1
|
Abbasi S, Lan H, Choupan J, Sheikh-Bahaei N, Pandey G, Varghese B. Deep learning for the harmonization of structural MRI scans: a survey. Biomed Eng Online 2024; 23:90. [PMID: 39217355 PMCID: PMC11365220 DOI: 10.1186/s12938-024-01280-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/10/2024] [Accepted: 08/06/2024] [Indexed: 09/04/2024] Open
Abstract
Medical imaging datasets for research are frequently collected from multiple imaging centers using different scanners, protocols, and settings. These variations affect data consistency and compatibility across different sources. Image harmonization is a critical step to mitigate the effects of factors like inherent differences between various vendors, hardware upgrades, protocol changes, and scanner calibration drift, as well as to ensure consistent data for medical image processing techniques. Given the critical importance and widespread relevance of this issue, a vast array of image harmonization methodologies have emerged, with deep learning-based approaches driving substantial advancements in recent times. The goal of this review paper is to examine the latest deep learning techniques employed for image harmonization by analyzing cutting-edge architectural approaches in the field of medical image harmonization, evaluating both their strengths and limitations. This paper begins by providing a comprehensive fundamental overview of image harmonization strategies, covering three critical aspects: established imaging datasets, commonly used evaluation metrics, and characteristics of different scanners. Subsequently, this paper analyzes recent structural MRI (Magnetic Resonance Imaging) harmonization techniques based on network architecture, network learning algorithm, network supervision strategy, and network output. The underlying architectures include U-Net, Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), flow-based generative models, transformer-based approaches, as well as custom-designed network architectures. This paper investigates the effectiveness of Disentangled Representation Learning (DRL) as a pivotal learning algorithm in harmonization. Lastly, the review highlights the primary limitations in harmonization techniques, specifically the lack of comprehensive quantitative comparisons across different methods. The overall aim of this review is to serve as a guide for researchers and practitioners to select appropriate architectures based on their specific conditions and requirements. It also aims to foster discussions around ongoing challenges in the field and shed light on promising future research directions with the potential for significant advancements.
Collapse
Affiliation(s)
- Soolmaz Abbasi
- Department of Computer Engineering, Yazd University, Yazd, Iran
| | - Haoyu Lan
- Department of Neurology, University of Southern California, Los Angeles, CA, USA
| | - Jeiran Choupan
- Department of Neurology, University of Southern California, Los Angeles, CA, USA
| | - Nasim Sheikh-Bahaei
- Department of Radiology, University of Southern California, Los Angeles, CA, USA
| | - Gaurav Pandey
- Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Bino Varghese
- Department of Radiology, University of Southern California, Los Angeles, CA, USA.
| |
Collapse
|
2
|
Sanvito F, Kaufmann TJ, Cloughesy TF, Wen PY, Ellingson BM. Standardized brain tumor imaging protocols for clinical trials: current recommendations and tips for integration. FRONTIERS IN RADIOLOGY 2023; 3:1267615. [PMID: 38152383 PMCID: PMC10751345 DOI: 10.3389/fradi.2023.1267615] [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: 07/26/2023] [Accepted: 11/24/2023] [Indexed: 12/29/2023]
Abstract
Standardized MRI acquisition protocols are crucial for reducing the measurement and interpretation variability associated with response assessment in brain tumor clinical trials. The main challenge is that standardized protocols should ensure high image quality while maximizing the number of institutions meeting the acquisition requirements. In recent years, extensive effort has been made by consensus groups to propose different "ideal" and "minimum requirements" brain tumor imaging protocols (BTIPs) for gliomas, brain metastases (BM), and primary central nervous system lymphomas (PCSNL). In clinical practice, BTIPs for clinical trials can be easily integrated with additional MRI sequences that may be desired for clinical patient management at individual sites. In this review, we summarize the general concepts behind the choice and timing of sequences included in the current recommended BTIPs, we provide a comparative overview, and discuss tips and caveats to integrate additional clinical or research sequences while preserving the recommended BTIPs. Finally, we also reflect on potential future directions for brain tumor imaging in clinical trials.
Collapse
Affiliation(s)
- Francesco Sanvito
- UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision and Imaging Biomarkers, University of California, Los Angeles, Los Angeles, CA, United States
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States
| | | | - Timothy F. Cloughesy
- UCLA Neuro-Oncology Program, University of California, Los Angeles, Los Angeles, CA, United States
- Department of Neurology, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States
| | - Patrick Y. Wen
- Center for Neuro-Oncology, Dana-Farber/Brigham and Women’s Cancer Center, Harvard Medical School, Boston, MA, United States
| | - Benjamin M. Ellingson
- UCLA Brain Tumor Imaging Laboratory (BTIL), Center for Computer Vision and Imaging Biomarkers, University of California, Los Angeles, Los Angeles, CA, United States
- Department of Radiological Sciences, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States
- Department of Bioengineering, Henry Samueli School of Engineering and Applied Science, University of California, Los Angeles, Los Angeles, CA, United States
- Department of Neurosurgery, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States
- Department of Psychiatry and Biobehavioral Sciences, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States
| |
Collapse
|
3
|
Kasabov NK, Bahrami H, Doborjeh M, Wang A. Brain-Inspired Spatio-Temporal Associative Memories for Neuroimaging Data Classification: EEG and fMRI. Bioengineering (Basel) 2023; 10:1341. [PMID: 38135932 PMCID: PMC10741022 DOI: 10.3390/bioengineering10121341] [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: 08/18/2023] [Revised: 10/16/2023] [Accepted: 11/14/2023] [Indexed: 12/24/2023] Open
Abstract
Humans learn from a lot of information sources to make decisions. Once this information is learned in the brain, spatio-temporal associations are made, connecting all these sources (variables) in space and time represented as brain connectivity. In reality, to make a decision, we usually have only part of the information, either as a limited number of variables, limited time to make the decision, or both. The brain functions as a spatio-temporal associative memory. Inspired by the ability of the human brain, a brain-inspired spatio-temporal associative memory was proposed earlier that utilized the NeuCube brain-inspired spiking neural network framework. Here we applied the STAM framework to develop STAM for neuroimaging data, on the cases of EEG and fMRI, resulting in STAM-EEG and STAM-fMRI. This paper showed that once a NeuCube STAM classification model was trained on a complete spatio-temporal EEG or fMRI data, it could be recalled using only part of the time series, or/and only part of the used variables. We evaluated both temporal and spatial association and generalization accuracy accordingly. This was a pilot study that opens the field for the development of classification systems on other neuroimaging data, such as longitudinal MRI data, trained on complete data but recalled on partial data. Future research includes STAM that will work on data, collected across different settings, in different labs and clinics, that may vary in terms of the variables and time of data collection, along with other parameters. The proposed STAM will be further investigated for early diagnosis and prognosis of brain conditions and for diagnostic/prognostic marker discovery.
Collapse
Affiliation(s)
- Nikola K. Kasabov
- Knowledge Engineering and Discovery Research Innovation, School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New Zealand; (H.B.); (M.D.)
- Intelligent Systems Research Center, University of Ulster, Londonderry BT48 7JL, UK
- Institute for Information and Communication Technologies, Bulgarian Academy of Sciences, 1113 Sofia, Bulgaria
- Computer Science and Engineering Department, Dalian University, Dalian 116622, China
- Auckland Bioengineering Institute, University of Auckland, Auckland 1010, New Zealand
- Knowledge Engineering Consulting Ltd., Auckland 1071, New Zealand
| | - Helena Bahrami
- Knowledge Engineering and Discovery Research Innovation, School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New Zealand; (H.B.); (M.D.)
- Core & Innovation, Wine-Searcher, Auckland 0640, New Zealand
- Royal Society Te Apārangi, Wellington 6011, New Zealand
- Research Association New Zealand (RANZ), Auckland 1010, New Zealand
| | - Maryam Doborjeh
- Knowledge Engineering and Discovery Research Innovation, School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New Zealand; (H.B.); (M.D.)
| | - Alan Wang
- Auckland Bioengineering Institute, University of Auckland, Auckland 1010, New Zealand
- Faculty of Medical and Health Sciences, University of Auckland, Auckland 1010, New Zealand
- Centre for Brain Research, University of Auckland, Auckland 1010, New Zealand
| |
Collapse
|
4
|
Ioannidis GS, Pigott LE, Iv M, Surlan-Popovic K, Wintermark M, Bisdas S, Marias K. Investigating the value of radiomics stemming from DSC quantitative biomarkers in IDH mutation prediction in gliomas. Front Neurol 2023; 14:1249452. [PMID: 38046592 PMCID: PMC10690367 DOI: 10.3389/fneur.2023.1249452] [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: 06/28/2023] [Accepted: 10/31/2023] [Indexed: 12/05/2023] Open
Abstract
Objective This study aims to assess the value of biomarker based radiomics to predict IDH mutation in gliomas. The patient cohort consists of 160 patients histopathologicaly proven of primary glioma (WHO grades 2-4) from 3 different centers. Methods To quantify the DSC perfusion signal two different mathematical modeling methods were used (Gamma fitting, leakage correction algorithms) considering the assumptions about the compartments contributing in the blood flow between the extra- and intra vascular space. Results The Mean slope of increase (MSI) and the K1 parameter of the bidirectional exchange model exhibited the highest performance with (ACC 74.3% AUROC 74.2%) and (ACC 75% AUROC 70.5%) respectively. Conclusion The proposed framework on DSC-MRI radiogenomics in gliomas has the potential of becoming a reliable diagnostic support tool exploiting the mathematical modeling of the DSC signal to characterize IDH mutation status through a more reproducible and standardized signal analysis scheme for facilitating clinical translation.
Collapse
Affiliation(s)
- Georgios S. Ioannidis
- Computational BioMedicine Laboratory (CBML), Institute of Computer Science, Foundation for Research and Technology—Hellas (FORTH), Heraklion, Greece
| | - Laura Elin Pigott
- Institute of Health and Social Care, London South Bank University, London, United Kingdom
- Faculty of Brain Science, Queen Square Institute of Neurology, University College London, London, United Kingdom
- Lysholm Department of Neuroradiology, The National Hospital for Neurology and Neurosurgery University College London, London, United Kingdom
| | - Michael Iv
- Department of Radiology, Division of Neuroimaging and Neurointervention, Stanford University, Stanford, CA, United States
| | - Katarina Surlan-Popovic
- Department of Radiology, Faculty of Medicine, University of Ljubljana, Ljubljana, Slovenia
- Department of Neuroradiology, University Medical Centre, Ljubljana, Slovenia
| | - Max Wintermark
- Department of Radiology, Division of Neuroimaging and Neurointervention, Stanford University, Stanford, CA, United States
| | - Sotirios Bisdas
- Department of Brain Repair and Rehabilitation, Queen Square Institute of Neurology, UCL, London, United Kingdom
- Department of Neuroradiology, The National Hospital for Neurology and Neurosurgery, University College London NHS Foundation Trust, London, United Kingdom
| | - Kostas Marias
- Computational BioMedicine Laboratory (CBML), Institute of Computer Science, Foundation for Research and Technology—Hellas (FORTH), Heraklion, Greece
- Department of Electrical and Computer Engineering, Hellenic Mediterranean University, Heraklion, Greece
| |
Collapse
|