: 39314357 PMCID: PMC11418962 DOI: 10.1101/2024.09.05.611489] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Subscribe] [Scholar Register] [Indexed: 09/25/2024]
Abstract
The increasing prevalence of multi-site diffusion-weighted magnetic resonance imaging (dMRI) studies potentially offers enhanced statistical power for investigating brain structure. However, these studies face challenges due to variations in scanner hardware and acquisition protocols. While several methods exist for dMRI data harmonization, few specifically address structural brain connectivity. We introduce a new distribution-matching approach to harmonizing structural brain connectivity across different sites and scanners. We evaluate our method using structural brain connectivity data from two distinct datasets of OASIS-3 and ADNI-2, comparing its performance to the widely used ComBat method. Our approach is meant to align the statistical properties of connectivity data from these two datasets. We examine the impact of harmonization on the correlation of brain connectivity with the Mini-Mental State Examination score and age. Our results demonstrate that our distribution-matching technique more effectively harmonizes structural brain connectivity, often producing stronger and more significant correlations compared to ComBat. Qualitative assessments illustrate the desired distributional alignment of ADNI-2 with OASIS-3, while quantitative evaluations confirm robust performance. This work contributes to the growing field of dMRI harmonization, potentially improving the reliability and comparability of structural connectivity studies that combine data from different sources in neuroscientific and clinical research.
Collapse
Affiliation(s)
- Zhen Zhou
- Athinoula A. Martinos Center for Biomedical Imaging, Radiology Department, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Bruce Fischl
- Athinoula A. Martinos Center for Biomedical Imaging, Radiology Department, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Iman Aganj
- Athinoula A. Martinos Center for Biomedical Imaging, Radiology Department, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
4
|
Zivadinov R, Tranquille A, Reeves JA, Dwyer MG, Bergsland N. Brain atrophy assessment in multiple sclerosis: technical- and subject-related barriers for translation to real-world application in individual subjects. Expert Rev Neurother 2024:1-16. [PMID: 39233336 DOI: 10.1080/14737175.2024.2398484] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/05/2024] [Accepted: 08/27/2024] [Indexed: 09/06/2024]
Abstract
INTRODUCTION Brain atrophy is a well-established MRI outcome for predicting clinical progression and monitoring treatment response in persons with multiple sclerosis (pwMS) at the group level. Despite the important progress made, the translation of brain atrophy assessment into clinical practice faces several challenges. AREAS COVERED In this review, the authors discuss technical- and subject-related barriers for implementing brain atrophy assessment as part of the clinical routine at the individual level. Substantial progress has been made to understand and mitigate technical barriers behind MRI acquisition. Numerous research and commercial segmentation techniques for volume estimation are available and technically validated, but their clinical value has not been fully established. A systematic assessment of subject-related barriers, which include genetic, environmental, biological, lifestyle, comorbidity, and aging confounders, is critical for the interpretation of brain atrophy measures at the individual subject level. Educating both medical providers and pwMS will help better clarify the benefits and limitations of assessing brain atrophy for disease monitoring and prognosis. EXPERT OPINION Integrating brain atrophy assessment into clinical practice for pwMS requires overcoming technical and subject-related challenges. Advances in MRI standardization, artificial intelligence, and clinician education will facilitate this process, improving disease management and potentially reducing long-term healthcare costs.
Collapse
Affiliation(s)
- Robert Zivadinov
- Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, Buffalo, NY, USA
- Center for Biomedical Imaging at the Clinical Translational Science Institute, University at Buffalo, State University of New York, Buffalo, NY, USA
| | - Ashley Tranquille
- Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, Buffalo, NY, USA
| | - Jack A Reeves
- Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, Buffalo, NY, USA
| | - Michael G Dwyer
- Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, Buffalo, NY, USA
- Center for Biomedical Imaging at the Clinical Translational Science Institute, University at Buffalo, State University of New York, Buffalo, NY, USA
| | - Niels Bergsland
- Buffalo Neuroimaging Analysis Center, Department of Neurology, Jacobs School of Medicine and Biomedical Sciences, University at Buffalo, Buffalo, NY, USA
| |
Collapse
|
5
|
Herlin B, Uszynski I, Chauvel M, Dupont S, Poupon C. Sex-related variability of white matter tracts in the whole HCP cohort. Brain Struct Funct 2024; 229:1713-1735. [PMID: 39012482 PMCID: PMC11374878 DOI: 10.1007/s00429-024-02833-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2024] [Accepted: 07/06/2024] [Indexed: 07/17/2024]
Abstract
Behavioral differences between men and women have been studied extensively, as have differences in brain anatomy. However, most studies have focused on differences in gray matter, while white matter has been much less studied. We conducted a comprehensive study of 77 deep white matter tracts to analyze their volumetric and microstructural variability between men and women in the full Human Connectome Project (HCP) cohort of 1065 healthy individuals aged 22-35 years. We found a significant difference in total brain volume between men and women (+ 12.6% in men), consistent with the literature. 16 tracts showed significant volumetric differences between men and women, one of which stood out due to a larger effect size: the corpus callosum genu, which was larger in women (+ 7.3% in women, p = 5.76 × 10-19). In addition, we found several differences in microstructural parameters between men and women, both using standard Diffusion Tensor Imaging (DTI) parameters and more complex microstructural parameters from the Neurite Orientation Dispersion and Density Imaging (NODDI) model, with the tracts showing the greatest differences belonging to motor (cortico-spinal tracts, cortico-cerebellar tracts) or limbic (cingulum, fornix, thalamo-temporal radiations) systems. These microstructural differences may be related to known behavioral differences between the sexes in timed motor performance, aggressiveness/impulsivity, and social cognition.
Collapse
Affiliation(s)
- B Herlin
- BAOBAB, NeuroSpin, Université Paris-Saclay, CNRS, CEA, Gif-Sur-Yvette, France.
- Rehabilitation Unit, AP-HP, Pitié-Salpêtrière Hospital, Paris, France.
- Université Paris Sorbonne, Paris, France.
| | - I Uszynski
- BAOBAB, NeuroSpin, Université Paris-Saclay, CNRS, CEA, Gif-Sur-Yvette, France
| | - M Chauvel
- BAOBAB, NeuroSpin, Université Paris-Saclay, CNRS, CEA, Gif-Sur-Yvette, France
| | - S Dupont
- Reference Center for Rare Epilepsies, Department of Neurology, Epileptology Unit, AP-HP, Pitié-Salpêtrière Hospital, Paris, France
- Rehabilitation Unit, AP-HP, Pitié-Salpêtrière Hospital, Paris, France
- Paris Brain Institute (ICM), Sorbonne-Université, Inserm U1127, CNRS 7225, Paris, France
- Université Paris Sorbonne, Paris, France
| | - C Poupon
- BAOBAB, NeuroSpin, Université Paris-Saclay, CNRS, CEA, Gif-Sur-Yvette, France
| |
Collapse
|
6
|
Newlin NR, Kim ME, Kanakaraj P, Yao T, Hohman T, Pechman KR, Beason-Held LL, Resnick SM, Archer D, Jefferson A, Landman BA, Moyer D. MidRISH: Unbiased harmonization of rotationally invariant harmonics of the diffusion signal. Magn Reson Imaging 2024; 111:113-119. [PMID: 38537892 PMCID: PMC11283839 DOI: 10.1016/j.mri.2024.03.033] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/09/2023] [Revised: 03/09/2024] [Accepted: 03/20/2024] [Indexed: 04/09/2024]
Abstract
Data harmonization is necessary for removing confounding effects in multi-site diffusion image analysis. One such harmonization method, LinearRISH, scales rotationally invariant spherical harmonic (RISH) features from one site ("target") to the second ("reference") to reduce confounding scanner effects. However, reference and target site designations are not arbitrary and resultant diffusion metrics (fractional anisotropy, mean diffusivity) are biased by this choice. In this work we propose MidRISH: rather than scaling reference RISH features to target RISH features, we project both sites to a mid-space. We validate MidRISH with the following experiments: harmonizing scanner differences from 37 matched patients free of cognitive impairment, and harmonizing acquisition and study differences on 117 matched patients free of cognitive impairment. We find that MidRISH reduces bias of reference selection while preserving harmonization efficacy of LinearRISH. Users should be cautious when performing LinearRISH harmonization. To select a reference site is to choose diffusion metric effect-size. Our proposed method eliminates the bias-inducing site selection step.
Collapse
Affiliation(s)
- Nancy R Newlin
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA.
| | - Michael E Kim
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | | | - Tianyuan Yao
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | - Timothy Hohman
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA; Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA; Vanderbilt Genetics Institute, Vanderbilt University School of Medicine, Nashville, TN, USA
| | - Kimberly R Pechman
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Lori L Beason-Held
- Laboratory of Behavioral Neuroscience, National Institute on Aging, National Institutes of Health, Baltimore, MD, USA
| | - Susan M Resnick
- Laboratory of Behavioral Neuroscience, National Institute on Aging, National Institutes of Health, Baltimore, MD, USA
| | - Derek Archer
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA; Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA; Vanderbilt Genetics Institute, Vanderbilt University School of Medicine, Nashville, TN, USA
| | - Angela Jefferson
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA; Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA; Department of Medicine, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Bennett A Landman
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA; Vanderbilt University Institute of Imaging Science, Vanderbilt University, Nashville, TN, USA
| | - Daniel Moyer
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| |
Collapse
|
7
|
Lin R, Gholipour A, Thiran JP, Karimi D, Kebiri H, Cuadra MB. CROSS-AGE AND CROSS-SITE DOMAIN SHIFT IMPACTS ON DEEP LEARNING-BASED WHITE MATTER FIBER ESTIMATION IN NEWBORN AND BABY BRAINS. ARXIV 2024:arXiv:2312.14773v2. [PMID: 38196752 PMCID: PMC10775359] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Subscribe] [Scholar Register] [Indexed: 01/11/2024]
Abstract
Deep learning models have shown great promise in estimating tissue microstructure from limited diffusion magnetic resonance imaging data. However, these models face domain shift challenges when test and train data are from different scanners and protocols, or when the models are applied to data with inherent variations such as the developing brains of infants and children scanned at various ages. Several techniques have been proposed to address some of these challenges, such as data harmonization or domain adaptation in the adult brain. However, those techniques remain unexplored for the estimation of fiber orientation distribution functions in the rapidly developing brains of infants. In this work, we extensively investigate the age effect and domain shift within and across two different cohorts of 201 newborns and 165 babies using the Method of Moments and fine-tuning strategies. Our results show that reduced variations in the microstructural development of babies in comparison to newborns directly impact the deep learning models' cross-age performance. We also demonstrate that a small number of target domain samples can significantly mitigate domain shift problems.
Collapse
Affiliation(s)
- Rizhong Lin
- Signal Processing Laboratory 5 (LTS5), École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
- Department of Radiology, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- College of Electronic and Information Engineering, Tongji University, Shanghai, China
| | - Ali Gholipour
- Computational Radiology Laboratory, Department of Radiology, Boston Children's Hospital and Harvard Medical School, Boston, MA, USA
| | - Jean-Philippe Thiran
- Signal Processing Laboratory 5 (LTS5), École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
- Department of Radiology, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- CIBM Center for Biomedical Imaging, Switzerland
| | - Davood Karimi
- Computational Radiology Laboratory, Department of Radiology, Boston Children's Hospital and Harvard Medical School, Boston, MA, USA
| | - Hamza Kebiri
- Department of Radiology, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- CIBM Center for Biomedical Imaging, Switzerland
| | - Meritxell Bach Cuadra
- CIBM Center for Biomedical Imaging, Switzerland
- Department of Radiology, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
| |
Collapse
|
8
|
Hajianfar G, Hosseini SA, Bagherieh S, Oveisi M, Shiri I, Zaidi H. Impact of harmonization on the reproducibility of MRI radiomic features when using different scanners, acquisition parameters, and image pre-processing techniques: a phantom study. Med Biol Eng Comput 2024; 62:2319-2332. [PMID: 38536580 DOI: 10.1007/s11517-024-03071-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2023] [Accepted: 03/05/2024] [Indexed: 07/31/2024]
Abstract
This study investigated the impact of ComBat harmonization on the reproducibility of radiomic features extracted from magnetic resonance images (MRI) acquired on different scanners, using various data acquisition parameters and multiple image pre-processing techniques using a dedicated MRI phantom. Four scanners were used to acquire an MRI of a nonanatomic phantom as part of the TCIA RIDER database. In fast spin-echo inversion recovery (IR) sequences, several inversion durations were employed, including 50, 100, 250, 500, 750, 1000, 1500, 2000, 2500, and 3000 ms. In addition, a 3D fast spoiled gradient recalled echo (FSPGR) sequence was used to investigate several flip angles (FA): 2, 5, 10, 15, 20, 25, and 30 degrees. Nineteen phantom compartments were manually segmented. Different approaches were used to pre-process each image: Bin discretization, Wavelet filter, Laplacian of Gaussian, logarithm, square, square root, and gradient. Overall, 92 first-, second-, and higher-order statistical radiomic features were extracted. ComBat harmonization was also applied to the extracted radiomic features. Finally, the Intraclass Correlation Coefficient (ICC) and Kruskal-Wallis's (KW) tests were implemented to assess the robustness of radiomic features. The number of non-significant features in the KW test ranged between 0-5 and 29-74 for various scanners, 31-91 and 37-92 for three times tests, 0-33 to 34-90 for FAs, and 3-68 to 65-89 for IRs before and after ComBat harmonization, with different image pre-processing techniques, respectively. The number of features with ICC over 90% ranged between 0-8 and 6-60 for various scanners, 11-75 and 17-80 for three times tests, 3-83 to 9-84 for FAs, and 3-49 to 3-63 for IRs before and after ComBat harmonization, with different image pre-processing techniques, respectively. The use of various scanners, IRs, and FAs has a great impact on radiomic features. However, the majority of scanner-robust features is also robust to IR and FA. Among the effective parameters in MR images, several tests in one scanner have a negligible impact on radiomic features. Different scanners and acquisition parameters using various image pre-processing might affect radiomic features to a large extent. ComBat harmonization might significantly impact the reproducibility of MRI radiomic features.
Collapse
Affiliation(s)
- Ghasem Hajianfar
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland
| | - Seyyed Ali Hosseini
- Translational Neuroimaging Laboratory, McGill University Research Centre for Studies in Aging, Douglas Hospital, McGill University, Montréal, Québec, Canada
- Department of Neurology and Neurosurgery, Faculty of Medicine, McGill University, Montréal, Québec, Canada
| | - Sara Bagherieh
- School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran
| | - Mehrdad Oveisi
- Department of Computer Science, University of British Columbia, Vancouver, BC, Canada
| | - Isaac Shiri
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Habib Zaidi
- Division of Nuclear Medicine and Molecular Imaging, Geneva University Hospital, CH-1211, Geneva, Switzerland.
- Department of Nuclear Medicine and Molecular Imaging, University of Groningen, University Medical Center Groningen, Groningen, Netherlands.
- Department of Nuclear Medicine, University of Southern Denmark, Odense, Denmark.
- University Research and Innovation Center, Óbuda University, Budapest, Hungary.
| |
Collapse
|
9
|
Quach M, Ali I, Shultz SR, Casillas-Espinosa PM, Hudson MR, Jones NC, Silva JC, Yamakawa GR, Braine EL, Immonen R, Staba RJ, Tohka J, Harris NG, Gröhn O, O'Brien TJ, Wright DK. ComBating inter-site differences in field strength: harmonizing preclinical traumatic brain injury MRI data. NMR IN BIOMEDICINE 2024; 37:e5142. [PMID: 38494895 DOI: 10.1002/nbm.5142] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/05/2023] [Revised: 12/09/2023] [Accepted: 02/15/2024] [Indexed: 03/19/2024]
Abstract
Integrating datasets from multiple sites and scanners can increase statistical power for neuroimaging studies but can also introduce significant inter-site confounds. We evaluated the effectiveness of ComBat, an empirical Bayes approach, to combine longitudinal preclinical MRI data acquired at 4.7 or 9.4 T at two different sites in Australia. Male Sprague Dawley rats underwent MRI on Days 2, 9, 28, and 150 following moderate/severe traumatic brain injury (TBI) or sham injury as part of Project 1 of the NIH/NINDS-funded Centre Without Walls EpiBioS4Rx project. Diffusion-weighted and multiple-gradient-echo images were acquired, and outcomes included QSM, FA, and ADC. Acute injury measures including apnea and self-righting reflex were consistent between sites. Mixed-effect analysis of ipsilateral and contralateral corpus callosum (CC) summary values revealed a significant effect of site on FA and ADC values, which was removed following ComBat harmonization. Bland-Altman plots for each metric showed reduced variability across sites following ComBat harmonization, including for QSM, despite appearing to be largely unaffected by inter-site differences and no effect of site observed. Following harmonization, the combined inter-site data revealed significant differences in the imaging metrics consistent with previously reported outcomes. TBI resulted in significantly reduced FA and increased susceptibility in the ipsilateral CC, and significantly reduced FA in the contralateral CC compared with sham-injured rats. Additionally, TBI rats also exhibited a reversal in ipsilateral CC ADC values over time with significantly reduced ADC at Day 9, followed by increased ADC 150 days after injury. Our findings demonstrate the need for harmonizing multi-site preclinical MRI data and show that this can be successfully achieved using ComBat while preserving phenotypical changes due to TBI.
Collapse
Affiliation(s)
- Mara Quach
- Department of Neuroscience, School of Translational Medicine, Monash University, Melbourne, Victoria, Australia
- Department of Biomedical Engineering, The University of Melbourne, Melbourne, Victoria, Australia
- Melbourne Brain Centre Imaging Unit, The University of Melbourne, Melbourne, Victoria, Australia
| | - Idrish Ali
- Department of Neuroscience, School of Translational Medicine, Monash University, Melbourne, Victoria, Australia
| | - Sandy R Shultz
- Department of Neuroscience, School of Translational Medicine, Monash University, Melbourne, Victoria, Australia
- Department of Medicine, The Royal Melbourne Hospital, The University of Melbourne, Parkville, Victoria, Australia
- Health Sciences, Vancouver Island University, Nanaimo, British Columbia, Canada
| | - Pablo M Casillas-Espinosa
- Department of Neuroscience, School of Translational Medicine, Monash University, Melbourne, Victoria, Australia
- Department of Medicine, The Royal Melbourne Hospital, The University of Melbourne, Parkville, Victoria, Australia
- Department of Neurology, The Alfred Hospital, Melbourne, Victoria, Australia
| | - Matthew R Hudson
- Department of Neuroscience, School of Translational Medicine, Monash University, Melbourne, Victoria, Australia
| | - Nigel C Jones
- Department of Neuroscience, School of Translational Medicine, Monash University, Melbourne, Victoria, Australia
| | - Juliana C Silva
- Department of Neuroscience, School of Translational Medicine, Monash University, Melbourne, Victoria, Australia
| | - Glenn R Yamakawa
- Department of Neuroscience, School of Translational Medicine, Monash University, Melbourne, Victoria, Australia
| | - Emma L Braine
- Department of Neuroscience, School of Translational Medicine, Monash University, Melbourne, Victoria, Australia
| | - Riikka Immonen
- A.I. Virtanen Institute for Molecular Sciences, University of Eastern Finland, Kuopio, Finland
| | - Richard J Staba
- Department of Neurology, David Geffen School of Medicine at University of California at Los Angeles, Los Angeles, California, USA
| | - Jussi Tohka
- A.I. Virtanen Institute for Molecular Sciences, University of Eastern Finland, Kuopio, Finland
| | - Neil G Harris
- Department of Neurology, David Geffen School of Medicine at University of California at Los Angeles, Los Angeles, California, USA
| | - Olli Gröhn
- A.I. Virtanen Institute for Molecular Sciences, University of Eastern Finland, Kuopio, Finland
| | - Terence J O'Brien
- Department of Neuroscience, School of Translational Medicine, Monash University, Melbourne, Victoria, Australia
- Department of Medicine, The Royal Melbourne Hospital, The University of Melbourne, Parkville, Victoria, Australia
- Department of Neurology, The Alfred Hospital, Melbourne, Victoria, Australia
| | - David K Wright
- Department of Neuroscience, School of Translational Medicine, Monash University, Melbourne, Victoria, Australia
| |
Collapse
|
10
|
Li Y, Zhang W, Wu Y, Yin L, Zhu C, Chen Y, Cetin-Karayumak S, Cho KIK, Zekelman LR, Rushmore J, Rathi Y, Makris N, O'Donnell LJ, Zhang F. A diffusion MRI tractography atlas for concurrent white matter mapping across Eastern and Western populations. Sci Data 2024; 11:787. [PMID: 39019877 PMCID: PMC11255335 DOI: 10.1038/s41597-024-03624-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/09/2024] [Accepted: 07/08/2024] [Indexed: 07/19/2024] Open
Abstract
The study of brain differences across Eastern and Western populations provides vital insights for understanding potential cultural and genetic influences on cognition and mental health. Diffusion MRI (dMRI) tractography is an important tool in assessing white matter (WM) connectivity and brain tissue microstructure across different populations. However, a comprehensive investigation into WM fiber tracts between Eastern and Western populations is challenged due to the lack of a cross-population WM atlas and the large site-specific variability of dMRI data. This study presents a dMRI tractography atlas, namely the East-West WM Atlas, for concurrent WM mapping between Eastern and Western populations and creates a large, harmonized dMRI dataset (n=306) based on the Human Connectome Project and the Chinese Human Connectome Project. The curated WM atlas, as well as subject-specific data including the harmonized dMRI data, the whole brain tractography data, and parcellated WM fiber tracts and their diffusion measures, are publicly released. This resource is a valuable addition to facilitating the exploration of brain commonalities and differences across diverse cultural backgrounds.
Collapse
Affiliation(s)
- Yijie Li
- School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
| | - Wei Zhang
- School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
| | - Ye Wu
- School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China
| | - Li Yin
- West China Hospital of Medical Science, Sichuan University, Chengdu, China
| | - Ce Zhu
- School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China
| | - Yuqian Chen
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | | | - Kang Ik K Cho
- Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | - Leo R Zekelman
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | - Jarrett Rushmore
- Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
- Department of Anatomy and Neurobiology, Boston University School of Medicine, Boston, USA
| | - Yogesh Rathi
- Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | - Nikos Makris
- Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, USA
| | - Lauren J O'Donnell
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, USA.
| | - Fan Zhang
- School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China.
| |
Collapse
|
11
|
Kebiri H, Gholipour A, Lin R, Vasung L, Calixto C, Krsnik Ž, Karimi D, Bach Cuadra M. Deep learning microstructure estimation of developing brains from diffusion MRI: A newborn and fetal study. Med Image Anal 2024; 95:103186. [PMID: 38701657 DOI: 10.1016/j.media.2024.103186] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2023] [Revised: 02/06/2024] [Accepted: 04/22/2024] [Indexed: 05/05/2024]
Abstract
Diffusion-weighted magnetic resonance imaging (dMRI) is widely used to assess the brain white matter. Fiber orientation distribution functions (FODs) are a common way of representing the orientation and density of white matter fibers. However, with standard FOD computation methods, accurate estimation requires a large number of measurements that usually cannot be acquired for newborns and fetuses. We propose to overcome this limitation by using a deep learning method to map as few as six diffusion-weighted measurements to the target FOD. To train the model, we use the FODs computed using multi-shell high angular resolution measurements as target. Extensive quantitative evaluations show that the new deep learning method, using significantly fewer measurements, achieves comparable or superior results than standard methods such as Constrained Spherical Deconvolution and two state-of-the-art deep learning methods. For voxels with one and two fibers, respectively, our method shows an agreement rate in terms of the number of fibers of 77.5% and 22.2%, which is 3% and 5.4% higher than other deep learning methods, and an angular error of 10° and 20°, which is 6° and 5° lower than other deep learning methods. To determine baselines for assessing the performance of our method, we compute agreement metrics using densely sampled newborn data. Moreover, we demonstrate the generalizability of the new deep learning method across scanners, acquisition protocols, and anatomy on two clinical external datasets of newborns and fetuses. We validate fetal FODs, successfully estimated for the first time with deep learning, using post-mortem histological data. Our results show the advantage of deep learning in computing the fiber orientation density for the developing brain from in-vivo dMRI measurements that are often very limited due to constrained acquisition times. Our findings also highlight the intrinsic limitations of dMRI for probing the developing brain microstructure.
Collapse
Affiliation(s)
- Hamza Kebiri
- CIBM Center for Biomedical Imaging, Switzerland; Department of Radiology, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland; Computational Radiology Laboratory, Department of Radiology, Boston Children's Hospital and Harvard Medical School, Boston, MA, USA.
| | - Ali Gholipour
- Computational Radiology Laboratory, Department of Radiology, Boston Children's Hospital and Harvard Medical School, Boston, MA, USA
| | - Rizhong Lin
- Department of Radiology, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland; Signal Processing Laboratory 5 (LTS5), École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
| | - Lana Vasung
- Department of Pediatrics, Boston Children's Hospital, and Harvard Medical School, Boston, MA, USA
| | - Camilo Calixto
- Computational Radiology Laboratory, Department of Radiology, Boston Children's Hospital and Harvard Medical School, Boston, MA, USA
| | - Željka Krsnik
- Croatian Institute for Brain Research, School of Medicine, University of Zagreb, Zagreb, Croatia
| | - Davood Karimi
- Computational Radiology Laboratory, Department of Radiology, Boston Children's Hospital and Harvard Medical School, Boston, MA, USA
| | - Meritxell Bach Cuadra
- CIBM Center for Biomedical Imaging, Switzerland; Department of Radiology, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
| |
Collapse
|
12
|
Takemura H, Kruper JA, Miyata T, Rokem A. Tractometry of Human Visual White Matter Pathways in Health and Disease. Magn Reson Med Sci 2024; 23:316-340. [PMID: 38866532 PMCID: PMC11234945 DOI: 10.2463/mrms.rev.2024-0007] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/14/2024] Open
Abstract
Diffusion-weighted MRI (dMRI) provides a unique non-invasive view of human brain tissue properties. The present review article focuses on tractometry analysis methods that use dMRI to assess the properties of brain tissue within the long-range connections comprising brain networks. We focus specifically on the major white matter tracts that convey visual information. These connections are particularly important because vision provides rich information from the environment that supports a large range of daily life activities. Many of the diseases of the visual system are associated with advanced aging, and tractometry of the visual system is particularly important in the modern aging society. We provide an overview of the tractometry analysis pipeline, which includes a primer on dMRI data acquisition, voxelwise model fitting, tractography, recognition of white matter tracts, and calculation of tract tissue property profiles. We then review dMRI-based methods for analyzing visual white matter tracts: the optic nerve, optic tract, optic radiation, forceps major, and vertical occipital fasciculus. For each tract, we review background anatomical knowledge together with recent findings in tractometry studies on these tracts and their properties in relation to visual function and disease. Overall, we find that measurements of the brain's visual white matter are sensitive to a range of disorders and correlate with perceptual abilities. We highlight new and promising analysis methods, as well as some of the current barriers to progress toward integration of these methods into clinical practice. These barriers, such as variability in measurements between protocols and instruments, are targets for future development.
Collapse
Affiliation(s)
- Hiromasa Takemura
- Division of Sensory and Cognitive Brain Mapping, Department of System Neuroscience, National Institute for Physiological Sciences, Okazaki, Aichi, Japan
- Graduate Institute for Advanced Studies, SOKENDAI, Hayama, Kanagawa, Japan
- Center for Information and Neural Networks (CiNet), Advanced ICT Research Institute, National Institute of Information and Communications Technology, Suita, Osaka, Japan
| | - John A Kruper
- Department of Psychology and eScience Institute, University of Washington, Seattle, WA, USA
| | - Toshikazu Miyata
- Division of Sensory and Cognitive Brain Mapping, Department of System Neuroscience, National Institute for Physiological Sciences, Okazaki, Aichi, Japan
- Center for Information and Neural Networks (CiNet), Advanced ICT Research Institute, National Institute of Information and Communications Technology, Suita, Osaka, Japan
| | - Ariel Rokem
- Department of Psychology and eScience Institute, University of Washington, Seattle, WA, USA
| |
Collapse
|
13
|
Liu Q, Ning L, Shaik IA, Liao C, Gagoski B, Bilgic B, Grissom W, Nielsen JF, Zaitsev M, Rathi Y. Reduced cross-scanner variability using vendor-agnostic sequences for single-shell diffusion MRI. Magn Reson Med 2024; 92:246-256. [PMID: 38469671 PMCID: PMC11055665 DOI: 10.1002/mrm.30062] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2023] [Revised: 01/31/2024] [Accepted: 02/05/2024] [Indexed: 03/13/2024]
Abstract
PURPOSE To reduce the inter-scanner variability of diffusion MRI (dMRI) measures between scanners from different vendors by developing a vendor-neutral dMRI pulse sequence using the open-source vendor-agnostic Pulseq platform. METHODS We implemented a standard EPI based dMRI sequence in Pulseq. We tested it on two clinical scanners from different vendors (Siemens Prisma and GE Premier), systematically evaluating and comparing the within- and inter-scanner variability across the vendors, using both the vendor-provided and Pulseq dMRI sequences. Assessments covered both a diffusion phantom and three human subjects, using standard error (SE) and Lin's concordance correlation to measure the repeatability and reproducibility of standard DTI metrics including fractional anisotropy (FA) and mean diffusivity (MD). RESULTS Identical dMRI sequences were executed on both scanners using Pulseq. On the phantom, the Pulseq sequence showed more than a 2.5× reduction in SE (variability) across Siemens and GE scanners. Furthermore, Pulseq sequences exhibited markedly reduced SE in-vivo, maintaining scan-rescan repeatability while delivering lower variability in FA and MD (more than 50% reduction in cortical/subcortical regions) compared to vendor-provided sequences. CONCLUSION The Pulseq diffusion sequence reduces the cross-scanner variability for both phantom and in-vivo data, which will benefit multi-center neuroimaging studies and improve the reproducibility of neuroimaging studies.
Collapse
Affiliation(s)
- Qiang Liu
- Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
- School of Biomedical Engineering, Southern Medical University, Guangzhou, China
| | - Lipeng Ning
- Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| | - Imam Ahmed Shaik
- Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| | - Congyu Liao
- Department of Radiology, Stanford University, Stanford, CA, United States
| | - Borjan Gagoski
- Department of Radiology, Harvard Medical School, Boston, MA, United States
- Fetal-Neonatal Neuroimaging & Developmental Science Center, Boston Children’s Hospital, Boston, MA, United States
| | - Berkin Bilgic
- Department of Radiology, Harvard Medical School, Boston, MA, United States
- Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Boston, MA, United States
- Harvard/MIT Health Sciences and Technology, Cambridge, MA, United States
| | - William Grissom
- Department of Biomedical Engineering, Case School of Medicine, Case Western Reserve University, Cleveland, OH, United States
| | - Jon-Fredrik Nielsen
- fMRI Laboratory and Biomedical Engineering, University of Michigan, Ann Arbor, MI, United States
| | - Maxim Zaitsev
- Division of Medical Physics, Department of Radiology, University Medical Center Freiburg, Freiburg, Germany
| | - Yogesh Rathi
- Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| |
Collapse
|
14
|
Alushaj E, Hemachandra D, Ganjavi H, Seergobin KN, Sharma M, Kashgari A, Barr J, Reisman W, Khan AR, MacDonald PA. Increased mean diffusivity of the caudal motor SNc identifies patients with REM sleep behaviour disorder and Parkinson's disease. NPJ Parkinsons Dis 2024; 10:128. [PMID: 38951528 PMCID: PMC11217278 DOI: 10.1038/s41531-024-00731-0] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/12/2023] [Accepted: 05/30/2024] [Indexed: 07/03/2024] Open
Abstract
Idiopathic rapid eye movement sleep behaviour disorder (iRBD)-a Parkinson's disease (PD) prodrome-might exhibit neural changes similar to those in PD. Substantia nigra pars compacta (SNc) degeneration underlies motor symptoms of PD. In iRBD and early PD (ePD), we measured diffusion MRI (dMRI) in the caudal motor SNc, which overlaps the nigrosome-1-the earliest-degenerating dopaminergic neurons in PD-and in the striatum. Nineteen iRBD, 26 ePD (1.7 ± 0.03 years), and 46 age-matched healthy controls (HCs) were scanned at Western University, and 47 iRBD, 115 ePD (0.9 ± 0.01 years), and 56 HCs were scanned through the Parkinson's Progression Markers Initiative, using 3T MRI. We segmented the SNc and striatum into subregions using automated probabilistic tractography to the cortex. We measured mean diffusivity (MD) and fractional anisotropy (FA) along white-matter bundles and subregional surfaces. We performed group-level and classification analyses. Increased caudal motor SNc surface MD was the only iRBD-HCs and ePD-HCs difference replicating across datasets (padj < 0.05). No iRBD-ePD differences emerged. Caudal motor SNc surface MD classified patient groups from HCs at the single-subject level with good-to-excellent balanced accuracy in an independent sample (0.91 iRBD and 0.86 iRBD and ePD combined), compared to fair performance for total SNc surface MD (0.72 iRBD and ePD). Caudal motor SNc surface MD correlated significantly with MDS-UPDRS-III scores in ePD patients. Using dMRI and automated segmentation, we detected changes suggesting altered microstructural integrity in iRBD and ePD in the nigrostriatal subregion known to degenerate first in PD. Surface MD of the caudal motor SNc presents a potential measure for inclusion in neuroimaging biomarkers of iRBD and PD.
Collapse
Affiliation(s)
- Erind Alushaj
- Department of Neuroscience, Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
- Western Institute for Neuroscience, Western University, London, ON, Canada
| | - Dimuthu Hemachandra
- Robarts Research Institute, Western University, London, ON, Canada
- School of Biomedical Engineering, Western University, London, ON, Canada
| | - Hooman Ganjavi
- Department of Psychiatry, Western University, London, ON, Canada
| | - Ken N Seergobin
- Western Institute for Neuroscience, Western University, London, ON, Canada
| | - Manas Sharma
- Department of Radiology, Western University, London, ON, Canada
- Department of Clinical Neurological Sciences, Western University, London, ON, Canada
| | - Alia Kashgari
- Department of Medicine, Respirology Division, Western University, London, ON, Canada
| | - Jennifer Barr
- Department of Psychiatry, Western University, London, ON, Canada
| | - William Reisman
- Department of Medicine, Respirology Division, Western University, London, ON, Canada
| | - Ali R Khan
- Robarts Research Institute, Western University, London, ON, Canada
- Department of Medical Biophysics, Western University, London, ON, Canada
| | - Penny A MacDonald
- Western Institute for Neuroscience, Western University, London, ON, Canada.
- Department of Clinical Neurological Sciences, Western University, London, ON, Canada.
| |
Collapse
|
15
|
Makowski C, Nichols TE, Dale AM. Quality over quantity: powering neuroimaging samples in psychiatry. Neuropsychopharmacology 2024:10.1038/s41386-024-01893-4. [PMID: 38902353 DOI: 10.1038/s41386-024-01893-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/22/2024] [Revised: 05/06/2024] [Accepted: 05/24/2024] [Indexed: 06/22/2024]
Abstract
Neuroimaging has been widely adopted in psychiatric research, with hopes that these non-invasive methods will provide important clues to the underpinnings and prediction of various mental health symptoms and outcomes. However, the translational impact of neuroimaging has not yet reached its promise, despite the plethora of computational methods, tools, and datasets at our disposal. Some have lamented that too many psychiatric neuroimaging studies have been underpowered with respect to sample size. In this review, we encourage this discourse to shift from a focus on sheer increases in sample size to more thoughtful choices surrounding experimental study designs. We propose considerations at multiple decision points throughout the study design, data modeling and analysis process that may help researchers working in psychiatric neuroimaging boost power for their research questions of interest without necessarily increasing sample size. We also provide suggestions for leveraging multiple datasets to inform each other and strengthen our confidence in the generalization of findings to both population-level and clinical samples. Through a greater emphasis on improving the quality of brain-based and clinical measures rather than merely quantity, meaningful and potentially translational clinical associations with neuroimaging measures can be achieved with more modest sample sizes in psychiatry.
Collapse
Affiliation(s)
- Carolina Makowski
- Department of Radiology, University of California San Diego, San Diego, CA, USA.
| | - Thomas E Nichols
- Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, UK
| | - Anders M Dale
- Departments of Radiology and Neurosciences, University of California San Diego, San Diego, CA, USA
| |
Collapse
|
16
|
Seoni S, Shahini A, Meiburger KM, Marzola F, Rotunno G, Acharya UR, Molinari F, Salvi M. All you need is data preparation: A systematic review of image harmonization techniques in Multi-center/device studies for medical support systems. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2024; 250:108200. [PMID: 38677080 DOI: 10.1016/j.cmpb.2024.108200] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 01/27/2024] [Revised: 04/20/2024] [Accepted: 04/22/2024] [Indexed: 04/29/2024]
Abstract
BACKGROUND AND OBJECTIVES Artificial intelligence (AI) models trained on multi-centric and multi-device studies can provide more robust insights and research findings compared to single-center studies. However, variability in acquisition protocols and equipment can introduce inconsistencies that hamper the effective pooling of multi-source datasets. This systematic review evaluates strategies for image harmonization, which standardizes appearances to enable reliable AI analysis of multi-source medical imaging. METHODS A literature search using PRISMA guidelines was conducted to identify relevant papers published between 2013 and 2023 analyzing multi-centric and multi-device medical imaging studies that utilized image harmonization approaches. RESULTS Common image harmonization techniques included grayscale normalization (improving classification accuracy by up to 24.42 %), resampling (increasing the percentage of robust radiomics features from 59.5 % to 89.25 %), and color normalization (enhancing AUC by up to 0.25 in external test sets). Initially, mathematical and statistical methods dominated, but machine and deep learning adoption has risen recently. Color imaging modalities like digital pathology and dermatology have remained prominent application areas, though harmonization efforts have expanded to diverse fields including radiology, nuclear medicine, and ultrasound imaging. In all the modalities covered by this review, image harmonization improved AI performance, with increasing of up to 24.42 % in classification accuracy and 47 % in segmentation Dice scores. CONCLUSIONS Continued progress in image harmonization represents a promising strategy for advancing healthcare by enabling large-scale, reliable analysis of integrated multi-source datasets using AI. Standardizing imaging data across clinical settings can help realize personalized, evidence-based care supported by data-driven technologies while mitigating biases associated with specific populations or acquisition protocols.
Collapse
Affiliation(s)
- Silvia Seoni
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - Alen Shahini
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - Kristen M Meiburger
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - Francesco Marzola
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - Giulia Rotunno
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - U Rajendra Acharya
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield, Australia; Centre for Health Research, University of Southern Queensland, Australia
| | - Filippo Molinari
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy
| | - Massimo Salvi
- Biolab, PolitoBIOMedLab, Department of Electronics and Telecommunications, Politecnico di Torino, Turin, Italy.
| |
Collapse
|
17
|
Ortug A, Guo Y, Feldman HA, Ou Y, Warren JLA, Dieuveuil H, Baumer NT, Faja SK, Takahashi E. Autism-associated brain differences can be observed in utero using MRI. Cereb Cortex 2024; 34:bhae117. [PMID: 38602735 PMCID: PMC11008691 DOI: 10.1093/cercor/bhae117] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/18/2023] [Revised: 03/01/2024] [Accepted: 03/02/2024] [Indexed: 04/12/2024] Open
Abstract
Developmental changes that occur before birth are thought to be associated with the development of autism spectrum disorders. Identifying anatomical predictors of early brain development may contribute to our understanding of the neurobiology of autism spectrum disorders and allow for earlier and more effective identification and treatment of autism spectrum disorders. In this study, we used retrospective clinical brain magnetic resonance imaging data from fetuses who were diagnosed with autism spectrum disorders later in life (prospective autism spectrum disorders) in order to identify the earliest magnetic resonance imaging-based regional volumetric biomarkers. Our results showed that magnetic resonance imaging-based autism spectrum disorder biomarkers can be found as early as in the fetal period and suggested that the increased volume of the insular cortex may be the most promising magnetic resonance imaging-based fetal biomarker for the future emergence of autism spectrum disorders, along with some additional, potentially useful changes in regional volumes and hemispheric asymmetries.
Collapse
Affiliation(s)
- Alpen Ortug
- Division of Newborn Medicine, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, United States
- Department of Radiology, Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA 02129, United States
- Department of Radiology, Harvard Medical School, Boston, MA 02115, United States
| | - Yurui Guo
- Division of Newborn Medicine, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, United States
| | - Henry A Feldman
- Division of Newborn Medicine, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, United States
| | - Yangming Ou
- Division of Newborn Medicine, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, United States
- Department of Radiology, Harvard Medical School, Boston, MA 02115, United States
| | - Jose Luis Alatorre Warren
- Division of Newborn Medicine, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, United States
- Department of Radiology, Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA 02129, United States
- Department of Radiology, Harvard Medical School, Boston, MA 02115, United States
| | - Harrison Dieuveuil
- Division of Newborn Medicine, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, United States
| | - Nicole T Baumer
- Department of Neurology, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, United States
- Department of Pediatrics, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, United States
| | - Susan K Faja
- Department of Pediatrics, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, United States
- Division of Developmental Medicine, Laboratories of Cognitive Neuroscience, Boston Children's Hospital, Harvard Medical School, Brookline, MA 02115, United States
| | - Emi Takahashi
- Division of Newborn Medicine, Department of Medicine, Boston Children’s Hospital, Harvard Medical School, Boston, MA 02115, United States
- Department of Radiology, Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA 02129, United States
- Department of Radiology, Harvard Medical School, Boston, MA 02115, United States
| |
Collapse
|
18
|
Cetin-Karayumak S, Zhang F, Zurrin R, Billah T, Zekelman L, Makris N, Pieper S, O'Donnell LJ, Rathi Y. Harmonized diffusion MRI data and white matter measures from the Adolescent Brain Cognitive Development Study. Sci Data 2024; 11:249. [PMID: 38413633 PMCID: PMC10899197 DOI: 10.1038/s41597-024-03058-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/25/2023] [Accepted: 02/12/2024] [Indexed: 02/29/2024] Open
Abstract
The Adolescent Brain Cognitive Development (ABCD) Study® has collected data from over 10,000 children across 21 sites, providing insights into adolescent brain development. However, site-specific scanner variability has made it challenging to use diffusion MRI (dMRI) data from this study. To address this, a dataset of harmonized and processed ABCD dMRI data (from release 3) has been created, comprising quality-controlled imaging data from 9,345 subjects, focusing exclusively on the baseline session, i.e., the first time point of the study. This resource required substantial computational time (approx. 50,000 CPU hours) for harmonization, whole-brain tractography, and white matter parcellation. The dataset includes harmonized dMRI data, 800 white matter clusters, 73 anatomically labeled white matter tracts in full and low resolution, and 804 different dMRI-derived measures per subject (72.3 TB total size). Accessible via the NIMH Data Archive, it offers a large-scale dMRI dataset for studying structural connectivity in child and adolescent neurodevelopment. Additionally, several post-harmonization experiments were conducted to demonstrate the success of the harmonization process on the ABCD dataset.
Collapse
Affiliation(s)
- Suheyla Cetin-Karayumak
- Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
- Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA.
| | - Fan Zhang
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Ryan Zurrin
- Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Tashrif Billah
- Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Leo Zekelman
- Department of Neurosurgery, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA
- Program in Speech and Hearing Bioscience and Technology, Division of Medical Sciences, Harvard University, Boston, Massachusetts, USA
| | - Nikos Makris
- Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA
- Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | | | - Lauren J O'Donnell
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA.
| | - Yogesh Rathi
- Department of Psychiatry, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA
- Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
- Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
19
|
Newlin NR, Kanakaraj P, Li T, Pechman K, Archer D, Jefferson A, Landman B, Moyer D. Learning site-invariant features of connectomes to harmonize complex network measures. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2024; 12930:129302E. [PMID: 39220624 PMCID: PMC11364372 DOI: 10.1117/12.3009645] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/04/2024]
Abstract
Multi-site diffusion MRI data is often acquired on different scanners and with distinct protocols. Differences in hardware and acquisition result in data that contains site dependent information, which confounds connectome analyses aiming to combine such multi-site data. We propose a data-driven solution that isolates site-invariant information whilst maintaining relevant features of the connectome. We construct a latent space that is uncorrelated with the imaging site and highly correlated with patient age and a connectome summary measure. Here, we focus on network modularity. The proposed model is a conditional, variational autoencoder with three additional prediction tasks: one for patient age, and two for modularity trained exclusively on data from each site. This model enables us to 1) isolate site-invariant biological features, 2) learn site context, and 3) re-inject site context and project biological features to desired site domains. We tested these hypotheses by projecting 77 connectomes from two studies and protocols (Vanderbilt Memory and Aging Project (VMAP) and Biomarkers of Cognitive Decline Among Normal Individuals (BIOCARD) to a common site. We find that the resulting dataset of modularity has statistically similar means (p-value <0.05) across sites. In addition, we fit a linear model to the joint dataset and find that positive correlations between age and modularity were preserved.
Collapse
Affiliation(s)
- Nancy R Newlin
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | | | - Thomas Li
- Department of Biomedical Engineering, Vanderbilt University, Nashville, Tennessee, USA
| | - Kimberly Pechman
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Derek Archer
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA
- Vanderbilt Genetics Institute, Vanderbilt University School of Medicine, Nashville, TN, USA
| | - Angela Jefferson
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Medicine, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Bennett Landman
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
- Department of Biomedical Engineering, Vanderbilt University, Nashville, Tennessee, USA
- Vanderbilt University Institute of Imaging Science, Vanderbilt University, Nashville, TN, USA
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
| | - Daniel Moyer
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| |
Collapse
|
20
|
Xu H, Newlin NR, Kim ME, Gao C, Kanakaraj P, Krishnan AR, Remedios LW, Khairi NM, Pechman K, Archer D, Hohman TJ, Jefferson AL, Isgum I, Huo Y, Moyer D, Schilling KG, Landman BA. Evaluation of Mean Shift, ComBat, and CycleGAN for Harmonizing Brain Connectivity Matrices Across Sites. PROCEEDINGS OF SPIE--THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING 2024; 12926:129261X. [PMID: 39310215 PMCID: PMC11415266 DOI: 10.1117/12.3005563] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/25/2024]
Abstract
Connectivity matrices derived from diffusion MRI (dMRI) provide an interpretable and generalizable way of understanding the human brain connectome. However, dMRI suffers from inter-site and between-scanner variation, which impedes analysis across datasets to improve robustness and reproducibility of results. To evaluate different harmonization approaches on connectivity matrices, we compared graph measures derived from these matrices before and after applying three harmonization techniques: mean shift, ComBat, and CycleGAN. The sample comprises 168 age-matched, sex-matched normal subjects from two studies: the Vanderbilt Memory and Aging Project (VMAP) and the Biomarkers of Cognitive Decline Among Normal Individuals (BIOCARD). First, we plotted the graph measures and used coefficient of variation (CoV) and the Mann-Whitney U test to evaluate different methods' effectiveness in removing site effects on the matrices and the derived graph measures. ComBat effectively eliminated site effects for global efficiency and modularity and outperformed the other two methods. However, all methods exhibited poor performance when harmonizing average betweenness centrality. Second, we tested whether our harmonization methods preserved correlations between age and graph measures. All methods except for CycleGAN in one direction improved correlations between age and global efficiency and between age and modularity from insignificant to significant with p-values less than 0.05.
Collapse
Affiliation(s)
- Hanliang Xu
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | - Nancy R Newlin
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | - Michael E Kim
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | - Chenyu Gao
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
| | | | - Aravind R Krishnan
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
| | - Lucas W Remedios
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | - Nazirah Mohd Khairi
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
| | - Kimberly Pechman
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Derek Archer
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA
- Vanderbilt Genetics Institute, Vanderbilt University School of Medicine, Nashville, TN, USA
| | - Timothy J Hohman
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA
- Vanderbilt Genetics Institute, Vanderbilt University School of Medicine, Nashville, TN, USA
| | - Angela L Jefferson
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Medicine, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Ivana Isgum
- Department of Biomedical Engineering and Physics & Radiology and Nuclear Medicine, University Medical Center Amsterdam, University of Amsterdam, Amsterdam, the Netherlands
| | - Yuankai Huo
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
| | - Daniel Moyer
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | - Kurt G Schilling
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
- Vanderbilt University Institute of Imaging Science, Vanderbilt University, Nashville, TN, USA
| | - Bennett A Landman
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
- Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA
- Vanderbilt University Institute of Imaging Science, Vanderbilt University, Nashville, TN, USA
- Department of Biomedical Engineering, Vanderbilt University, Nashville, TN, USA
| |
Collapse
|
21
|
Xu H, Newlin NR, Kim ME, Gao C, Kanakaraj P, Krishnan AR, Remedios LW, Khairi NM, Pechman K, Archer D, Hohman TJ, Jefferson AL, Isgum I, Huo Y, Moyer D, Schilling KG, Landman BA. Evaluation of Mean Shift, ComBat, and CycleGAN for Harmonizing Brain Connectivity Matrices Across Sites. ARXIV 2024:arXiv:2401.06798v2. [PMID: 38344221 PMCID: PMC10854272] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Figures] [Subscribe] [Scholar Register] [Indexed: 02/17/2024]
Abstract
Connectivity matrices derived from diffusion MRI (dMRI) provide an interpretable and generalizable way of understanding the human brain connectome. However, dMRI suffers from inter-site and between-scanner variation, which impedes analysis across datasets to improve robustness and reproducibility of results. To evaluate different harmonization approaches on connectivity matrices, we compared graph measures derived from these matrices before and after applying three harmonization techniques: mean shift, ComBat, and CycleGAN. The sample comprises 168 age-matched, sex-matched normal subjects from two studies: the Vanderbilt Memory and Aging Project (VMAP) and the Biomarkers of Cognitive Decline Among Normal Individuals (BIOCARD). First, we plotted the graph measures and used coefficient of variation (CoV) and the Mann-Whitney U test to evaluate different methods' effectiveness in removing site effects on the matrices and the derived graph measures. ComBat effectively eliminated site effects for global efficiency and modularity and outperformed the other two methods. However, all methods exhibited poor performance when harmonizing average betweenness centrality. Second, we tested whether our harmonization methods preserved correlations between age and graph measures. All methods except for CycleGAN in one direction improved correlations between age and global efficiency and between age and modularity from insignificant to significant with p-values less than 0.05.
Collapse
Affiliation(s)
- Hanliang Xu
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | - Nancy R Newlin
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | - Michael E Kim
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | - Chenyu Gao
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
| | | | - Aravind R Krishnan
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
| | - Lucas W Remedios
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | - Nazirah Mohd Khairi
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
| | - Kimberly Pechman
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Derek Archer
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA
- Vanderbilt Genetics Institute, Vanderbilt University School of Medicine, Nashville, TN, USA
| | - Timothy J Hohman
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA
- Vanderbilt Genetics Institute, Vanderbilt University School of Medicine, Nashville, TN, USA
| | - Angela L Jefferson
- Vanderbilt Memory and Alzheimer's Center, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA
- Department of Medicine, Vanderbilt University Medical Center, Nashville, TN, USA
| | - Ivana Isgum
- Department of Biomedical Engineering and Physics & Radiology and Nuclear Medicine, University Medical Center Amsterdam, University of Amsterdam, Amsterdam, the Netherlands
| | - Yuankai Huo
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
| | - Daniel Moyer
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
| | - Kurt G Schilling
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
- Vanderbilt University Institute of Imaging Science, Vanderbilt University, Nashville, TN, USA
| | - Bennett A Landman
- Department of Computer Science, Vanderbilt University, Nashville, TN, USA
- Department of Electrical and Computer Engineering, Vanderbilt University, Nashville, TN, USA
- Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA
- Vanderbilt University Institute of Imaging Science, Vanderbilt University, Nashville, TN, USA
- Department of Biomedical Engineering, Vanderbilt University, Nashville, TN, USA
| |
Collapse
|
22
|
Marzi C, Giannelli M, Barucci A, Tessa C, Mascalchi M, Diciotti S. Efficacy of MRI data harmonization in the age of machine learning: a multicenter study across 36 datasets. Sci Data 2024; 11:115. [PMID: 38263181 PMCID: PMC10805868 DOI: 10.1038/s41597-023-02421-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2022] [Accepted: 07/27/2023] [Indexed: 01/25/2024] Open
Abstract
Pooling publicly-available MRI data from multiple sites allows to assemble extensive groups of subjects, increase statistical power, and promote data reuse with machine learning techniques. The harmonization of multicenter data is necessary to reduce the confounding effect associated with non-biological sources of variability in the data. However, when applied to the entire dataset before machine learning, the harmonization leads to data leakage, because information outside the training set may affect model building, and potentially falsely overestimate performance. We propose a 1) measurement of the efficacy of data harmonization; 2) harmonizer transformer, i.e., an implementation of the ComBat harmonization allowing its encapsulation among the preprocessing steps of a machine learning pipeline, avoiding data leakage by design. We tested these tools using brain T1-weighted MRI data from 1740 healthy subjects acquired at 36 sites. After harmonization, the site effect was removed or reduced, and we showed the data leakage effect in predicting individual age from MRI data, highlighting that introducing the harmonizer transformer into a machine learning pipeline allows for avoiding data leakage by design.
Collapse
Affiliation(s)
- Chiara Marzi
- Department of Statistics, Computer Science and Applications "Giuseppe Parenti", University of Florence, 50134, Florence, Italy
- "Nello Carrara" Institute of Applied Physics (IFAC), National Research Council (CNR), 50019, Sesto Fiorentino, Florence, Italy
| | - Marco Giannelli
- Unit of Medical Physics, Pisa University Hospital "Azienda Ospedaliero-Universitaria Pisana", 56126, Pisa, Italy
| | - Andrea Barucci
- "Nello Carrara" Institute of Applied Physics (IFAC), National Research Council (CNR), 50019, Sesto Fiorentino, Florence, Italy
| | - Carlo Tessa
- Radiology Unit Apuane e Lunigiana, Azienda USL Toscana Nord Ovest, 54100, Massa, Italy
| | - Mario Mascalchi
- Department of Experimental and Clinical Biomedical Sciences "Mario Serio", University of Florence, 50139, Florence, Italy
- Division of Epidemiology and Clinical Governance, Institute for Study, Prevention and netwoRk in Oncology (ISPRO), 50139, Florence, Italy
| | - Stefano Diciotti
- Department of Electrical, Electronic, and Information Engineering "Guglielmo Marconi" - DEI, University of Bologna, 47522, Cesena, Italy.
- Alma Mater Research Institute for Human-Centered Artificial Intelligence, University of Bologna, 40121, Bologna, Italy.
| |
Collapse
|
23
|
Coffman C, Feczko E, Larsen B, Tervo-Clemmens B, Conan G, Lundquist JT, Houghton A, Moore LA, Weldon K, McCollum R, Perrone AJ, Fayzullobekova B, Madison TJ, Earl E, Dominguez OM, Fair DA, Basu S. Heritability estimation of subcortical volumes in a multi-ethnic multi-site cohort study. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2024:2024.01.11.575231. [PMID: 38260520 PMCID: PMC10802572 DOI: 10.1101/2024.01.11.575231] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/24/2024]
Abstract
Heritability of regional subcortical brain volumes (rSBVs) describes the role of genetics in middle and inner brain development. rSBVs are highly heritable in adults but are not characterized well in adolescents. The Adolescent Brain Cognitive Development study (ABCD), taken over 22 US sites, provides data to characterize the heritability of subcortical structures in adolescence. In ABCD, site-specific effects co-occur with genetic effects which can bias heritability estimates. Existing methods adjusting for site effects require additional steps to adjust for site effects and can lead to inconsistent estimation. We propose a random-effect model-based method of moments approach that is a single step estimator and is a theoretically consistent estimator even when sites are imbalanced and performs well under simulations. We compare methods on rSBVs from ABCD. The proposed approach yielded heritability estimates similar to previous results derived from single-site studies. The cerebellum cortex and hippocampus were the most heritable regions (> 50%).
Collapse
Affiliation(s)
- Christian Coffman
- Division of Biostatistics, University of Minnesota, 100 Church Street SE, Minneapolis, 55455-0213, MN, USA
| | - Eric Feczko
- Department of Pediatrics, University of Minnesota, 100 Church Street SE, Minneapolis, 55455-0213, MN, USA
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Bart Larsen
- Department of Pediatrics, University of Minnesota, 100 Church Street SE, Minneapolis, 55455-0213, MN, USA
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Brenden Tervo-Clemmens
- Department of Psychiatry & Behavioral Sciences, University of Minnesota, 100 Church Street SE, Minneapolis, 55455-0213, MN, USA
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Gregory Conan
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Jacob T. Lundquist
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Audrey Houghton
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Lucille A. Moore
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Kimberly Weldon
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Rae McCollum
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Anders J. Perrone
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Begim Fayzullobekova
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Thomas J. Madison
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Eric Earl
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Oscar Miranda Dominguez
- Department of Pediatrics, University of Minnesota, 100 Church Street SE, Minneapolis, 55455-0213, MN, USA
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Damien A. Fair
- Department of Pediatrics, University of Minnesota, 100 Church Street SE, Minneapolis, 55455-0213, MN, USA
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| | - Saonli Basu
- Division of Biostatistics, University of Minnesota, 100 Church Street SE, Minneapolis, 55455-0213, MN, USA
- Masonic Institue for the Devloping Brain, University of Minnesota, 2025 East River Parkway, Minneapolis, 55414, MN, USA
| |
Collapse
|
24
|
Van Dyken PC, MacKinley M, Khan AR, Palaniyappan L. Cortical Network Disruption Is Minimal in Early Stages of Psychosis. SCHIZOPHRENIA BULLETIN OPEN 2024; 5:sgae010. [PMID: 39144115 PMCID: PMC11207789 DOI: 10.1093/schizbullopen/sgae010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Indexed: 08/16/2024]
Abstract
Background and Hypothesis Schizophrenia is associated with white matter disruption and topological reorganization of cortical connectivity but the trajectory of these changes, from the first psychotic episode to established illness, is poorly understood. Current studies in first-episode psychosis (FEP) patients using diffusion magnetic resonance imaging (dMRI) suggest such disruption may be detectable at the onset of psychosis, but specific results vary widely, and few reports have contextualized their findings with direct comparison to young adults with established illness. Study Design Diffusion and T1-weighted 7T MR scans were obtained from N = 112 individuals (58 with untreated FEP, 17 with established schizophrenia, 37 healthy controls) recruited from London, Ontario. Voxel- and network-based analyses were used to detect changes in diffusion microstructural parameters. Graph theory metrics were used to probe changes in the cortical network hierarchy and to assess the vulnerability of hub regions to disruption. The analysis was replicated with N = 111 (57 patients, 54 controls) from the Human Connectome Project-Early Psychosis (HCP-EP) dataset. Study Results Widespread microstructural changes were found in people with established illness, but changes in FEP patients were minimal. Unlike the established illness group, no appreciable topological changes in the cortical network were observed in FEP patients. These results were replicated in the early psychosis patients of the HCP-EP datasets, which were indistinguishable from controls in most metrics. Conclusions The white matter structural changes observed in established schizophrenia are not a prominent feature in the early stages of this illness.
Collapse
Affiliation(s)
- Peter C Van Dyken
- Neuroscience Graduate Program, Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
| | - Michael MacKinley
- Lawson Health Research Institute, London Health Sciences Centre, London, ON, Canada
| | - Ali R Khan
- Robarts Research Institute, Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
- Department of Medical Biophysics, Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
| | - Lena Palaniyappan
- Robarts Research Institute, Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
- Department of Medical Biophysics, Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
- Department of Psychiatry, Douglas Mental Health University Institute, McGill University, London, ON, Canada
- Department of Psychiatry, Schulich School of Medicine and Dentistry, Western University, London, ON, Canada
| |
Collapse
|
25
|
Yao T, Rheault F, Cai LY, Nath V, Asad Z, Newlin N, Cui C, Deng R, Ramadass K, Shafer A, Resnick S, Schilling K, Landman BA, Huo Y. Robust fiber orientation distribution function estimation using deep constrained spherical deconvolution for diffusion-weighted magnetic resonance imaging. J Med Imaging (Bellingham) 2024; 11:014005. [PMID: 38188934 PMCID: PMC10768686 DOI: 10.1117/1.jmi.11.1.014005] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/09/2023] [Revised: 11/04/2023] [Accepted: 12/14/2023] [Indexed: 01/09/2024] Open
Abstract
Purpose Diffusion-weighted magnetic resonance imaging (DW-MRI) is a critical imaging method for capturing and modeling tissue microarchitecture at a millimeter scale. A common practice to model the measured DW-MRI signal is via fiber orientation distribution function (fODF). This function is the essential first step for the downstream tractography and connectivity analyses. With recent advantages in data sharing, large-scale multisite DW-MRI datasets are being made available for multisite studies. However, measurement variabilities (e.g., inter- and intrasite variability, hardware performance, and sequence design) are inevitable during the acquisition of DW-MRI. Most existing model-based methods [e.g., constrained spherical deconvolution (CSD)] and learning-based methods (e.g., deep learning) do not explicitly consider such variabilities in fODF modeling, which consequently leads to inferior performance on multisite and/or longitudinal diffusion studies. Approach In this paper, we propose a data-driven deep CSD method to explicitly constrain the scan-rescan variabilities for a more reproducible and robust estimation of brain microstructure from repeated DW-MRI scans. Specifically, the proposed method introduces a three-dimensional volumetric scanner-invariant regularization scheme during the fODF estimation. We study the Human Connectome Project (HCP) young adults test-retest group as well as the MASiVar dataset (with inter- and intrasite scan/rescan data). The Baltimore Longitudinal Study of Aging dataset is employed for external validation. Results From the experimental results, the proposed data-driven framework outperforms the existing benchmarks in repeated fODF estimation. By introducing the contrastive loss with scan/rescan data, the proposed method achieved a higher consistency while maintaining higher angular correlation coefficients with the CSD modeling. The proposed method is assessing the downstream connectivity analysis and shows increased performance in distinguishing subjects with different biomarkers. Conclusion We propose a deep CSD method to explicitly reduce the scan-rescan variabilities, so as to model a more reproducible and robust brain microstructure from repeated DW-MRI scans. The plug-and-play design of the proposed approach is potentially applicable to a wider range of data harmonization problems in neuroimaging.
Collapse
Affiliation(s)
- Tianyuan Yao
- Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States
| | - Francois Rheault
- Université de Sherbrooke, Department of Computer Science, Sherbrooke, Québec, Canada
| | - Leon Y. Cai
- Vanderbilt University, Department of Biomedical Engineering, Nashville, Tennessee, United States
| | - Vishwesh Nath
- NVIDIA Corporation, Bethesda, Maryland, United States
| | - Zuhayr Asad
- Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States
| | - Nancy Newlin
- Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States
| | - Can Cui
- Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States
| | - Ruining Deng
- Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States
| | - Karthik Ramadass
- Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States
| | - Andrea Shafer
- National Institute on Aging, Laboratory of Behavioral Neuroscience, Baltimore, Maryland, United States
| | - Susan Resnick
- National Institute on Aging, Laboratory of Behavioral Neuroscience, Baltimore, Maryland, United States
| | - Kurt Schilling
- Vanderbilt University, Department of Biomedical Engineering, Nashville, Tennessee, United States
| | - Bennett A. Landman
- Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States
- Vanderbilt University, Department of Biomedical Engineering, Nashville, Tennessee, United States
- Vanderbilt University, Department of Electrical and Computer Engineering, Nashville, Tennessee, United States
| | - Yuankai Huo
- Vanderbilt University, Department of Computer Science, Nashville, Tennessee, United States
- Vanderbilt University, Department of Electrical and Computer Engineering, Nashville, Tennessee, United States
| |
Collapse
|
26
|
Mito R, Pedersen M, Pardoe H, Parker D, Smith RE, Cameron J, Scheffer IE, Berkovic SF, Vaughan DN, Jackson GD. Exploring individual fixel-based white matter abnormalities in epilepsy. Brain Commun 2023; 6:fcad352. [PMID: 38187877 PMCID: PMC10768884 DOI: 10.1093/braincomms/fcad352] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2023] [Revised: 11/02/2023] [Accepted: 12/21/2023] [Indexed: 01/09/2024] Open
Abstract
Diffusion MRI has provided insight into the widespread structural connectivity changes that characterize epilepsies. Although syndrome-specific white matter abnormalities have been demonstrated, studies to date have predominantly relied on statistical comparisons between patient and control groups. For diffusion MRI techniques to be of clinical value, they should be able to detect white matter microstructural changes in individual patients. In this study, we apply an individualized approach to a technique known as fixel-based analysis, to examine fibre-tract-specific abnormalities in individuals with epilepsy. We explore the potential clinical value of this individualized fixel-based approach in epilepsy patients with differing syndromic diagnoses. Diffusion MRI data from 90 neurologically healthy control participants and 10 patients with epilepsy (temporal lobe epilepsy, progressive myoclonus epilepsy, and Dravet Syndrome, malformations of cortical development) were included in this study. Measures of fibre density and cross-section were extracted for all participants across brain white matter fixels, and mean values were computed within select tracts-of-interest. Scanner harmonized and normalized data were then used to compute Z-scores for individual patients with epilepsy. White matter abnormalities were observed in distinct patterns in individual patients with epilepsy, both at the tract and fixel level. For patients with specific epilepsy syndromes, the detected white matter abnormalities were in line with expected syndrome-specific clinical phenotypes. In patients with lesional epilepsies (e.g. hippocampal sclerosis, periventricular nodular heterotopia, and bottom-of-sulcus dysplasia), white matter abnormalities were spatially concordant with lesion location. This proof-of-principle study demonstrates the clinical potential of translating advanced diffusion MRI methodology to individual-patient-level use in epilepsy. This technique could be useful both in aiding diagnosis of specific epilepsy syndromes, and in localizing structural abnormalities, and is readily amenable to other neurological disorders. We have included code and data for this study so that individualized white matter changes can be explored robustly in larger cohorts in future work.
Collapse
Affiliation(s)
- Remika Mito
- Florey Institute of Neuroscience and Mental Health, Heidelberg, Victoria 3084, Australia
- Florey Department of Neuroscience and Mental Health, University of Melbourne, Melbourne, Victoria 3010, Australia
| | - Mangor Pedersen
- Florey Institute of Neuroscience and Mental Health, Heidelberg, Victoria 3084, Australia
- Department of Psychology and Neuroscience, Auckland University of Technology (AUT), Auckland 1142, New Zealand
| | - Heath Pardoe
- Florey Institute of Neuroscience and Mental Health, Heidelberg, Victoria 3084, Australia
| | - Donna Parker
- Florey Institute of Neuroscience and Mental Health, Heidelberg, Victoria 3084, Australia
| | - Robert E Smith
- Florey Institute of Neuroscience and Mental Health, Heidelberg, Victoria 3084, Australia
- Florey Department of Neuroscience and Mental Health, University of Melbourne, Melbourne, Victoria 3010, Australia
| | - Jillian Cameron
- Epilepsy Research Centre, Department of Medicine, University of Melbourne, Austin Health, Heidelberg, Victoria 3084, Australia
| | - Ingrid E Scheffer
- Epilepsy Research Centre, Department of Medicine, University of Melbourne, Austin Health, Heidelberg, Victoria 3084, Australia
| | - Samuel F Berkovic
- Epilepsy Research Centre, Department of Medicine, University of Melbourne, Austin Health, Heidelberg, Victoria 3084, Australia
| | - David N Vaughan
- Florey Institute of Neuroscience and Mental Health, Heidelberg, Victoria 3084, Australia
- Florey Department of Neuroscience and Mental Health, University of Melbourne, Melbourne, Victoria 3010, Australia
- Department of Neurology, Austin Health, Heidelberg, Victoria 3084, Australia
| | - Graeme D Jackson
- Florey Institute of Neuroscience and Mental Health, Heidelberg, Victoria 3084, Australia
- Florey Department of Neuroscience and Mental Health, University of Melbourne, Melbourne, Victoria 3010, Australia
- Department of Neurology, Austin Health, Heidelberg, Victoria 3084, Australia
| |
Collapse
|
27
|
Kaļva K, Zdanovskis N, Šneidere K, Kostiks A, Karelis G, Platkājis A, Stepens A. Whole Brain and Corpus Callosum Fractional Anisotropy Differences in Patients with Cognitive Impairment. Diagnostics (Basel) 2023; 13:3679. [PMID: 38132263 PMCID: PMC10742911 DOI: 10.3390/diagnostics13243679] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/31/2023] [Revised: 11/20/2023] [Accepted: 12/14/2023] [Indexed: 12/23/2023] Open
Abstract
Diffusion tensor imaging (DTI) is an MRI analysis method that could help assess cognitive impairment (CI) in the ageing population more accurately. In this research, we evaluated fractional anisotropy (FA) of whole brain (WB) and corpus callosum (CC) in patients with normal cognition (NC), mild cognitive impairment (MCI), and moderate/severe cognitive impairment (SCI). In total, 41 participants were included in a cross-sectional study and divided into groups based on Montreal Cognitive Assessment (MoCA) scores (NC group, nine participants, MCI group, sixteen participants, and SCI group, sixteen participants). All participants underwent an MRI examination that included a DTI sequence. FA values between the groups were assessed by analysing FA value and age normative percentile. We did not find statistically significant differences between the groups when analysing CC FA values. Both approaches showed statistically significant differences in WB FA values between the MCI-SCI and MCI-NC groups, where the MCI group participants showed the highest mean FA and highest mean FA normative percentile results in WB.
Collapse
Affiliation(s)
- Kalvis Kaļva
- Department of Radiology, Riga Stradins University, LV-1007 Riga, Latvia; (K.K.)
- Department of Radiology, Riga East Clinical University Hospital, LV-1038 Riga, Latvia
| | - Nauris Zdanovskis
- Department of Radiology, Riga Stradins University, LV-1007 Riga, Latvia; (K.K.)
- Department of Radiology, Riga East Clinical University Hospital, LV-1038 Riga, Latvia
- Military Medicine Research and Study Centre, Riga Stradins University, LV-1007 Riga, Latvia
| | - Kristīne Šneidere
- Military Medicine Research and Study Centre, Riga Stradins University, LV-1007 Riga, Latvia
- Department of Health Psychology and Paedagogy, Riga Stradins University, LV-1007 Riga, Latvia
| | - Andrejs Kostiks
- Department of Neurology and Neurosurgery, Riga East University Hospital, LV-1038 Riga, Latvia; (A.K.)
| | - Guntis Karelis
- Department of Neurology and Neurosurgery, Riga East University Hospital, LV-1038 Riga, Latvia; (A.K.)
- Department of Infectology, Riga Stradins University, LV-1007 Riga, Latvia
| | - Ardis Platkājis
- Department of Radiology, Riga Stradins University, LV-1007 Riga, Latvia; (K.K.)
- Department of Radiology, Riga East Clinical University Hospital, LV-1038 Riga, Latvia
| | - Ainārs Stepens
- Military Medicine Research and Study Centre, Riga Stradins University, LV-1007 Riga, Latvia
| |
Collapse
|
28
|
Qu Y, Wang P, Yao H, Wang D, Song C, Yang H, Zhang Z, Chen P, Kang X, Du K, Fan L, Zhou B, Han T, Yu C, Zhang X, Zuo N, Jiang T, Zhou Y, Liu B, Han Y, Lu J, Liu Y. Reproducible Abnormalities and Diagnostic Generalizability of White Matter in Alzheimer's Disease. Neurosci Bull 2023; 39:1533-1543. [PMID: 37014553 PMCID: PMC10533766 DOI: 10.1007/s12264-023-01041-w] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/29/2022] [Accepted: 11/29/2022] [Indexed: 04/05/2023] Open
Abstract
Alzheimer's disease (AD) is associated with the impairment of white matter (WM) tracts. The current study aimed to verify the utility of WM as the neuroimaging marker of AD with multisite diffusion tensor imaging datasets [321 patients with AD, 265 patients with mild cognitive impairment (MCI), 279 normal controls (NC)], a unified pipeline, and independent site cross-validation. Automated fiber quantification was used to extract diffusion profiles along tracts. Random-effects meta-analyses showed a reproducible degeneration pattern in which fractional anisotropy significantly decreased in the AD and MCI groups compared with NC. Machine learning models using tract-based features showed good generalizability among independent site cross-validation. The diffusion metrics of the altered regions and the AD probability predicted by the models were highly correlated with cognitive ability in the AD and MCI groups. We highlighted the reproducibility and generalizability of the degeneration pattern of WM tracts in AD.
Collapse
Affiliation(s)
- Yida Qu
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Pan Wang
- Department of Neurology, Tianjin Huanhu Hospital, Tianjin University, Tianjin, 300222, China
| | - Hongxiang Yao
- Department of Neurology, Tianjin Huanhu Hospital, Tianjin University, Tianjin, 300222, China
| | - Dawei Wang
- Department of Radiology, Department of Epidemiology and Health Statistics, School of Public Health, Qilu Hospital of Shandong University, Ji'nan, 250063, China
| | - Chengyuan Song
- Department of Neurology, Qilu Hospital of Shandong University, Ji'nan, 250063, China
| | - Hongwei Yang
- Department of Radiology, Xuanwu Hospital of Capital Medical University, Beijing, 100053, China
| | - Zengqiang Zhang
- Branch of Chinese, PLA General Hospital, Sanya, 572022, China
| | - Pindong Chen
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Xiaopeng Kang
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Kai Du
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Lingzhong Fan
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Bo Zhou
- Department of Neurology, The Second Medical Centre, National Clinical Research Centre for Geriatric Diseases, Chinese PLA General Hospital, Beijing, 100089, China
| | - Tong Han
- Department of Radiology, Tianjin Huanhu Hospital, Tianjin, 300222, China
| | - Chunshui Yu
- Department of Radiology, Tianjin Medical University General Hospital, Tianjin, 300052, China
| | - Xi Zhang
- Department of Neurology, The Second Medical Centre, National Clinical Research Centre for Geriatric Diseases, Chinese PLA General Hospital, Beijing, 100089, China
| | - Nianming Zuo
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Tianzi Jiang
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China
| | - Yuying Zhou
- Department of Neurology, Tianjin Huanhu Hospital, Tianjin University, Tianjin, 300222, China
| | - Bing Liu
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
- School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, 100049, China
- State Key Lab of Cognition Neuroscience & Learning, Beijing Normal University, Beijing, 100091, China
| | - Ying Han
- Department of Neurology, Xuanwu Hospital of Capital Medical University, Beijing, 100053, China
- Beijing Institute of Geriatrics, Beijing, 100053, China
- National Clinical Research Center for Geriatric Disorders, Beijing, 100053, China
- Center of Alzheimer's Disease, Beijing Institute for Brain Disorders, Beijing, 100053, China
| | - Jie Lu
- Department of Radiology, Xuanwu Hospital of Capital Medical University, Beijing, 100053, China.
| | - Yong Liu
- Brainnetome Center and National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China.
- School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, 100876, China.
| |
Collapse
|
29
|
Newman BT, Patrie JT, Druzgal TJ. An intracellular isotropic diffusion signal is positively associated with pubertal development in white matter. Dev Cogn Neurosci 2023; 63:101301. [PMID: 37717292 PMCID: PMC10511341 DOI: 10.1016/j.dcn.2023.101301] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2023] [Revised: 08/14/2023] [Accepted: 09/13/2023] [Indexed: 09/19/2023] Open
Abstract
Puberty is a key event in adolescent development that involves significant, hormone-driven changes to many aspects of physiology including the brain. Understanding how the brain responds during this time period is important for evaluating neuronal developments that affect mental health throughout adolescence and the adult lifespan. This study examines diffusion MRI scans from the cross-sectional ABCD Study baseline cohort, a large multi-site study containing thousands of participants, to describe the relationship between pubertal development and brain microstructure. Using advanced, 3-tissue constrained spherical deconvolution methods, this study is able to describe multiple tissue compartments beyond only white matter (WM) axonal qualities. After controlling for age, sex, brain volume, subject handedness, scanning site, and sibling relationships, we observe a positive relationship between an isotropic, intracellular diffusion signal fraction and pubertal development across a majority of regions of interest (ROIs) in the WM skeleton. We also observe regional effects from an intracellular anisotropic signal fraction compartment and extracellular isotropic free water-like compartment in several ROIs. This cross-sectional work suggests that changes in pubertal status are associated with a complex response from brain tissue that cannot be completely described by traditional methods focusing only on WM axonal properties.
Collapse
Affiliation(s)
- Benjamin T Newman
- Department of Radiology and Medical Imaging, School of Medicine, University of Virginia, USA.
| | - James T Patrie
- Department of Public Health Sciences, School of Medicine, University of Virginia, USA
| | - T Jason Druzgal
- Department of Radiology and Medical Imaging, School of Medicine, University of Virginia, USA
| |
Collapse
|
30
|
Yeow LY, Teh YX, Lu X, Srinivasa AC, Tan E, Tan TSE, Tang PH, Kn BP. Prediction of MYCN Gene Amplification in Pediatric Neuroblastomas: Development of a Deep Learning-Based Tool for Automatic Tumor Segmentation and Comparative Analysis of Computed Tomography-Based Radiomics Features Harmonization. J Comput Assist Tomogr 2023; 47:786-795. [PMID: 37707410 DOI: 10.1097/rct.0000000000001480] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 06/03/2023]
Abstract
OBJECTIVE MYCN oncogene amplification is closely linked to high-grade neuroblastoma with poor prognosis. Accurate quantification is essential for risk assessment, which guides clinical decision making and disease management. This study proposes an end-to-end deep-learning framework for automatic tumor segmentation of pediatric neuroblastomas and radiomics features-based classification of MYCN gene amplification. METHODS Data from pretreatment contrast-enhanced computed tomography scans and MYCN status from 47 cases of pediatric neuroblastomas treated at a tertiary children's hospital from 2009 to 2020 were reviewed. Automated tumor segmentation and grading pipeline includes (1) a modified U-Net for tumor segmentation; (2) extraction of radiomic textural features; (3) feature-based ComBat harmonization for removal of variabilities across scanners; (4) feature selection using 2 approaches, namely, ( a ) an ensemble approach and ( b ) stepwise forward-and-backward selection method using logistic regression classifier; and (5) radiomics features-based classification of MYCN gene amplification using machine learning classifiers. RESULTS Median train/test Dice score for modified U-Net was 0.728/0.680. The top 3 features from the ensemble approach were neighborhood gray-tone difference matrix (NGTDM) busyness, NGTDM strength, and gray-level run-length matrix (GLRLM) low gray-level run emphasis, whereas those from the stepwise approach were GLRLM low gray-level run emphasis, GLRLM high gray-level run emphasis, and NGTDM coarseness. The top-performing tumor classification algorithm achieved a weighted F1 score of 97%, an area under the receiver operating characteristic curve of 96.9%, an accuracy of 96.97%, and a negative predictive value of 100%. Harmonization-based tumor classification improved the accuracy by 2% to 3% for all classifiers. CONCLUSION The proposed end-to-end framework achieved high accuracy for MYCN gene amplification status classification.
Collapse
Affiliation(s)
- Ling Yun Yeow
- From the Bioinformatics Institute, Agency for Science, Technology and Research (A*STAR)
| | - Yu Xuan Teh
- Division of Mathematical Sciences, School of Physical and Mathematical Sciences, Nanyang Technological University
| | | | | | - Eelin Tan
- Department of Diagnostic & Interventional Imaging, KK Women's and Children's Hospital, Singapore, Singapore
| | - Timothy Shao Ern Tan
- Department of Diagnostic & Interventional Imaging, KK Women's and Children's Hospital, Singapore, Singapore
| | - Phua Hwee Tang
- Department of Diagnostic & Interventional Imaging, KK Women's and Children's Hospital, Singapore, Singapore
| | - Bhanu Prakash Kn
- From the Bioinformatics Institute, Agency for Science, Technology and Research (A*STAR)
| |
Collapse
|
31
|
Newlin NR, Kim ME, Kanakaraj P, Yao T, Hohman T, Pechman KR, Beason-Held LL, Resnick SM, Archer D, Jefferson A, Landman BA, Moyer D. MidRISH: Unbiased harmonization of rotationally invariant harmonics of the diffusion signal. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.08.12.553099. [PMID: 37645973 PMCID: PMC10462069 DOI: 10.1101/2023.08.12.553099] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/31/2023]
Abstract
Objective Data harmonization is necessary for removing confounding effects in multi-site diffusion image analysis. One such harmonization method, LinearRISH, scales rotationally invariant spherical harmonic (RISH) features from one site ("target") to the second ("reference") to reduce confounding scanner effects. However, reference and target site designations are not arbitrary and resultant diffusion metrics (fractional anisotropy, mean diffusivity) are biased by this choice. In this work we propose MidRISH: rather than scaling reference RISH features to target RISH features, we project both sites to a mid-space. Methods We validate MidRISH with the following experiments: harmonizing scanner differences from 37 matched patients free of cognitive impairment, and harmonizing acquisition and study differences on 117 matched patients free of cognitive impairment. Conclusion MidRISH reduces bias of reference selection while preserving harmonization efficacy of LinearRISH. Significance Users should be cautious when performing LinearRISH harmonization. To select a reference site is to choose diffusion metric effect-size. Our proposed method eliminates the bias-inducing site selection step.
Collapse
Affiliation(s)
- Nancy R Newlin
- Department of Computer Science at Vanderbilt University, Nashville, TN, USA
| | - Michael E Kim
- Department of Computer Science at Vanderbilt University, Nashville, TN, USA
| | | | - Tianyuan Yao
- Department of Computer Science at Vanderbilt University, Nashville, TN, USA
| | - Timothy Hohman
- VMAC, VUMC, Nashville, TN, USA and Vanderbilt University, Nashville, TN, USA
| | | | - Lori L Beason-Held
- Laboratory of Behavioral Neuroscience, National Institute on Aging, National Institutes of Health, Baltimore, MD, USA
| | - Susan M Resnick
- Laboratory of Behavioral Neuroscience, National Institute on Aging, National Institutes of Health, Baltimore, MD, USA
| | - Derek Archer
- VMAC, VUMC, Nashville, TN, USA and Vanderbilt University, Nashville, TN, USA
| | - Angela Jefferson
- VMAC, VUMC, Nashville, TN, USA and Vanderbilt University, Nashville, TN, USA
| | - Bennett A Landman
- Department of Computer Science at Vanderbilt University, Nashville, TN, USA
| | - Daniel Moyer
- Department of Computer Science at Vanderbilt University, Nashville, TN, USA
| |
Collapse
|
32
|
Xu H, Hao Y, Zhang Y, Zhou D, Kärkkäinen T, Nickerson LD, Li H, Cong F. Harmonization of multi-site functional MRI data with dual-projection based ICA model. Front Neurosci 2023; 17:1225606. [PMID: 37547146 PMCID: PMC10401882 DOI: 10.3389/fnins.2023.1225606] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/19/2023] [Accepted: 07/06/2023] [Indexed: 08/08/2023] Open
Abstract
Modern neuroimaging studies frequently merge magnetic resonance imaging (MRI) data from multiple sites. A larger and more diverse group of participants can increase the statistical power, enhance the reliability and reproducibility of neuroimaging research, and obtain findings more representative of the general population. However, measurement biases caused by site differences in scanners represent a barrier when pooling data collected from different sites. The existence of site effects can mask biological effects and lead to spurious findings. We recently proposed a powerful denoising strategy that implements dual-projection (DP) theory based on ICA to remove site-related effects from pooled data, demonstrating the method for simulated and in vivo structural MRI data. This study investigates the use of our DP-based ICA denoising method for harmonizing functional MRI (fMRI) data collected from the Autism Brain Imaging Data Exchange II. After frequency-domain and regional homogeneity analyses, two modalities, including amplitude of low frequency fluctuation (ALFF) and regional homogeneity (ReHo), were used to validate our method. The results indicate that DP-based ICA denoising method removes unwanted site effects for both two fMRI modalities, with increases in the significance of the associations between non-imaging variables (age, sex, etc.) and fMRI measures. In conclusion, our DP method can be applied to fMRI data in multi-site studies, enabling more accurate and reliable neuroimaging research findings.
Collapse
Affiliation(s)
- Huashuai Xu
- School of Biomedical Engineering, Dalian University of Technology, Dalian, China
- Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland
| | - Yuxing Hao
- School of Biomedical Engineering, Dalian University of Technology, Dalian, China
| | - Yunge Zhang
- School of Biomedical Engineering, Dalian University of Technology, Dalian, China
| | - Dongyue Zhou
- School of Biomedical Engineering, Dalian University of Technology, Dalian, China
| | - Tommi Kärkkäinen
- Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland
| | - Lisa D. Nickerson
- McLean Imaging Center, McLean Hospital, Belmont, MA, United States
- Department of Psychiatry, Harvard Medical School, Boston, MA, United States
| | - Huanjie Li
- School of Biomedical Engineering, Dalian University of Technology, Dalian, China
| | - Fengyu Cong
- School of Biomedical Engineering, Dalian University of Technology, Dalian, China
- Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland
- School of Artificial Intelligence, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China
- Key Laboratory of Integrated Circuit and Biomedical Electronic System, Dalian University of Technology, Dalian, China
| |
Collapse
|
33
|
Dipietro L, Gonzalez-Mego P, Ramos-Estebanez C, Zukowski LH, Mikkilineni R, Rushmore RJ, Wagner T. The evolution of Big Data in neuroscience and neurology. JOURNAL OF BIG DATA 2023; 10:116. [PMID: 37441339 PMCID: PMC10333390 DOI: 10.1186/s40537-023-00751-2] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 01/28/2023] [Accepted: 05/08/2023] [Indexed: 07/15/2023]
Abstract
Neurological diseases are on the rise worldwide, leading to increased healthcare costs and diminished quality of life in patients. In recent years, Big Data has started to transform the fields of Neuroscience and Neurology. Scientists and clinicians are collaborating in global alliances, combining diverse datasets on a massive scale, and solving complex computational problems that demand the utilization of increasingly powerful computational resources. This Big Data revolution is opening new avenues for developing innovative treatments for neurological diseases. Our paper surveys Big Data's impact on neurological patient care, as exemplified through work done in a comprehensive selection of areas, including Connectomics, Alzheimer's Disease, Stroke, Depression, Parkinson's Disease, Pain, and Addiction (e.g., Opioid Use Disorder). We present an overview of research and the methodologies utilizing Big Data in each area, as well as their current limitations and technical challenges. Despite the potential benefits, the full potential of Big Data in these fields currently remains unrealized. We close with recommendations for future research aimed at optimizing the use of Big Data in Neuroscience and Neurology for improved patient outcomes. Supplementary Information The online version contains supplementary material available at 10.1186/s40537-023-00751-2.
Collapse
Affiliation(s)
| | - Paola Gonzalez-Mego
- Spaulding Rehabilitation/Neuromodulation Lab, Harvard Medical School, Cambridge, MA USA
| | | | | | | | | | - Timothy Wagner
- Highland Instruments, Cambridge, MA USA
- Harvard-MIT Division of Health Sciences and Technology, Cambridge, MA USA
| |
Collapse
|
34
|
Kebiri H, Gholipour A, Vasung L, Krsnik Ž, Karimi D, Cuadra MB. Deep learning microstructure estimation of developing brains from diffusion MRI: a newborn and fetal study. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.07.01.547351. [PMID: 37425859 PMCID: PMC10327173 DOI: 10.1101/2023.07.01.547351] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/11/2023]
Abstract
Diffusion-weighted magnetic resonance imaging (dMRI) is widely used to assess the brain white matter. Fiber orientation distribution functions (FODs) are a common way of representing the orientation and density of white matter fibers. However, with standard FOD computation methods, accurate estimation of FODs requires a large number of measurements that usually cannot be acquired for newborns and fetuses. We propose to overcome this limitation by using a deep learning method to map as few as six diffusion-weighted measurements to the target FOD. To train the model, we use the FODs computed using multi-shell high angular resolution measurements as target. Extensive quantitative evaluations show that the new deep learning method, using significantly fewer measurements, achieves comparable or superior results to standard methods such as Constrained Spherical Deconvolution. We demonstrate the generalizability of the new deep learning method across scanners, acquisition protocols, and anatomy on two clinical datasets of newborns and fetuses. Additionally, we compute agreement metrics within the HARDI newborn dataset, and validate fetal FODs with post-mortem histological data. The results of this study show the advantage of deep learning in inferring the microstructure of the developing brain from in-vivo dMRI measurements that are often very limited due to subject motion and limited acquisition times, but also highlight the intrinsic limitations of dMRI in the analysis of the developing brain microstructure. These findings, therefore, advocate for the need for improved methods that are tailored to studying the early development of human brain.
Collapse
Affiliation(s)
- Hamza Kebiri
- CIBM Center for Biomedical Imaging, Switzerland
- Department of Radiology, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
- Computational Radiology Laboratory, Department of Radiology, Boston Children's Hospital and Harvard Medical School, Boston, Massachusetts, USA
| | - Ali Gholipour
- Computational Radiology Laboratory, Department of Radiology, Boston Children's Hospital and Harvard Medical School, Boston, Massachusetts, USA
| | - Lana Vasung
- Department of Pediatrics, Boston Children's Hospital, and Harvard Medical School, Boston, Massachusetts, USA
| | - Željka Krsnik
- Croatian Institute for Brain Research, School of Medicine, University of Zagreb, Zagreb, Croatia
| | - Davood Karimi
- Computational Radiology Laboratory, Department of Radiology, Boston Children's Hospital and Harvard Medical School, Boston, Massachusetts, USA
| | - Meritxell Bach Cuadra
- CIBM Center for Biomedical Imaging, Switzerland
- Department of Radiology, Lausanne University Hospital (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland
| |
Collapse
|
35
|
Siqueira Pinto M, Winzeck S, Kornaropoulos EN, Richter S, Paolella R, Correia MM, Glocker B, Williams G, Vik A, Posti JP, Haberg A, Stenberg J, Guns PJ, den Dekker AJ, Menon DK, Sijbers J, Van Dyck P, Newcombe VFJ. Use of Support Vector Machines Approach via ComBat Harmonized Diffusion Tensor Imaging for the Diagnosis and Prognosis of Mild Traumatic Brain Injury: A CENTER-TBI Study. J Neurotrauma 2023; 40:1317-1338. [PMID: 36974359 DOI: 10.1089/neu.2022.0365] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 03/29/2023] Open
Abstract
The prediction of functional outcome after mild traumatic brain injury (mTBI) is challenging. Conventional magnetic resonance imaging (MRI) does not do a good job of explaining the variance in outcome, as many patients with incomplete recovery will have normal-appearing clinical neuroimaging. More advanced quantitative techniques such as diffusion MRI (dMRI), can detect microstructural changes not otherwise visible, and so may offer a way to improve outcome prediction. In this study, we explore the potential of linear support vector classifiers (linearSVCs) to identify dMRI biomarkers that can predict recovery after mTBI. Simultaneously, the harmonization of fractional anisotropy (FA) and mean diffusivity (MD) via ComBat was evaluated and compared for the classification performances of the linearSVCs. We included dMRI scans of 179 mTBI patients and 85 controls from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI), a multi-center prospective cohort study, up to 21 days post-injury. Patients were dichotomized according to their Extended Glasgow Outcome Scale (GOSE) scores at 6 months into complete (n = 92; GOSE = 8) and incomplete (n = 87; GOSE <8) recovery. FA and MD maps were registered to a common space and harmonized via the ComBat algorithm. LinearSVCs were applied to distinguish: (1) mTBI patients from controls and (2) mTBI patients with complete from those with incomplete recovery. The linearSVCs were trained on (1) age and sex only, (2) non-harmonized, (3) two-category-harmonized ComBat, and (4) three-category-harmonized ComBat FA and MD images combined with age and sex. White matter FA and MD voxels and regions of interest (ROIs) within the John Hopkins University (JHU) atlas were examined. Recursive feature elimination was used to identify the 10% most discriminative voxels or the 10 most discriminative ROIs for each implementation. mTBI patients displayed significantly higher MD and lower FA values than controls for the discriminative voxels and ROIs. For the analysis between mTBI patients and controls, the three-category-harmonized ComBat FA and MD voxel-wise linearSVC provided significantly higher classification scores (81.4% accuracy, 93.3% sensitivity, 80.3% F1-score, and 0.88 area under the curve [AUC], p < 0.05) compared with the classification based on age and sex only and the ROI approaches (accuracies: 59.8% and 64.8%, respectively). Similar to the analysis between mTBI patients and controls, the three-category-harmonized ComBat FA and MD maps voxelwise approach yields statistically significant prediction scores between mTBI patients with complete and those with incomplete recovery (71.8% specificity, 66.2% F1-score and 0.71 AUC, p < 0.05), which provided a modest increase in the classification score (accuracy: 66.4%) compared with the classification based on age and sex only and ROI-wise approaches (accuracy: 61.4% and 64.7%, respectively). This study showed that ComBat harmonized FA and MD may provide additional information for diagnosis and prognosis of mTBI in a multi-modal machine learning approach. These findings demonstrate that dMRI may assist in the early detection of patients at risk of incomplete recovery from mTBI.
Collapse
Affiliation(s)
- Maíra Siqueira Pinto
- Department of Radiology, Antwerp University Hospital, Antwerp, Belgium
- imec-Vision Lab, University of Antwerp, Antwerp, Belgium
- μNEURO Research Center of Excellence, University of Antwerp, Antwerp, Belgium
| | - Stefan Winzeck
- BioMedIA Group, Department of Computing, Imperial College London, London, United Kingdom
- Division of Anaesthesia, Department of Medicine, Department of Neurosciences, University of Cambridge, Cambridge, United Kingdom
| | - Evgenios N Kornaropoulos
- Division of Anaesthesia, Department of Medicine, Department of Neurosciences, University of Cambridge, Cambridge, United Kingdom
| | - Sophie Richter
- Division of Anaesthesia, Department of Medicine, Department of Neurosciences, University of Cambridge, Cambridge, United Kingdom
| | - Roberto Paolella
- imec-Vision Lab, University of Antwerp, Antwerp, Belgium
- μNEURO Research Center of Excellence, University of Antwerp, Antwerp, Belgium
- Icometrix, Leuven, Belgium
| | - Marta M Correia
- MRC Cognition and Brain Sciences Unit, Department of Neurosciences, University of Cambridge, Cambridge, United Kingdom
| | - Ben Glocker
- BioMedIA Group, Department of Computing, Imperial College London, London, United Kingdom
| | - Guy Williams
- Wolfson Brain Imaging Centre, Department of Neurosciences, University of Cambridge, Cambridge, United Kingdom
| | - Anne Vik
- Department of Neuromedicine and Movement Science, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology (NTNU), Trondheim, Norway
- Department of Neurosurgery, St. Olavs Hospital, Trondheim University Hospital, Trondheim, Norway
| | - Jussi P Posti
- Department of Neurosurgery and Turku Brain Injury Center, Turku University Hospital and University of Turku, Turku, Finland
| | - Asta Haberg
- Department of Neuromedicine and Movement Science, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology (NTNU), Trondheim, Norway
- Department of Radiology and Nuclear Medicine, St. Olavs Hospital, Trondheim University Hospital, Trondheim, Norway
| | - Jonas Stenberg
- Department of Neuromedicine and Movement Science, Faculty of Medicine and Health Sciences, Norwegian University of Science and Technology (NTNU), Trondheim, Norway
- Department of Radiology and Nuclear Medicine, St. Olavs Hospital, Trondheim University Hospital, Trondheim, Norway
| | | | - Arnold J den Dekker
- imec-Vision Lab, University of Antwerp, Antwerp, Belgium
- μNEURO Research Center of Excellence, University of Antwerp, Antwerp, Belgium
| | - David K Menon
- Division of Anaesthesia, Department of Medicine, Department of Neurosciences, University of Cambridge, Cambridge, United Kingdom
| | - Jan Sijbers
- imec-Vision Lab, University of Antwerp, Antwerp, Belgium
- μNEURO Research Center of Excellence, University of Antwerp, Antwerp, Belgium
| | - Pieter Van Dyck
- Department of Radiology, Antwerp University Hospital, Antwerp, Belgium
- mVISION, University of Antwerp, Antwerp, Belgium
| | - Virginia F J Newcombe
- Division of Anaesthesia, Department of Medicine, Department of Neurosciences, University of Cambridge, Cambridge, United Kingdom
| |
Collapse
|
36
|
Hu F, Chen AA, Horng H, Bashyam V, Davatzikos C, Alexander-Bloch A, Li M, Shou H, Satterthwaite TD, Yu M, Shinohara RT. Image harmonization: A review of statistical and deep learning methods for removing batch effects and evaluation metrics for effective harmonization. Neuroimage 2023; 274:120125. [PMID: 37084926 PMCID: PMC10257347 DOI: 10.1016/j.neuroimage.2023.120125] [Citation(s) in RCA: 18] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/14/2023] [Revised: 04/12/2023] [Accepted: 04/19/2023] [Indexed: 04/23/2023] Open
Abstract
Magnetic resonance imaging and computed tomography from multiple batches (e.g. sites, scanners, datasets, etc.) are increasingly used alongside complex downstream analyses to obtain new insights into the human brain. However, significant confounding due to batch-related technical variation, called batch effects, is present in this data; direct application of downstream analyses to the data may lead to biased results. Image harmonization methods seek to remove these batch effects and enable increased generalizability and reproducibility of downstream results. In this review, we describe and categorize current approaches in statistical and deep learning harmonization methods. We also describe current evaluation metrics used to assess harmonization methods and provide a standardized framework to evaluate newly-proposed methods for effective harmonization and preservation of biological information. Finally, we provide recommendations to end-users to advocate for more effective use of current methods and to methodologists to direct future efforts and accelerate development of the field.
Collapse
Affiliation(s)
- Fengling Hu
- Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, 423 Guardian Dr, Philadelphia, PA 19104, United States.
| | - Andrew A Chen
- Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, 423 Guardian Dr, Philadelphia, PA 19104, United States
| | - Hannah Horng
- Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, 423 Guardian Dr, Philadelphia, PA 19104, United States
| | - Vishnu Bashyam
- Center for Biomedical Image Computing and Analytics (CBICA), Perelman School of Medicine, United States
| | - Christos Davatzikos
- Center for Biomedical Image Computing and Analytics (CBICA), Perelman School of Medicine, United States
| | - Aaron Alexander-Bloch
- Department of Psychiatry, Perelman School of Medicine, University of Pennsylvania, United States; Penn-CHOP Lifespan Brain Institute, United States; Department of Child and Adolescent Psychiatry and Behavioral Science, Children's Hospital of Philadelphia, United States
| | - Mingyao Li
- Statistical Center for Single-Cell and Spatial Genomics, Perelman School of Medicine, University of Pennsylvania, United States
| | - Haochang Shou
- Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, 423 Guardian Dr, Philadelphia, PA 19104, United States; Center for Biomedical Image Computing and Analytics (CBICA), Perelman School of Medicine, United States
| | - Theodore D Satterthwaite
- Department of Psychiatry, Perelman School of Medicine, University of Pennsylvania, United States; Penn-CHOP Lifespan Brain Institute, United States; The Penn Lifespan Informatics and Neuroimaging Center, Department of Psychiatry, Perelman School of Medicine, University of Pennsylvania, United States
| | - Meichen Yu
- Indiana Alzheimer's Disease Research Center, Indiana University School of Medicine, United States
| | - Russell T Shinohara
- Penn Statistics in Imaging and Visualization Endeavor (PennSIVE), Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, 423 Guardian Dr, Philadelphia, PA 19104, United States; Center for Biomedical Image Computing and Analytics (CBICA), Perelman School of Medicine, United States
| |
Collapse
|
37
|
Cetin-Karayumak S, Zhang F, Billah T, Zekelman L, Makris N, Pieper S, O’Donnell LJ, Rathi Y. Harmonized diffusion MRI data and white matter measures from the Adolescent Brain Cognitive Development Study. BIORXIV : THE PREPRINT SERVER FOR BIOLOGY 2023:2023.04.04.535587. [PMID: 37066186 PMCID: PMC10104063 DOI: 10.1101/2023.04.04.535587] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/18/2023]
Abstract
The Adolescent Brain Cognitive Development (ABCD) study has collected data from over 10,000 children across 21 sites, providing valuable insights into adolescent brain development. However, site-specific scanner variability has made it challenging to use diffusion MRI (dMRI) data from this study. To address this, a database of harmonized and processed ABCD dMRI data has been created, comprising quality-controlled imaging data from 9345 subjects. This resource required significant computational effort, taking ~50,000 CPU hours to harmonize the data, perform white matter parcellation, and run whole brain tractography. The database includes harmonized dMRI data, 800 white matter clusters, 73 anatomically labeled white matter tracts both in full-resolution (for analysis) and low-resolution (for visualization), and 804 different dMRI-derived measures per subject. It is available via the NIMH Data Archive and offers tremendous potential for scientific discoveries in structural connectivity studies of neurodevelopment in children and adolescents. Additionally, several post-harmonization experiments were conducted to demonstrate the success of the harmonization process on the ABCD dataset.
Collapse
Affiliation(s)
- Suheyla Cetin-Karayumak
- Department of Psychiatry, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Fan Zhang
- Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Tashrif Billah
- Department of Psychiatry, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Leo Zekelman
- Department of Neurosurgery, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts, USA
- Program in Speech and Hearing Bioscience and Technology, Division of Medical Sciences, Harvard University, Boston, Massachusetts, USA
| | - Nikos Makris
- Department of Psychiatry, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts, USA
- Department of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | | | - Lauren J. O’Donnell
- Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Yogesh Rathi
- Department of Psychiatry, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts, USA
- Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts, USA
| |
Collapse
|
38
|
Chu DY, Adluru N, Nair VA, Adluru A, Choi T, Kessler-Jones A, Dabbs K, Hou J, Hermann B, Prabhakaran V, Ahmed R. Application of data harmonization and tract-based spatial statistics reveals white matter structural abnormalities in pediatric patients with focal cortical dysplasia. Epilepsy Behav 2023; 142:109190. [PMID: 37011527 PMCID: PMC10371876 DOI: 10.1016/j.yebeh.2023.109190] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/12/2022] [Revised: 03/16/2023] [Accepted: 03/18/2023] [Indexed: 04/05/2023]
Abstract
Our study assessed diffusion tensor imaging (DTI) metrics of fractional anisotropy (FA), mean diffusivity (MD), and radial diffusivity (RD) in pediatric subjects with epilepsy secondary to Focal Cortical Dysplasia (FCD) to improve our understanding of structural network changes associated with FCD related epilepsy. We utilized a data harmonization (DH) approach to minimize confounding effects induced by MRI protocol differences. We also assessed correlations between DTI metrics and neurocognitive measures of the fluid reasoning index (FRI), verbal comprehension index (VCI), and visuospatial index (VSI). Data (n = 51) from 23 FCD patients and 28 typically developing controls (TD) scanned clinically on either 1.5T, 3T, or 3T-wide-bore MRI were retrospectively analyzed. Tract-based spatial statistics (TBSS) with threshold-free cluster enhancement and permutation testing with 100,000 permutations were used for statistical analysis. To account for imaging protocol differences, we employed non-parametric data harmonization prior to permutation testing. Our analysis demonstrates that DH effectively removed MRI protocol-based differences typical in clinical acquisitions while preserving group differences in DTI metrics between FCD and TD subjects. Furthermore, DH strengthened the association between DTI metrics and neurocognitive indices. Fractional anisotropy, MD, and RD metrics showed stronger correlation with FRI and VSI than VCI. Our results demonstrate that DH is an integral step to reduce the confounding effect of MRI protocol differences during the analysis of white matter tracts and highlights biological differences between FCD and healthy control subjects. Characterization of white matter changes associated with FCD-related epilepsy may better inform prognosis and treatment approaches.
Collapse
Affiliation(s)
- Daniel Y Chu
- Department of Radiology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA; Department of Neurology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Nagesh Adluru
- Department of Radiology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA; Waisman Center, University of Wisconsin, Madison, WI, USA
| | - Veena A Nair
- Department of Radiology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Anusha Adluru
- Department of Radiology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Timothy Choi
- Department of Radiology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Alanna Kessler-Jones
- Department of Neurology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA; Waisman Center, University of Wisconsin, Madison, WI, USA
| | - Kevin Dabbs
- Department of Neurology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Jiancheng Hou
- Department of Radiology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Bruce Hermann
- Department of Neurology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Vivek Prabhakaran
- Department of Radiology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA; Department of Neurology, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA; Department of Medical Physics, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA; Department of Psychiatry, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA
| | - Raheel Ahmed
- Department of Neurological Surgery, School of Medicine and Public Health, University of Wisconsin, Madison, WI, USA.
| |
Collapse
|
39
|
Wade RG, Lu F, Poruslrani Y, Karia C, Feltbower RG, Plein S, Bourke G, Teh I. Meta-analysis of the normal diffusion tensor imaging values of the peripheral nerves in the upper limb. Sci Rep 2023; 13:4852. [PMID: 36964186 PMCID: PMC10039047 DOI: 10.1038/s41598-023-31307-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2022] [Accepted: 03/09/2023] [Indexed: 03/26/2023] Open
Abstract
Peripheral neuropathy affects 1 in 10 adults over the age of 40 years. Given the absence of a reliable diagnostic test for peripheral neuropathy, there has been a surge of research into diffusion tensor imaging (DTI) because it characterises nerve microstructure and provides reproducible proxy measures of myelination, axon diameter, fibre density and organisation. Before researchers and clinicians can reliably use diffusion tensor imaging to assess the 'health' of the major nerves of the upper limb, we must understand the "normal" range of values and how they vary with experimental conditions. We searched PubMed, Embase, medRxiv and bioRxiv for studies which reported the findings of DTI of the upper limb in healthy adults. Four review authors independently triple extracted data. Using the meta suite of Stata 17, we estimated the normal fractional anisotropy (FA) and diffusivity (mean, MD; radial, RD; axial AD) values of the median, radial and ulnar nerve in the arm, elbow and forearm. Using meta-regression, we explored how DTI metrics varied with age and experimental conditions. We included 20 studies reporting data from 391 limbs, belonging to 346 adults (189 males and 154 females, ~ 1.2 M:1F) of mean age 34 years (median 31, range 20-80). In the arm, there was no difference in the FA (pooled mean 0.59 mm2/s [95% CI 0.57, 0.62]; I2 98%) or MD (pooled mean 1.13 × 10-3 mm2/s [95% CI 1.08, 1.18]; I2 99%) of the median, radial and ulnar nerves. Around the elbow, the ulnar nerve had a 12% lower FA than the median and radial nerves (95% CI - 0.25, 0.00) and significantly higher MD, RD and AD. In the forearm, the FA (pooled mean 0.55 [95% CI 0.59, 0.64]; I2 96%) and MD (pooled mean 1.03 × 10-3 mm2/s [95% CI 0.94, 1.12]; I2 99%) of the three nerves were similar. Multivariable meta regression showed that the b-value, TE, TR, spatial resolution and age of the subject were clinically important moderators of DTI parameters in peripheral nerves. We show that subject age, as well as the b-value, TE, TR and spatial resolution are important moderators of DTI metrics from healthy nerves in the adult upper limb. The normal ranges shown here may inform future clinical and research studies.
Collapse
Affiliation(s)
- Ryckie G Wade
- Leeds Institute for Medical Research, The Advanced Imaging Centre, Leeds General Infirmary, University of Leeds, Leeds, LS1 3EX, UK.
- Department of Plastic and Reconstructive Surgery, Leeds Teaching Hospitals Trust, Leeds, UK.
| | - Fangqing Lu
- Leeds Institute for Medical Research, The Advanced Imaging Centre, Leeds General Infirmary, University of Leeds, Leeds, LS1 3EX, UK
| | - Yohan Poruslrani
- Royal College of Surgeons in Ireland, University of Medicine and Health Sciences, Dublin, Ireland
| | - Chiraag Karia
- Department of Plastic and Reconstructive Surgery, Leeds Teaching Hospitals Trust, Leeds, UK
| | | | - Sven Plein
- Leeds Institute for Cardiovascular and Metabolic Medicine, University of Leeds, Leeds, UK
- The Advanced Imaging Centre, Leeds Teaching Hospitals Trust, Leeds, UK
| | - Grainne Bourke
- Leeds Institute for Medical Research, The Advanced Imaging Centre, Leeds General Infirmary, University of Leeds, Leeds, LS1 3EX, UK
- Department of Plastic and Reconstructive Surgery, Leeds Teaching Hospitals Trust, Leeds, UK
| | - Irvin Teh
- Leeds Institute for Cardiovascular and Metabolic Medicine, University of Leeds, Leeds, UK
- The Advanced Imaging Centre, Leeds Teaching Hospitals Trust, Leeds, UK
| |
Collapse
|
40
|
Wen G, Shim V, Holdsworth SJ, Fernandez J, Qiao M, Kasabov N, Wang A. Machine Learning for Brain MRI Data Harmonisation: A Systematic Review. Bioengineering (Basel) 2023; 10:bioengineering10040397. [PMID: 37106584 PMCID: PMC10135601 DOI: 10.3390/bioengineering10040397] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/20/2023] [Revised: 03/16/2023] [Accepted: 03/21/2023] [Indexed: 04/29/2023] Open
Abstract
BACKGROUND Magnetic Resonance Imaging (MRI) data collected from multiple centres can be heterogeneous due to factors such as the scanner used and the site location. To reduce this heterogeneity, the data needs to be harmonised. In recent years, machine learning (ML) has been used to solve different types of problems related to MRI data, showing great promise. OBJECTIVE This study explores how well various ML algorithms perform in harmonising MRI data, both implicitly and explicitly, by summarising the findings in relevant peer-reviewed articles. Furthermore, it provides guidelines for the use of current methods and identifies potential future research directions. METHOD This review covers articles published through PubMed, Web of Science, and IEEE databases through June 2022. Data from studies were analysed based on the criteria of Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA). Quality assessment questions were derived to assess the quality of the included publications. RESULTS a total of 41 articles published between 2015 and 2022 were identified and analysed. In the review, MRI data has been found to be harmonised either in an implicit (n = 21) or an explicit (n = 20) way. Three MRI modalities were identified: structural MRI (n = 28), diffusion MRI (n = 7) and functional MRI (n = 6). CONCLUSION Various ML techniques have been employed to harmonise different types of MRI data. There is currently a lack of consistent evaluation methods and metrics used across studies, and it is recommended that the issue be addressed in future studies. Harmonisation of MRI data using ML shows promises in improving performance for ML downstream tasks, while caution should be exercised when using ML-harmonised data for direct interpretation.
Collapse
Affiliation(s)
- Grace Wen
- Auckland Bioengineering Institute, University of Auckland, Auckland 1142, New Zealand
| | - Vickie Shim
- Auckland Bioengineering Institute, University of Auckland, Auckland 1142, New Zealand
- Centre for Brain Research, University of Auckland, Auckland 1142, New Zealand
| | - Samantha Jane Holdsworth
- Centre for Brain Research, University of Auckland, Auckland 1142, New Zealand
- Mātai Medical Research Institute, Tairāwhiti-Gisborne 4010, New Zealand
- Department of Anatomy & Medical Imaging, Faculty of Medical and Health Sciences, University of Auckland, Auckland 1142, New Zealand
| | - Justin Fernandez
- Auckland Bioengineering Institute, University of Auckland, Auckland 1142, New Zealand
| | - Miao Qiao
- Department of Computer Science, University of Auckland, Auckland 1142, New Zealand
| | - Nikola Kasabov
- Auckland Bioengineering Institute, University of Auckland, Auckland 1142, New Zealand
- Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, Auckland 1010, New Zealand
- Intelligent Systems Research Centre, Ulster University, Londonderry BT52 1SA, UK
- Institute for Information and Communication Technologies, Bulgarian Academy of Sciences, 1113 Sofia, Bulgaria
| | - Alan Wang
- Auckland Bioengineering Institute, University of Auckland, Auckland 1142, New Zealand
- Centre for Brain Research, University of Auckland, Auckland 1142, New Zealand
- Department of Anatomy & Medical Imaging, Faculty of Medical and Health Sciences, University of Auckland, Auckland 1142, New Zealand
| |
Collapse
|
41
|
Cui H, Dai W, Zhu Y, Kan X, Gu AAC, Lukemire J, Zhan L, He L, Guo Y, Yang C. BrainGB: A Benchmark for Brain Network Analysis With Graph Neural Networks. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:493-506. [PMID: 36318557 PMCID: PMC10079627 DOI: 10.1109/tmi.2022.3218745] [Citation(s) in RCA: 11] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/16/2023]
Abstract
Mapping the connectome of the human brain using structural or functional connectivity has become one of the most pervasive paradigms for neuroimaging analysis. Recently, Graph Neural Networks (GNNs) motivated from geometric deep learning have attracted broad interest due to their established power for modeling complex networked data. Despite their superior performance in many fields, there has not yet been a systematic study of how to design effective GNNs for brain network analysis. To bridge this gap, we present BrainGB, a benchmark for brain network analysis with GNNs. BrainGB standardizes the process by (1) summarizing brain network construction pipelines for both functional and structural neuroimaging modalities and (2) modularizing the implementation of GNN designs. We conduct extensive experiments on datasets across cohorts and modalities and recommend a set of general recipes for effective GNN designs on brain networks. To support open and reproducible research on GNN-based brain network analysis, we host the BrainGB website at https://braingb.us with models, tutorials, examples, as well as an out-of-box Python package. We hope that this work will provide useful empirical evidence and offer insights for future research in this novel and promising direction.
Collapse
|
42
|
Diffusion Tensor Imaging in Amyotrophic Lateral Sclerosis: Machine Learning for Biomarker Development. Int J Mol Sci 2023; 24:ijms24031911. [PMID: 36768231 PMCID: PMC9915541 DOI: 10.3390/ijms24031911] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/30/2022] [Revised: 01/11/2023] [Accepted: 01/16/2023] [Indexed: 01/21/2023] Open
Abstract
Diffusion tensor imaging (DTI) allows the in vivo imaging of pathological white matter alterations, either with unbiased voxel-wise or hypothesis-guided tract-based analysis. Alterations of diffusion metrics are indicative of the cerebral status of patients with amyotrophic lateral sclerosis (ALS) at the individual level. Using machine learning (ML) models to analyze complex and high-dimensional neuroimaging data sets, new opportunities for DTI-based biomarkers in ALS arise. This review aims to summarize how different ML models based on DTI parameters can be used for supervised diagnostic classifications and to provide individualized patient stratification with unsupervised approaches in ALS. To capture the whole spectrum of neuropathological signatures, DTI might be combined with additional modalities, such as structural T1w 3-D MRI in ML models. To further improve the power of ML in ALS and enable the application of deep learning models, standardized DTI protocols and multi-center collaborations are needed to validate multimodal DTI biomarkers. The application of ML models to multiparametric MRI/multimodal DTI-based data sets will enable a detailed assessment of neuropathological signatures in patients with ALS and the development of novel neuroimaging biomarkers that could be used in the clinical workup.
Collapse
|
43
|
Dobre EG, Surcel M, Constantin C, Ilie MA, Caruntu A, Caruntu C, Neagu M. Skin Cancer Pathobiology at a Glance: A Focus on Imaging Techniques and Their Potential for Improved Diagnosis and Surveillance in Clinical Cohorts. Int J Mol Sci 2023; 24:ijms24021079. [PMID: 36674595 PMCID: PMC9866322 DOI: 10.3390/ijms24021079] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2022] [Revised: 01/02/2023] [Accepted: 01/03/2023] [Indexed: 01/08/2023] Open
Abstract
Early diagnosis is essential for completely eradicating skin cancer and maximizing patients' clinical benefits. Emerging optical imaging modalities such as reflectance confocal microscopy (RCM), optical coherence tomography (OCT), magnetic resonance imaging (MRI), near-infrared (NIR) bioimaging, positron emission tomography (PET), and their combinations provide non-invasive imaging data that may help in the early detection of cutaneous tumors and surgical planning. Hence, they seem appropriate for observing dynamic processes such as blood flow, immune cell activation, and tumor energy metabolism, which may be relevant for disease evolution. This review discusses the latest technological and methodological advances in imaging techniques that may be applied for skin cancer detection and monitoring. In the first instance, we will describe the principle and prospective clinical applications of the most commonly used imaging techniques, highlighting the challenges and opportunities of their implementation in the clinical setting. We will also highlight how imaging techniques may complement the molecular and histological approaches in sharpening the non-invasive skin characterization, laying the ground for more personalized approaches in skin cancer patients.
Collapse
Affiliation(s)
- Elena-Georgiana Dobre
- Faculty of Biology, University of Bucharest, Splaiul Independentei 91-95, 050095 Bucharest, Romania
| | - Mihaela Surcel
- Immunology Department, “Victor Babes” National Institute of Pathology, 050096 Bucharest, Romania
| | - Carolina Constantin
- Immunology Department, “Victor Babes” National Institute of Pathology, 050096 Bucharest, Romania
- Department of Pathology, Colentina University Hospital, 020125 Bucharest, Romania
| | | | - Ana Caruntu
- Department of Oral and Maxillofacial Surgery, “Carol Davila” Central Military Emergency Hospital, 010825 Bucharest, Romania
- Department of Oral and Maxillofacial Surgery, Faculty of Dental Medicine, “Titu Maiorescu” University, 031593 Bucharest, Romania
| | - Constantin Caruntu
- Department of Physiology, “Carol Davila” University of Medicine and Pharmacy, 050474 Bucharest, Romania
- Department of Dermatology, “Prof. N.C. Paulescu” National Institute of Diabetes, Nutrition and Metabolic Diseases, 011233 Bucharest, Romania
- Correspondence:
| | - Monica Neagu
- Faculty of Biology, University of Bucharest, Splaiul Independentei 91-95, 050095 Bucharest, Romania
- Immunology Department, “Victor Babes” National Institute of Pathology, 050096 Bucharest, Romania
- Department of Pathology, Colentina University Hospital, 020125 Bucharest, Romania
| |
Collapse
|
44
|
Ni HC, Chao YP, Tseng RY, Wu CT, Cocchi L, Chou TL, Chen RS, Gau SSF, Yeh CH, Lin HY. Lack of effects of four-week theta burst stimulation on white matter macro/microstructure in children and adolescents with autism. Neuroimage Clin 2023; 37:103324. [PMID: 36638598 PMCID: PMC9852693 DOI: 10.1016/j.nicl.2023.103324] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2022] [Revised: 12/18/2022] [Accepted: 01/05/2023] [Indexed: 01/09/2023]
Abstract
Following the published behavioral and cognitive results of this single-blind parallel sham-controlled randomized clinical trial, the current study aimed to explore the impact of intermittent theta burst stimulation (iTBS), a variant of excitatory transcranial magnetic stimulation, over the bilateral posterior superior temporal sulci (pSTS) on white matter macro/microstructure in intellectually able children and adolescents with autism. Participants were randomized and blindly received active or sham iTBS for 4 weeks (the single-blind sham-controlled phase). Then, all participants continued to receive active iTBS for another 4 weeks (the open-label phase). The clinical results were published elsewhere. Here, we present diffusion magnetic resonance imaging data on potential changes in white matter measures after iTBS. Twenty-two participants in Active-Active group and 27 participants in Sham-Active group underwent multi-shell high angular resolution diffusion imaging (64-direction for b = 2000 & 1000 s/mm2, respectively) at baseline, week 4, and week 8. With longitudinal fixel-based analysis, we found no white matter changes following iTBS from baseline to week 4 (a null treatment by time interaction and a null within-group paired comparison in the Active-Active group), nor from baseline to week 8 (null within-group paired comparisons in both Active-Active and Sham-Active groups). As for the brain-symptoms relationship, we did not find baseline white matter metrics associated with symptom changes at week 4 in either group. Our results raise the question of what the minimal cumulative stimulation dose required to induce the white matter plasticity is.
Collapse
Affiliation(s)
- Hsing-Chang Ni
- Department of Psychiatry, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan
| | - Yi-Ping Chao
- Deparment of Computer Science and Information Engineering, Chang Gung University, Taoyuan, Taiwan; Department of Otorhinolaryngology-Head and Neck Surgery, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan
| | - Rung-Yu Tseng
- Department of Psychiatry, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan; Institute for Radiological Research, Chang Gung University, Taoyuan, Taiwan
| | - Chen-Te Wu
- Department of Medical Imaging and Intervention, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan
| | - Luca Cocchi
- Clinical Brain Networks Group, QIMR Berghofer Medical Research Institute, Brisbane, Queensland, Australia
| | - Tai-Li Chou
- Department of Psychology, National Taiwan University, Taipei, Taiwan; Graduate Institute of Brain and Mind Sciences, College of Medicine, National Taiwan University, Taipei, Taiwan; Neurobiology and Cognitive Science Center, National Taiwan University, Taipei, Taiwan
| | - Rou-Shayn Chen
- Department of Neurology, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan
| | - Susan Shur-Fen Gau
- Graduate Institute of Brain and Mind Sciences, College of Medicine, National Taiwan University, Taipei, Taiwan; Department of Psychiatry, National Taiwan University Hospital and College of Medicine, Taipei, Taiwan
| | - Chun-Hung Yeh
- Department of Psychiatry, Chang Gung Memorial Hospital at Linkou, Taoyuan, Taiwan; Institute for Radiological Research, Chang Gung University, Taoyuan, Taiwan.
| | - Hsiang-Yuan Lin
- Azrieli Adult Neurodevelopmental Centre, Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, Ontario, Canada; Department of Psychiatry, Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada
| |
Collapse
|
45
|
Choi YJ, Jeon KJ, Lee A, Han SS, Lee C. Harmonization of robust radiomic features in the submandibular gland using multi-ultrasound systems: a preliminary study. Dentomaxillofac Radiol 2023; 52:20220284. [PMID: 36341993 PMCID: PMC9974233 DOI: 10.1259/dmfr.20220284] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2022] [Revised: 10/07/2022] [Accepted: 10/11/2022] [Indexed: 11/09/2022] Open
Abstract
OBJECTIVE This study aimed to identify robust radiomic features in multiultrasonography of the submandibular gland and normalize the interdevice discrepancies by applying a machine-learning-based harmonization method. METHODS Ultrasonographic images of normal submandibular gland of young healthy adults, aged between 20 and 40 years, were selected from two different devices. In a total of 30 images, the region of interest was determined along the border of gland parenchyma, and 103 radiomic features were extracted using A-VIEW. The coefficient of variation (CV) was obtained for individual features, and the features showing CV less than 10% were selected. For the selected features, the interdevice discrepancy was normalized using machine-learning method, called the ComBat harmonization. Median differences of the features between the two scanners, before and after harmonization, were compared using Mann-Whitney U-test; confidence interval of 95%. RESULTS Among total 103 radiomic features, 17 features were selected as robust, showing CV less than 10% in both scanners. All values of selected features, except two, showed a statistical difference between the two devices. After applying the ComBat harmonization method, the median and distribution of the 16 features were harmonized to show no significant difference between the two scanners (p > 0.05). One feature remained different (p ≤ 0.05). CONCLUSION On ultrasonographic examination, robust radiomic features for normal submandibular gland were obtained and interdevice normalization was efficiently conducted using ComBat harmonization. Our findings would be useful for multidevices or multicenter studies based on clinical ultrasonographic imaging data to improve the accuracy of the overall diagnostic model.
Collapse
Affiliation(s)
- Yoon Joo Choi
- Department of Oral and Maxillofacial Radiology, Yonsei University College of Dentistry, Seoul, South Korea
| | - Kug Jin Jeon
- Department of Oral and Maxillofacial Radiology, Yonsei University College of Dentistry, Seoul, South Korea
| | - Ari Lee
- Department of Oral and Maxillofacial Radiology, Yonsei University College of Dentistry, Seoul, South Korea
| | - Sang-Sun Han
- Department of Oral and Maxillofacial Radiology, Yonsei University College of Dentistry, Seoul, South Korea
| | | |
Collapse
|
46
|
White matter changes following electroconvulsive therapy for depression: a multicenter ComBat harmonization approach. Transl Psychiatry 2022; 12:517. [PMID: 36526624 PMCID: PMC9758171 DOI: 10.1038/s41398-022-02284-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/03/2022] [Revised: 11/23/2022] [Accepted: 12/07/2022] [Indexed: 12/23/2022] Open
Abstract
ECT is proposed to exert a therapeutic effect on WM microstructure, but the limited power of previous studies made it difficult to highlight consistent patterns of change in diffusion metrics. We initiated a multicenter analysis and sought to address whether changes in WM microstructure occur following ECT. Diffusion tensor imaging (DTI) data (n = 58) from 4 different sites were harmonized before pooling them by using ComBat, a batch-effect correction tool that removes inter-site technical variability, preserves inter-site biological variability, and maximizes statistical power. Downstream statistical analyses aimed to quantify changes in Fractional Anisotropy (FA), Mean Diffusivity (MD), Radial Diffusivity (RD) and Axial Diffusivity (AD), by employing whole-brain, tract-based spatial statistics (TBSS). ECT increased FA in the right splenium of the corpus callosum and the left cortico-spinal tract. AD in the left superior longitudinal fasciculus and the right inferior fronto-occipital fasciculus was raised. Increases in MD and RD could be observed in overlapping white matter structures of both hemispheres. At baseline, responders showed significantly smaller FA values in the left forceps major and smaller AD values in the right uncinate fasciculus compared with non-responders. By harmonizing multicenter data, we demonstrate that ECT modulates altered WM microstructure in important brain circuits that are implicated in the pathophysiology of depression. Furthermore, responders appear to present a more decreased WM integrity at baseline which could point toward a specific subtype of patients, characterized by a more altered neuroplasticity, who are especially sensitive to the potent neuroplastic effects of ECT.
Collapse
|
47
|
Richter S, Winzeck S, Correia MM, Kornaropoulos EN, Manktelow A, Outtrim J, Chatfield D, Posti JP, Tenovuo O, Williams GB, Menon DK, Newcombe VF. Validation of cross-sectional and longitudinal ComBat harmonization methods for magnetic resonance imaging data on a travelling subject cohort. NEUROIMAGE. REPORTS 2022; 2:None. [PMID: 36507071 PMCID: PMC9726680 DOI: 10.1016/j.ynirp.2022.100136] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 02/25/2022] [Revised: 09/07/2022] [Accepted: 09/14/2022] [Indexed: 11/05/2022]
Abstract
Background The growth in multi-center neuroimaging studies generated a need for methods that mitigate the differences in hardware and acquisition protocols across sites i.e., scanner effects. ComBat harmonization methods have shown promise but have not yet been tested on all the data types commonly studied with magnetic resonance imaging (MRI). This study aimed to validate neuroCombat, longCombat and gamCombat on both structural and diffusion metrics in both cross-sectional and longitudinal data. Methods We used a travelling subject design whereby 73 healthy volunteers contributed 161 scans across two sites and four machines using one T1 and five diffusion MRI protocols. Scanner was defined as a composite of site, machine and protocol. A common pipeline extracted two structural metrics (volumes and cortical thickness) and two diffusion tensor imaging metrics (mean diffusivity and fractional anisotropy) for seven regions of interest including gray and (except for cortical thickness) white matter regions. Results Structural data exhibited no significant scanner effect and therefore did not benefit from harmonization in our particular cohort. Indeed, attempting harmonization obscured the true biological effect for some regions of interest. Diffusion data contained marked scanner effects and was successfully harmonized by all methods, resulting in smaller scanner effects and better detection of true biological effects. LongCombat less effectively reduced the scanner effect for cross-sectional white matter data but had a slightly lower probability of incorrectly finding group differences in simulations, compared to neuroCombat and gamCombat. False positive rates for all methods and all metrics did not significantly exceed 5%. Conclusions Statistical harmonization of structural data is not always necessary and harmonization in the absence of a scanner effect may be harmful. Harmonization of diffusion MRI data is highly recommended with neuroCombat, longCombat and gamCombat performing well in cross-sectional and longitudinal settings.
Collapse
Affiliation(s)
- Sophie Richter
- Division of Anaesthesia, Department of Medicine, University of Cambridge, Cambridge, UK
- Corresponding author.
| | - Stefan Winzeck
- Division of Anaesthesia, Department of Medicine, University of Cambridge, Cambridge, UK
- BioMedIA Group, Department of Computing, Imperial College London, London, UK
| | - Marta M. Correia
- MRC Cognition and Brain Sciences Unit, University of Cambridge, Cambridge, UK
| | | | - Anne Manktelow
- Division of Anaesthesia, Department of Medicine, University of Cambridge, Cambridge, UK
| | - Joanne Outtrim
- Division of Anaesthesia, Department of Medicine, University of Cambridge, Cambridge, UK
| | - Doris Chatfield
- Division of Anaesthesia, Department of Medicine, University of Cambridge, Cambridge, UK
| | - Jussi P. Posti
- Turku Brain Injury Center, Turku University Hospital & University of Turku, Turku, Finland
- Department of Neurosurgery, Turku University Hospital, Turku, Finland
| | - Olli Tenovuo
- Turku Brain Injury Center, Turku University Hospital & University of Turku, Turku, Finland
| | - Guy B. Williams
- Wolfson Brain Imaging Centre, Department of Clinical Neurosciences, University of Cambridge, Cambridge, UK
| | - David K. Menon
- Division of Anaesthesia, Department of Medicine, University of Cambridge, Cambridge, UK
| | | |
Collapse
|
48
|
Du X, Wei X, Ding H, Yu Y, Xie Y, Ji Y, Zhang Y, Chai C, Liang M, Li J, Zhuo C, Yu C, Qin W. Unraveling schizophrenia replicable functional connectivity disruption patterns across sites. Hum Brain Mapp 2022; 44:156-169. [PMID: 36222054 PMCID: PMC9783440 DOI: 10.1002/hbm.26108] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2022] [Revised: 09/19/2022] [Accepted: 09/20/2022] [Indexed: 02/05/2023] Open
Abstract
Functional connectivity (FC) disruption is a remarkable characteristic of schizophrenia. However, heterogeneous patterns reported across sites severely hindered its clinical generalization. Based on qualified nodal-based FC of 340 schizophrenia patients (SZ) and 348 normal controls (NC) acquired from seven different scanners, this study compared four commonly used site-effect correction methods in removing the site-related heterogeneities, and then tried to cluster the abnormal FCs into several replicable and independent disrupted subnets across sites, related them to clinical symptoms, and evaluated their potentials in schizophrenia classification. Among the four site-related heterogeneity correction methods, ComBat harmonization (F1 score: 0.806 ± 0.145) achieved the overall best balance between sensitivity and false discovery rate in unraveling the aberrant FCs of schizophrenia in the local and public data sets. Hierarchical clustering analysis identified three replicable FC disruption subnets across the local and public data sets: hypo-connectivity within sensory areas (Net1), hypo-connectivity within thalamus, striatum, and ventral attention network (Net2), and hyper-connectivity between thalamus and sensory processing system (Net3). Notably, the derived composite FC within Net1 was negatively correlated with hostility and disorientation in the public validation set (p < .05). Finally, the three subnet-specific composite FCs (Best area under the receiver operating characteristic curve [AUC] = 0.728) can robustly and meaningfully discriminate the SZ from NC with comparable performance with the full identified FCs features (best AUC = 0.765) in the out-of-sample public data set (Z = -1.583, p = .114). In conclusion, ComBat harmonization was most robust in detecting aberrant connectivity for schizophrenia. Besides, the three subnet-specific composite FC measures might be replicable neuroimaging markers for schizophrenia.
Collapse
Affiliation(s)
- Xiaotong Du
- Department of RadiologyTianjin Medical University General HospitalTianjinChina,Tianjin Key Lab of Functional ImagingTianjin Medical University General HospitalTianjinChina
| | - Xiaotong Wei
- Department of RadiologyTianjin Medical University General HospitalTianjinChina,Tianjin Key Lab of Functional ImagingTianjin Medical University General HospitalTianjinChina
| | - Hao Ding
- Department of RadiologyTianjin Medical University General HospitalTianjinChina,Tianjin Key Lab of Functional ImagingTianjin Medical University General HospitalTianjinChina,School of Medical ImagingTianjin Medical UniversityTianjinChina
| | - Ying Yu
- Department of RadiologyTianjin Medical University General HospitalTianjinChina,Tianjin Key Lab of Functional ImagingTianjin Medical University General HospitalTianjinChina
| | - Yingying Xie
- Department of RadiologyTianjin Medical University General HospitalTianjinChina,Tianjin Key Lab of Functional ImagingTianjin Medical University General HospitalTianjinChina
| | - Yi Ji
- Department of RadiologyTianjin Medical University General HospitalTianjinChina,Tianjin Key Lab of Functional ImagingTianjin Medical University General HospitalTianjinChina
| | - Yu Zhang
- Department of RadiologyTianjin Medical University General HospitalTianjinChina,Tianjin Key Lab of Functional ImagingTianjin Medical University General HospitalTianjinChina
| | - Chao Chai
- Department of RadiologyTianjin Medical University General HospitalTianjinChina,Tianjin Key Lab of Functional ImagingTianjin Medical University General HospitalTianjinChina
| | - Meng Liang
- Department of RadiologyTianjin Medical University General HospitalTianjinChina,Tianjin Key Lab of Functional ImagingTianjin Medical University General HospitalTianjinChina,School of Medical ImagingTianjin Medical UniversityTianjinChina
| | - Jie Li
- Department of Psychiatry Functional Neuroimaging LaboratoryTianjin Mental Health Center, Tianjin Anding HospitalTianjinChina
| | - Chuanjun Zhuo
- Department of Psychiatry Functional Neuroimaging LaboratoryTianjin Mental Health Center, Tianjin Anding HospitalTianjinChina
| | - Chunshui Yu
- Department of RadiologyTianjin Medical University General HospitalTianjinChina,Tianjin Key Lab of Functional ImagingTianjin Medical University General HospitalTianjinChina,School of Medical ImagingTianjin Medical UniversityTianjinChina
| | - Wen Qin
- Department of RadiologyTianjin Medical University General HospitalTianjinChina,Tianjin Key Lab of Functional ImagingTianjin Medical University General HospitalTianjinChina
| |
Collapse
|
49
|
Behler A, Lulé D, Ludolph AC, Kassubek J, Müller HP. Longitudinal monitoring of amyotrophic lateral sclerosis by diffusion tensor imaging: Power calculations for group studies. Front Neurosci 2022; 16:929151. [PMID: 36117627 PMCID: PMC9479493 DOI: 10.3389/fnins.2022.929151] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2022] [Accepted: 07/20/2022] [Indexed: 11/21/2022] Open
Abstract
Introduction Diffusion tensor imaging (DTI) can be used to map disease progression in amyotrophic lateral sclerosis (ALS) and therefore is a promising candidate for a biomarker in ALS. To this end, longitudinal study protocols need to be optimized and validated regarding group sizes and time intervals between visits. The objective of this study was to assess the influences of sample size, the schedule of follow-up measurements, and measurement uncertainties on the statistical power to optimize longitudinal DTI study protocols in ALS. Patients and methods To estimate the measurement uncertainty of a tract-of–interest-based DTI approach, longitudinal test-retest measurements were applied first to a normal data set. Then, DTI data sets of 80 patients with ALS and 50 healthy participants were analyzed in the simulation of longitudinal trajectories, that is, longitudinal fractional anisotropy (FA) values for follow-up sessions were simulated for synthetic patient and control groups with different rates of FA decrease in the corticospinal tract. Monte Carlo simulations of synthetic longitudinal study groups were used to estimate the statistical power and thus the potentially needed sample sizes for a various number of scans at one visit, different time intervals between baseline and follow-up measurements, and measurement uncertainties. Results From the simulation for different longitudinal FA decrease rates, it was found that two scans per session increased the statistical power in the investigated settings unless sample sizes were sufficiently large and time intervals were appropriately long. The positive effect of a second scan per session on the statistical power was particularly pronounced for FA values with high measurement uncertainty, for which the third scan per session increased the statistical power even further. Conclusion With more than one scan per session, the statistical power of longitudinal DTI studies can be increased in patients with ALS. Consequently, sufficient statistical power can be achieved even with limited sample sizes. An improved longitudinal DTI study protocol contributes to the detection of small changes in diffusion metrics and thereby supports DTI as an applicable and reliable non-invasive biomarker in ALS.
Collapse
Affiliation(s)
- Anna Behler
- Department of Neurology, University of Ulm, Ulm, Germany
| | - Dorothée Lulé
- Department of Neurology, University of Ulm, Ulm, Germany
| | - Albert C Ludolph
- Department of Neurology, University of Ulm, Ulm, Germany.,Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE), Ulm, Germany
| | - Jan Kassubek
- Department of Neurology, University of Ulm, Ulm, Germany.,Deutsches Zentrum für Neurodegenerative Erkrankungen (DZNE), Ulm, Germany
| | | |
Collapse
|
50
|
Roffet F, Delrieux C, Patow G. Assessing Multi-Site rs-fMRI-Based Connectomic Harmonization Using Information Theory. Brain Sci 2022; 12:brainsci12091219. [PMID: 36138956 PMCID: PMC9496818 DOI: 10.3390/brainsci12091219] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/14/2022] [Revised: 09/01/2022] [Accepted: 09/06/2022] [Indexed: 11/17/2022] Open
Abstract
Several harmonization techniques have recently been proposed for connectomics/networks derived from resting-state functional magnetic resonance imaging (rs-fMRI) acquired at multiple sites. These techniques have the objective of mitigating site-specific biases that complicate its subsequent analysis and, therefore, compromise the quality of the results when these images are analyzed together. Thus, harmonization is indispensable when large cohorts are required in which the data obtained must be independent of the particular condition of each resonator, its make and model, its calibration, and other features or artifacts that may affect the significance of the acquisition. To date, no assessment of the actual efficacy of these harmonization techniques has been proposed. In this work, we apply recently introduced Information Theory tools to analyze the effectiveness of these techniques, developing a methodology that allows us to compare different harmonization models. We demonstrate the usefulness of this methodology by applying it to some of the most widespread harmonization frameworks and datasets. As a result, we are able to show that some of these techniques are indeed ineffective since the acquisition site can still be determined from the fMRI data after the processing.
Collapse
Affiliation(s)
- Facundo Roffet
- Department of Electrical and Computer Engineering (DIEC), Universidad Nacional del Sur, Bahía Blanca AR-B8000, Argentina
| | - Claudio Delrieux
- Department of Electrical and Computer Engineering (DIEC), Universidad Nacional del Sur and National Council for Scientific and Technical Research (CONICET), Bahía Blanca AR-B8000, Argentina
| | - Gustavo Patow
- ViRVIG, University of Girona, 17003 Girona, Spain
- Correspondence:
| |
Collapse
|