1
|
Prieto-González LS, Agulles-Pedrós L. Exploring the Potential of Machine Learning Algorithms to Improve Diffusion Nuclear Magnetic Resonance Imaging Models Analysis. J Med Phys 2024; 49:189-202. [PMID: 39131437 PMCID: PMC11309135 DOI: 10.4103/jmp.jmp_10_24] [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: 01/17/2024] [Revised: 03/27/2024] [Accepted: 04/15/2024] [Indexed: 08/13/2024] Open
Abstract
Purpose This paper explores different machine learning (ML) algorithms for analyzing diffusion nuclear magnetic resonance imaging (dMRI) models when analytical fitting shows restrictions. It reviews various ML techniques for dMRI analysis and evaluates their performance on different b-values range datasets, comparing them with analytical methods. Materials and Methods After standard fitting for reference, four sets of diffusion-weighted nuclear magnetic resonance images were used to train/test various ML algorithms for prediction of diffusion coefficient (D), pseudo-diffusion coefficient (D*), perfusion fraction (f), and kurtosis (K). ML classification algorithms, including extra-tree classifier (ETC), logistic regression, C-support vector, extra-gradient boost, and multilayer perceptron (MLP), were used to determine the existence of diffusion parameters (D, D*, f, and K) within single voxels. Regression algorithms, including linear regression, polynomial regression, ridge, lasso, random forest (RF), elastic-net, and support-vector machines, were used to estimate the value of the diffusion parameters. Performance was evaluated using accuracy (ACC), area under the curve (AUC) tests, and cross-validation root mean square error (RMSECV). Computational timing was also assessed. Results ETC and MLP were the best classifiers, with 94.1% and 91.7%, respectively, for the ACC test and 98.7% and 96.3% for the AUC test. For parameter estimation, RF algorithm yielded the most accurate results The RMSECV percentages were: 8.39% for D, 3.57% for D*, 4.52% for f, and 3.53% for K. After the training phase, the ML methods demonstrated a substantial decrease in computational time, being approximately 232 times faster than the conventional methods. Conclusions The findings suggest that ML algorithms can enhance the efficiency of dMRI model analysis and offer new perspectives on the microstructural and functional organization of biological tissues. This paper also discusses the limitations and future directions of ML-based dMRI analysis.
Collapse
Affiliation(s)
| | - Luis Agulles-Pedrós
- Department of Physics, Medical Physics Group, National University of Colombia, Campus Bogotá, Bogotá, Colombia
| |
Collapse
|
2
|
Nair AK, Adluru N, Finley AJ, Gresham LK, Skinner SE, Alexander AL, Davidson RJ, Ryff CD, Schaefer SM. Purpose in life as a resilience factor for brain health: diffusion MRI findings from the Midlife in the U.S. study. Front Psychiatry 2024; 15:1355998. [PMID: 38505799 PMCID: PMC10948414 DOI: 10.3389/fpsyt.2024.1355998] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/21/2023] [Accepted: 02/09/2024] [Indexed: 03/21/2024] Open
Abstract
Introduction A greater sense of purpose in life is associated with several health benefits relevant for active aging, but the mechanisms remain unclear. We evaluated if purpose in life was associated with indices of brain health. Methods We examined data from the Midlife in the United States (MIDUS) Neuroscience Project. Diffusion weighted magnetic resonance imaging data (n=138; mean age 65.2 years, age range 48-95; 80 females; 37 black, indigenous, and people of color) were used to estimate microstructural indices of brain health such as axonal density, and axonal orientation. The seven-item purpose in life scale was used. Permutation analysis of linear models was used to examine associations between purpose in life scores and the diffusion metrics in white matter and in the bilateral hippocampus, adjusting for age, sex, education, and race. Results and discussion Greater sense of purpose in life was associated with brain microstructural features consistent with better brain health. Positive associations were found in both white matter and the right hippocampus, where multiple convergent associations were detected. The hippocampus is a brain structure involved in learning and memory that is vulnerable to stress but retains the capacity to grow and adapt through old age. Our findings suggest pathways through which an enhanced sense of purpose in life may contribute to better brain health and promote healthy aging. Since purpose in life is known to decline with age, interventions and policy changes that facilitate a greater sense of purpose may extend and improve the brain health of individuals and thus improve public health.
Collapse
Affiliation(s)
- Ajay Kumar Nair
- Institute on Aging, University of Wisconsin-Madison, Madison, WI, United States
| | - Nagesh Adluru
- Waisman Center, University of Wisconsin-Madison, Madison, WI, United States
- Department of Radiology, University of Wisconsin-Madison, Madison, WI, United States
| | - Anna J. Finley
- Institute on Aging, University of Wisconsin-Madison, Madison, WI, United States
| | - Lauren K. Gresham
- Institute on Aging, University of Wisconsin-Madison, Madison, WI, United States
| | - Sarah E. Skinner
- Institute on Aging, University of Wisconsin-Madison, Madison, WI, United States
| | - Andrew L. Alexander
- Waisman Center, University of Wisconsin-Madison, Madison, WI, United States
- Department of Medical Physics, University of Wisconsin-Madison, Madison, WI, United States
| | - Richard J. Davidson
- Center for Healthy Minds, University of Wisconsin-Madison, Madison, WI, United States
| | - Carol D. Ryff
- Institute on Aging, University of Wisconsin-Madison, Madison, WI, United States
| | - Stacey M. Schaefer
- Institute on Aging, University of Wisconsin-Madison, Madison, WI, United States
| |
Collapse
|
3
|
Baxi M, Cetin-Karayumak S, Papadimitriou G, Makris N, van der Kouwe A, Jenkins B, Moore TL, Rosene DL, Kubicki M, Rathi Y. Investigating the contribution of cytoarchitecture to diffusion MRI measures in gray matter using histology. FRONTIERS IN NEUROIMAGING 2022; 1:947526. [PMID: 37555179 PMCID: PMC10406256 DOI: 10.3389/fnimg.2022.947526] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 05/18/2022] [Accepted: 07/19/2022] [Indexed: 08/10/2023]
Abstract
Postmortem studies are currently considered a gold standard for investigating brain structure at the cellular level. To investigate cellular changes in the context of human development, aging, or disease treatment, non-invasive in-vivo imaging methods such as diffusion MRI (dMRI) are needed. However, dMRI measures are only indirect measures and require validation in gray matter (GM) in the context of their sensitivity to the underlying cytoarchitecture, which has been lacking. Therefore, in this study we conducted direct comparisons between in-vivo dMRI measures and histology acquired from the same four rhesus monkeys. Average and heterogeneity of fractional anisotropy and trace from diffusion tensor imaging and mean squared displacement (MSD) and return-to-origin-probability from biexponential model were calculated in nine cytoarchitectonically different GM regions using dMRI data. DMRI measures were compared with corresponding histology measures of regional average and heterogeneity in cell area density. Results show that both average and heterogeneity in trace and MSD measures are sensitive to the underlying cytoarchitecture (cell area density) and capture different aspects of cell composition and organization. Trace and MSD thus would prove valuable as non-invasive imaging biomarkers in future studies investigating GM cytoarchitectural changes related to development and aging as well as abnormal cellular pathologies in clinical studies.
Collapse
Affiliation(s)
- Madhura Baxi
- Graduate Program for Neuroscience, Boston University, Boston, MA, United States
- Psychiatry Neuroimaging Laboratory, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States
| | - Suheyla Cetin-Karayumak
- Psychiatry Neuroimaging Laboratory, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States
| | - George Papadimitriou
- Center for Morphometric Analysis, Massachusetts General Hospital, Charlestown, MA, United States
| | - Nikos Makris
- Psychiatry Neuroimaging Laboratory, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States
| | - Andre van der Kouwe
- Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA, United States
| | - Bruce Jenkins
- Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA, United States
| | - Tara L. Moore
- Anatomy and Neurobiology, Boston University School of Medicine, Boston, MA, United States
- Center for Systems Neuroscience, Boston, MA, United States
| | - Douglas L. Rosene
- Anatomy and Neurobiology, Boston University School of Medicine, Boston, MA, United States
- Center for Systems Neuroscience, Boston, MA, United States
| | - Marek Kubicki
- Psychiatry Neuroimaging Laboratory, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States
- Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA, United States
| | - Yogesh Rathi
- Psychiatry Neuroimaging Laboratory, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States
- Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Charlestown, MA, United States
| |
Collapse
|
4
|
Taha HT, Chad JA, Chen JJ. DKI enhances the sensitivity and interpretability of age-related DTI patterns in the white matter of UK biobank participants. Neurobiol Aging 2022; 115:39-49. [PMID: 35468551 DOI: 10.1016/j.neurobiolaging.2022.03.008] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2021] [Revised: 03/09/2022] [Accepted: 03/12/2022] [Indexed: 12/25/2022]
Abstract
Studies of healthy brain aging traditionally report diffusivity patterns associated with white matter degeneration using diffusion tensor imaging (DTI), which assumes that diffusion measured at typical b-values (approximately 1000 s/mm2) is Gaussian. Diffusion kurtosis imaging (DKI) is an extension of DTI that measures non-Gaussian diffusion (kurtosis) to better capture microenvironmental processes by incorporating additional data at a higher b-value. In this study, using diffusion data (b-values of 1000 and 2000 s/mm2) from 700 UK Biobank participants aged 46-80, we investigate (1) the extent of novel information gained from adding diffusional kurtosis to diffusivity observations in aging, and (2) how conventional DTI metrics in aging compare with diffusivity metrics derived from DKI, which are corrected for kurtosis. We establish a pattern of lower kurtosis alongside higher diffusivity among older adults, with kurtosis generally being more sensitive to age than diffusivity. We also find discrepancies between diffusivity metrics derived from DTI and DKI, emphasizing the importance of accounting for non-Gaussian diffusion when interpreting age-related diffusivity patterns.
Collapse
Affiliation(s)
- Hiba T Taha
- Rotman Research Institute, Baycrest Health Sciences, Toronto, Ontario, Canada; Institute of Medical Science, University of Toronto, Toronto, Ontario, Canada
| | - Jordan A Chad
- Rotman Research Institute, Baycrest Health Sciences, Toronto, Ontario, Canada; Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada
| | - J Jean Chen
- Rotman Research Institute, Baycrest Health Sciences, Toronto, Ontario, Canada; Department of Medical Biophysics, University of Toronto, Toronto, Ontario, Canada; Institute of Biomedical Engineering, University of Toronto, Toronto, Ontario, Canada.
| |
Collapse
|
5
|
Asschenfeldt B, Evald L, Salvig C, Heiberg J, Østergaard L, Eskildsen SF, Hjortdal VE. Altered Cerebral Microstructure in Adults With Atrial Septal Defect and Ventricular Septal Defect Repaired in Childhood. J Am Heart Assoc 2022; 11:e020915. [PMID: 35699183 PMCID: PMC9238637 DOI: 10.1161/jaha.121.020915] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/21/2023]
Abstract
Background Delayed brain development, brain injury, and neurodevelopmental disabilities are commonly observed in infants operated for complex congenital heart defect. Our previous findings of poorer neurodevelopmental outcomes in individuals operated for simple congenital heart defects calls for further etiological clarification. Hence, we examined the microstructural tissue composition in cerebral cortex and subcortical structures in comparison to healthy controls and whether differences were associated with neurodevelopmental outcomes. Methods and Results Adults (n=62) who underwent surgical closure of an atrial septal defect (n=33) or a ventricular septal defect (n=29) in childhood and a group of healthy, matched controls (n=38) were enrolled. Brain diffusional kurtosis imaging and neuropsychological assessment were performed. Cortical and subcortical tissue microstructure were assessed using mean kurtosis tensor and mean diffusivity and compared between groups and tested for associations with neuropsychological outcomes. Alterations in microstructural tissue composition were found in the parietal, temporal, and occipital lobes in the congenital heart defects, with distinct mean kurtosis tensor cluster‐specific changes in the right visual cortex (pericalcarine gyrus, P=0.002; occipital part of fusiform and lingual gyri, P=0.019). Altered microstructural tissue composition in the subcortical structures was uncovered in atrial septal defects but not in ventricular septal defects. Associations were found between altered cerebral microstructure and social recognition and executive function. Conclusions Children operated for simple congenital heart defects demonstrated altered microstructural tissue composition in the cerebral cortex and subcortical structures during adulthood when compared with healthy peers. Alterations in cerebral microstructural tissue composition were associated with poorer neuropsychological performance. Registration URL: https://www.clinicaltrials.gov; Unique identifier: NCT03871881.
Collapse
Affiliation(s)
- Benjamin Asschenfeldt
- Department of Cardiothoracic & Vascular Surgery Aarhus University Hospital Denmark.,Department of Clinical Medicine Aarhus University Denmark
| | - Lars Evald
- Department of Clinical Medicine Aarhus University Denmark.,Hammel Neurorehabilitation Centre and University Research Clinic Denmark
| | - Camilla Salvig
- Department of Cardiothoracic & Vascular Surgery Aarhus University Hospital Denmark
| | - Johan Heiberg
- Department of Cardiothoracic & Vascular Surgery Aarhus University Hospital Denmark.,Department of Clinical Medicine Aarhus University Denmark
| | - Leif Østergaard
- Center of Functionally Integrative Neuroscience Aarhus University Denmark.,Department of Clinical Medicine Aarhus University Denmark.,Neuroradiology Research Unit, Department of Radiology Aarhus University Hospital Denmark
| | - Simon Fristed Eskildsen
- Center of Functionally Integrative Neuroscience Aarhus University Denmark.,Department of Clinical Medicine Aarhus University Denmark
| | - Vibeke Elisabeth Hjortdal
- Department of Clinical Medicine Aarhus University Denmark.,Department of Cardiothoracic Surgery, Rigshospitalet and Institute of Clinical Medicine University of Copenhagen Denmark
| |
Collapse
|
6
|
Henriksen OM, del Mar Álvarez-Torres M, Figueiredo P, Hangel G, Keil VC, Nechifor RE, Riemer F, Schmainda KM, Warnert EAH, Wiegers EC, Booth TC. High-Grade Glioma Treatment Response Monitoring Biomarkers: A Position Statement on the Evidence Supporting the Use of Advanced MRI Techniques in the Clinic, and the Latest Bench-to-Bedside Developments. Part 1: Perfusion and Diffusion Techniques. Front Oncol 2022; 12:810263. [PMID: 35359414 PMCID: PMC8961422 DOI: 10.3389/fonc.2022.810263] [Citation(s) in RCA: 28] [Impact Index Per Article: 14.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/06/2021] [Accepted: 01/05/2022] [Indexed: 01/16/2023] Open
Abstract
Objective Summarize evidence for use of advanced MRI techniques as monitoring biomarkers in the clinic, and highlight the latest bench-to-bedside developments. Methods Experts in advanced MRI techniques applied to high-grade glioma treatment response assessment convened through a European framework. Current evidence regarding the potential for monitoring biomarkers in adult high-grade glioma is reviewed, and individual modalities of perfusion, permeability, and microstructure imaging are discussed (in Part 1 of two). In Part 2, we discuss modalities related to metabolism and/or chemical composition, appraise the clinic readiness of the individual modalities, and consider post-processing methodologies involving the combination of MRI approaches (multiparametric imaging) or machine learning (radiomics). Results High-grade glioma vasculature exhibits increased perfusion, blood volume, and permeability compared with normal brain tissue. Measures of cerebral blood volume derived from dynamic susceptibility contrast-enhanced MRI have consistently provided information about brain tumor growth and response to treatment; it is the most clinically validated advanced technique. Clinical studies have proven the potential of dynamic contrast-enhanced MRI for distinguishing post-treatment related effects from recurrence, but the optimal acquisition protocol, mode of analysis, parameter of highest diagnostic value, and optimal cut-off points remain to be established. Arterial spin labeling techniques do not require the injection of a contrast agent, and repeated measurements of cerebral blood flow can be performed. The absence of potential gadolinium deposition effects allows widespread use in pediatric patients and those with impaired renal function. More data are necessary to establish clinical validity as monitoring biomarkers. Diffusion-weighted imaging, apparent diffusion coefficient analysis, diffusion tensor or kurtosis imaging, intravoxel incoherent motion, and other microstructural modeling approaches also allow treatment response assessment; more robust data are required to validate these alone or when applied to post-processing methodologies. Conclusion Considerable progress has been made in the development of these monitoring biomarkers. Many techniques are in their infancy, whereas others have generated a larger body of evidence for clinical application.
Collapse
Affiliation(s)
- Otto M. Henriksen
- Department of Clinical Physiology, Nuclear Medicine and PET, Copenhagen University Hospital Rigshospitalet, Copenhagen, Denmark
| | | | - Patricia Figueiredo
- Department of Bioengineering and Institute for Systems and Robotics-Lisboa, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
| | - Gilbert Hangel
- Department of Neurosurgery, Medical University, Vienna, Austria
- High-Field MR Centre, Department of Biomedical Imaging and Image-Guided Therapy, Medical University, Vienna, Austria
| | - Vera C. Keil
- Department of Radiology and Nuclear Medicine, Amsterdam UMC, Amsterdam, Netherlands
| | - Ruben E. Nechifor
- International Institute for the Advanced Studies of Psychotherapy and Applied Mental Health, Department of Clinical Psychology and Psychotherapy, Babes-Bolyai University, Cluj-Napoca, Romania
| | - Frank Riemer
- Mohn Medical Imaging and Visualization Centre (MMIV), Department of Radiology, Haukeland University Hospital, Bergen, Norway
| | - Kathleen M. Schmainda
- Department of Biophysics, Medical College of Wisconsin, Milwaukee, WI, United States
| | | | - Evita C. Wiegers
- Department of Radiology, University Medical Center Utrecht, Utrecht, Netherlands
| | - Thomas C. Booth
-
School of Biomedical Engineering and Imaging Sciences, St. Thomas’ Hospital, King’s College London, London, United Kingdom
- Department of Neuroradiology, King’s College Hospital NHS Foundation Trust, London, United Kingdom
| |
Collapse
|