1
|
Demuth S, Paris J, Faddeenkov I, De Sèze J, Gourraud PA. Clinical applications of deep learning in neuroinflammatory diseases: A scoping review. Rev Neurol (Paris) 2024:S0035-3787(24)00522-8. [PMID: 38772806 DOI: 10.1016/j.neurol.2024.04.004] [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: 02/18/2024] [Revised: 03/26/2024] [Accepted: 04/09/2024] [Indexed: 05/23/2024]
Abstract
BACKGROUND Deep learning (DL) is an artificial intelligence technology that has aroused much excitement for predictive medicine due to its ability to process raw data modalities such as images, text, and time series of signals. OBJECTIVES Here, we intend to give the clinical reader elements to understand this technology, taking neuroinflammatory diseases as an illustrative use case of clinical translation efforts. We reviewed the scope of this rapidly evolving field to get quantitative insights about which clinical applications concentrate the efforts and which data modalities are most commonly used. METHODS We queried the PubMed database for articles reporting DL algorithms for clinical applications in neuroinflammatory diseases and the radiology.healthairegister.com website for commercial algorithms. RESULTS The review included 148 articles published between 2018 and 2024 and five commercial algorithms. The clinical applications could be grouped as computer-aided diagnosis, individual prognosis, functional assessment, the segmentation of radiological structures, and the optimization of data acquisition. Our review highlighted important discrepancies in efforts. The segmentation of radiological structures and computer-aided diagnosis currently concentrate most efforts with an overrepresentation of imaging. Various model architectures have addressed different applications, relatively low volume of data, and diverse data modalities. We report the high-level technical characteristics of the algorithms and synthesize narratively the clinical applications. Predictive performances and some common a priori on this topic are finally discussed. CONCLUSION The currently reported efforts position DL as an information processing technology, enhancing existing modalities of paraclinical investigations and bringing perspectives to make innovative ones actionable for healthcare.
Collapse
Affiliation(s)
- S Demuth
- Inserm U1064, CR2TI - Center for Research in Transplantation and Translational Immunology, Nantes University, 44000 Nantes, France; Inserm U1119 : biopathologie de la myéline, neuroprotection et stratégies thérapeutiques, University of Strasbourg, 1, rue Eugène-Boeckel - CS 60026, 67084 Strasbourg, France.
| | - J Paris
- Inserm U1064, CR2TI - Center for Research in Transplantation and Translational Immunology, Nantes University, 44000 Nantes, France
| | - I Faddeenkov
- Inserm U1064, CR2TI - Center for Research in Transplantation and Translational Immunology, Nantes University, 44000 Nantes, France
| | - J De Sèze
- Inserm U1119 : biopathologie de la myéline, neuroprotection et stratégies thérapeutiques, University of Strasbourg, 1, rue Eugène-Boeckel - CS 60026, 67084 Strasbourg, France; Department of Neurology, University Hospital of Strasbourg, 1, avenue Molière, 67200 Strasbourg, France; Inserm CIC 1434 Clinical Investigation Center, University Hospital of Strasbourg, 1, avenue Molière, 67200 Strasbourg, France
| | - P-A Gourraud
- Inserm U1064, CR2TI - Center for Research in Transplantation and Translational Immunology, Nantes University, 44000 Nantes, France; "Data clinic", Department of Public Health, University Hospital of Nantes, Nantes, France
| |
Collapse
|
2
|
Hu Y, Huang ZA, Liu R, Xue X, Sun X, Song L, Tan KC. Source Free Semi-Supervised Transfer Learning for Diagnosis of Mental Disorders on fMRI Scans. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2023; 45:13778-13795. [PMID: 37486851 DOI: 10.1109/tpami.2023.3298332] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 07/26/2023]
Abstract
The high prevalence of mental disorders gradually poses a huge pressure on the public healthcare services. Deep learning-based computer-aided diagnosis (CAD) has emerged to relieve the tension in healthcare institutions by detecting abnormal neuroimaging-derived phenotypes. However, training deep learning models relies on sufficient annotated datasets, which can be costly and laborious. Semi-supervised learning (SSL) and transfer learning (TL) can mitigate this challenge by leveraging unlabeled data within the same institution and advantageous information from source domain, respectively. This work is the first attempt to propose an effective semi-supervised transfer learning (SSTL) framework dubbed S3TL for CAD of mental disorders on fMRI data. Within S3TL, a secure cross-domain feature alignment method is developed to generate target-related source model in SSL. Subsequently, we propose an enhanced dual-stage pseudo-labeling approach to assign pseudo-labels for unlabeled samples in target domain. Finally, an advantageous knowledge transfer method is conducted to improve the generalization capability of the target model. Comprehensive experimental results demonstrate that S3TL achieves competitive accuracies of 69.14%, 69.65%, and 72.62% on ABIDE-I, ABIDE-II, and ADHD-200 datasets, respectively. Furthermore, the simulation experiments also demonstrate the application potential of S3TL through model interpretation analysis and federated learning extension.
Collapse
|
3
|
Spagnolo F, Depeursinge A, Schädelin S, Akbulut A, Müller H, Barakovic M, Melie-Garcia L, Bach Cuadra M, Granziera C. How far MS lesion detection and segmentation are integrated into the clinical workflow? A systematic review. Neuroimage Clin 2023; 39:103491. [PMID: 37659189 PMCID: PMC10480555 DOI: 10.1016/j.nicl.2023.103491] [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: 08/02/2023] [Accepted: 08/04/2023] [Indexed: 09/04/2023]
Abstract
INTRODUCTION Over the past few years, the deep learning community has developed and validated a plethora of tools for lesion detection and segmentation in Multiple Sclerosis (MS). However, there is an important gap between validating models technically and clinically. To this end, a six-step framework necessary for the development, validation, and integration of quantitative tools in the clinic was recently proposed under the name of the Quantitative Neuroradiology Initiative (QNI). AIMS Investigate to what extent automatic tools in MS fulfill the QNI framework necessary to integrate automated detection and segmentation into the clinical neuroradiology workflow. METHODS Adopting the systematic Cochrane literature review methodology, we screened and summarised published scientific articles that perform automatic MS lesions detection and segmentation. We categorised the retrieved studies based on their degree of fulfillment of QNI's six-steps, which include a tool's technical assessment, clinical validation, and integration. RESULTS We found 156 studies; 146/156 (94%) fullfilled the first QNI step, 155/156 (99%) the second, 8/156 (5%) the third, 3/156 (2%) the fourth, 5/156 (3%) the fifth and only one the sixth. CONCLUSIONS To date, little has been done to evaluate the clinical performance and the integration in the clinical workflow of available methods for MS lesion detection/segmentation. In addition, the socio-economic effects and the impact on patients' management of such tools remain almost unexplored.
Collapse
Affiliation(s)
- Federico Spagnolo
- Translational Imaging in Neurology (ThINK) Basel, Department of Biomedical Engineering, Faculty of Medicine, University Hospital Basel and University of Basel, Basel, Switzerland; Department of Neurology, University Hospital Basel, Basel, Switzerland; Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), University Hospital Basel and University of Basel, Basel, Switzerland; MedGIFT, Institute of Informatics, School of Management, HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland, Sierre, Switzerland
| | - Adrien Depeursinge
- MedGIFT, Institute of Informatics, School of Management, HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland, Sierre, Switzerland; Nuclear Medicine and Molecular Imaging Department, Lausanne University Hospital (CHUV) and University of Lausanne, Lausanne, Switzerland
| | - Sabine Schädelin
- Translational Imaging in Neurology (ThINK) Basel, Department of Biomedical Engineering, Faculty of Medicine, University Hospital Basel and University of Basel, Basel, Switzerland; Clinical Trial Unit, Department of Clinical Research, University Hospital Basel, University of Basel, Basel, Switzerland
| | - Aysenur Akbulut
- Translational Imaging in Neurology (ThINK) Basel, Department of Biomedical Engineering, Faculty of Medicine, University Hospital Basel and University of Basel, Basel, Switzerland; Ankara University School of Medicine, Ankara, Turkey
| | - Henning Müller
- MedGIFT, Institute of Informatics, School of Management, HES-SO Valais-Wallis University of Applied Sciences and Arts Western Switzerland, Sierre, Switzerland; The Sense Research and Innovation Center, Lausanne and Sion, Switzerland
| | - Muhamed Barakovic
- Translational Imaging in Neurology (ThINK) Basel, Department of Biomedical Engineering, Faculty of Medicine, University Hospital Basel and University of Basel, Basel, Switzerland; Department of Neurology, University Hospital Basel, Basel, Switzerland; Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), University Hospital Basel and University of Basel, Basel, Switzerland
| | - Lester Melie-Garcia
- Translational Imaging in Neurology (ThINK) Basel, Department of Biomedical Engineering, Faculty of Medicine, University Hospital Basel and University of Basel, Basel, Switzerland; Department of Neurology, University Hospital Basel, Basel, Switzerland; Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), University Hospital Basel and University of Basel, Basel, Switzerland
| | - Meritxell Bach Cuadra
- CIBM Center for Biomedical Imaging, Lausanne, Switzerland; Radiology Department, Lausanne University Hospital (CHUV) and University of Lausanne, Lausanne, Switzerland
| | - Cristina Granziera
- Translational Imaging in Neurology (ThINK) Basel, Department of Biomedical Engineering, Faculty of Medicine, University Hospital Basel and University of Basel, Basel, Switzerland; Department of Neurology, University Hospital Basel, Basel, Switzerland; Research Center for Clinical Neuroimmunology and Neuroscience Basel (RC2NB), University Hospital Basel and University of Basel, Basel, Switzerland.
| |
Collapse
|
4
|
Liu D, Cabezas M, Wang D, Tang Z, Bai L, Zhan G, Luo Y, Kyle K, Ly L, Yu J, Shieh CC, Nguyen A, Kandasamy Karuppiah E, Sullivan R, Calamante F, Barnett M, Ouyang W, Cai W, Wang C. Multiple sclerosis lesion segmentation: revisiting weighting mechanisms for federated learning. Front Neurosci 2023; 17:1167612. [PMID: 37274196 PMCID: PMC10232857 DOI: 10.3389/fnins.2023.1167612] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2023] [Accepted: 04/24/2023] [Indexed: 06/06/2023] Open
Abstract
Background and introduction Federated learning (FL) has been widely employed for medical image analysis to facilitate multi-client collaborative learning without sharing raw data. Despite great success, FL's applications remain suboptimal in neuroimage analysis tasks such as lesion segmentation in multiple sclerosis (MS), due to variance in lesion characteristics imparted by different scanners and acquisition parameters. Methods In this work, we propose the first FL MS lesion segmentation framework via two effective re-weighting mechanisms. Specifically, a learnable weight is assigned to each local node during the aggregation process, based on its segmentation performance. In addition, the segmentation loss function in each client is also re-weighted according to the lesion volume for the data during training. Results The proposed method has been validated on two FL MS segmentation scenarios using public and clinical datasets. Specifically, the case-wise and voxel-wise Dice score of the proposed method under the first public dataset is 65.20 and 74.30, respectively. On the second in-house dataset, the case-wise and voxel-wise Dice score is 53.66, and 62.31, respectively. Discussions and conclusions The Comparison experiments on two FL MS segmentation scenarios using public and clinical datasets have demonstrated the effectiveness of the proposed method by significantly outperforming other FL methods. Furthermore, the segmentation performance of FL incorporating our proposed aggregation mechanism can achieve comparable performance to that from centralized training with all the raw data.
Collapse
Affiliation(s)
- Dongnan Liu
- School of Computer Science, The University of Sydney, Sydney, NSW, Australia
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
| | - Mariano Cabezas
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
| | - Dongang Wang
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
| | - Zihao Tang
- School of Computer Science, The University of Sydney, Sydney, NSW, Australia
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
| | - Lei Bai
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
- School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia
| | - Geng Zhan
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
| | - Yuling Luo
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
| | - Kain Kyle
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
| | - Linda Ly
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
| | - James Yu
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
| | - Chun-Chien Shieh
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
| | - Aria Nguyen
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
| | | | - Ryan Sullivan
- School of Biomedical Engineering, The University of Sydney, Sydney, NSW, Australia
| | - Fernando Calamante
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
- School of Biomedical Engineering, The University of Sydney, Sydney, NSW, Australia
- Sydney Imaging, The University of Sydney, Sydney, NSW, Australia
| | - Michael Barnett
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
| | - Wanli Ouyang
- School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia
| | - Weidong Cai
- School of Computer Science, The University of Sydney, Sydney, NSW, Australia
| | - Chenyu Wang
- Brain and Mind Centre, The University of Sydney, Sydney, NSW, Australia
- Sydney Neuroimaging Analysis Centre, Camperdown, NSW, Australia
| |
Collapse
|
5
|
van Tulder G, de Bruijne M. Unpaired, unsupervised domain adaptation assumes your domains are already similar. Med Image Anal 2023; 87:102825. [PMID: 37116296 DOI: 10.1016/j.media.2023.102825] [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: 04/29/2022] [Revised: 03/30/2023] [Accepted: 04/17/2023] [Indexed: 04/30/2023]
Abstract
Unsupervised domain adaptation is a popular method in medical image analysis, but it can be tricky to make it work: without labels to link the domains, domains must be matched using feature distributions. If there is no additional information, this often leaves a choice between multiple possibilities to map the data that may be equally likely but not equally correct. In this paper we explore the fundamental problems that may arise in unsupervised domain adaptation, and discuss conditions that might still make it work. Focusing on medical image analysis, we argue that images from different domains may have similar class balance, similar intensities, similar spatial structure, or similar textures. We demonstrate how these implicit conditions can affect domain adaptation performance in experiments with synthetic data, MNIST digits, and medical images. We observe that practical success of unsupervised domain adaptation relies on existing similarities in the data, and is anything but guaranteed in the general case. Understanding these implicit assumptions is a key step in identifying potential problems in domain adaptation and improving the reliability of the results.
Collapse
Affiliation(s)
- Gijs van Tulder
- Data Science group, Faculty of Science, Radboud University, Postbus 9010, 6500 GL Nijmegen, The Netherlands; Biomedical Imaging Group, Erasmus MC, Postbus 2040, 3000 CA Rotterdam, The Netherlands.
| | - Marleen de Bruijne
- Biomedical Imaging Group, Erasmus MC, Postbus 2040, 3000 CA Rotterdam, The Netherlands; Department of Computer Science, University of Copenhagen, Universitetsparken 1, 2100 Copenhagen, Denmark.
| |
Collapse
|
6
|
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
|
7
|
Chen J, Chen S, Wee L, Dekker A, Bermejo I. Deep learning based unpaired image-to-image translation applications for medical physics: a systematic review. Phys Med Biol 2023; 68. [PMID: 36753766 DOI: 10.1088/1361-6560/acba74] [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: 08/05/2022] [Accepted: 02/08/2023] [Indexed: 02/10/2023]
Abstract
Purpose. There is a growing number of publications on the application of unpaired image-to-image (I2I) translation in medical imaging. However, a systematic review covering the current state of this topic for medical physicists is lacking. The aim of this article is to provide a comprehensive review of current challenges and opportunities for medical physicists and engineers to apply I2I translation in practice.Methods and materials. The PubMed electronic database was searched using terms referring to unpaired (unsupervised), I2I translation, and medical imaging. This review has been reported in compliance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. From each full-text article, we extracted information extracted regarding technical and clinical applications of methods, Transparent Reporting for Individual Prognosis Or Diagnosis (TRIPOD) study type, performance of algorithm and accessibility of source code and pre-trained models.Results. Among 461 unique records, 55 full-text articles were included in the review. The major technical applications described in the selected literature are segmentation (26 studies), unpaired domain adaptation (18 studies), and denoising (8 studies). In terms of clinical applications, unpaired I2I translation has been used for automatic contouring of regions of interest in MRI, CT, x-ray and ultrasound images, fast MRI or low dose CT imaging, CT or MRI only based radiotherapy planning, etc Only 5 studies validated their models using an independent test set and none were externally validated by independent researchers. Finally, 12 articles published their source code and only one study published their pre-trained models.Conclusion. I2I translation of medical images offers a range of valuable applications for medical physicists. However, the scarcity of external validation studies of I2I models and the shortage of publicly available pre-trained models limits the immediate applicability of the proposed methods in practice.
Collapse
Affiliation(s)
- Junhua Chen
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, 6229 ET, The Netherlands
| | - Shenlun Chen
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, 6229 ET, The Netherlands
| | - Leonard Wee
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, 6229 ET, The Netherlands
| | - Andre Dekker
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, 6229 ET, The Netherlands
| | - Inigo Bermejo
- Department of Radiation Oncology (MAASTRO), GROW School for Oncology and Developmental Biology, Maastricht University Medical Centre+, Maastricht, 6229 ET, The Netherlands
| |
Collapse
|
8
|
Saat P, Nogovitsyn N, Hassan MY, Ganaie MA, Souza R, Hemmati H. A domain adaptation benchmark for T1-weighted brain magnetic resonance image segmentation. Front Neuroinform 2022; 16:919779. [PMID: 36213544 PMCID: PMC9538795 DOI: 10.3389/fninf.2022.919779] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/13/2022] [Accepted: 08/29/2022] [Indexed: 01/18/2023] Open
Abstract
Accurate brain segmentation is critical for magnetic resonance imaging (MRI) analysis pipelines. Machine-learning-based brain MR image segmentation methods are among the state-of-the-art techniques for this task. Nevertheless, the segmentations produced by machine learning models often degrade in the presence of expected domain shifts between the test and train sets data distributions. These domain shifts are expected due to several factors, such as scanner hardware and software differences, technology updates, and differences in MRI acquisition parameters. Domain adaptation (DA) methods can make machine learning models more resilient to these domain shifts. This paper proposes a benchmark for investigating DA techniques for brain MR image segmentation using data collected across sites with scanners from different vendors (Philips, Siemens, and General Electric). Our work provides labeled data, publicly available source code for a set of baseline and DA models, and a benchmark for assessing different brain MR image segmentation techniques. We applied the proposed benchmark to evaluate two segmentation tasks: skull-stripping; and white-matter, gray-matter, and cerebrospinal fluid segmentation, but the benchmark can be extended to other brain structures. Our main findings during the development of this benchmark are that there is not a single DA technique that consistently outperforms others, and hyperparameter tuning and computational times for these methods still pose a challenge before broader adoption of these methods in the clinical practice.
Collapse
Affiliation(s)
- Parisa Saat
- Electrical and Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, Canada
- *Correspondence: Parisa Saat
| | - Nikita Nogovitsyn
- Centre for Depression and Suicide Studies, St. Michael's Hospital, Toronto, ON, Canada
- Mood Disorders Program, Department of Psychiatry and Behavioural Neurosciences, McMaster University, Hamilton, ON, Canada
| | - Muhammad Yusuf Hassan
- Electrical and Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, Canada
- Electrical Engineering, Indian Institute of Technology, Gandhinagar, Gujarat, India
| | - Muhammad Athar Ganaie
- Electrical and Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, Canada
- Chemical Engineering, Indian Institute of Technology, Kharagpur, West Bengal, India
| | - Roberto Souza
- Electrical and Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, Canada
- Hotchkiss Brain Institute, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada
| | - Hadi Hemmati
- Electrical and Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, Canada
- Electrical Engineering and Computer Science, Lassonde School of Engineering, York University, Toronto, ON, Canada
| |
Collapse
|
9
|
Ma Y, Zhang C, Cabezas M, Song Y, Tang Z, Liu D, Cai W, Barnett M, Wang C. Multiple Sclerosis Lesion Analysis in Brain Magnetic Resonance Images: Techniques and Clinical Applications. IEEE J Biomed Health Inform 2022; 26:2680-2692. [PMID: 35171783 DOI: 10.1109/jbhi.2022.3151741] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Abstract
Multiple sclerosis (MS) is a chronic inflammatory and degenerative disease of the central nervous system, characterized by the appearance of focal lesions in the white and gray matter that topographically correlate with an individual patients neurological symptoms and signs. Magnetic resonance imaging (MRI) provides detailed in-vivo structural information, permitting the quantification and categorization of MS lesions that critically inform disease management. Traditionally, MS lesions have been manually annotated on 2D MRI slices, a process that is inefficient and prone to inter-/intra-observer errors. Recently, automated statistical imaging analysis techniques have been proposed to detect and segment MS lesions based on MRI voxel intensity. However, their effectiveness is limited by the heterogeneity of both MRI data acquisition techniques and the appearance of MS lesions. By learning complex lesion representations directly from images, deep learning techniques have achieved remarkable breakthroughs in the MS lesion segmentation task. Here, we provide a comprehensive review of state-of-the-art automatic statistical and deep-learning MS segmentation methods and discuss current and future clinical applications. Further, we review technical strategies, such as domain adaptation, to enhance MS lesion segmentation in real-world clinical settings.
Collapse
|
10
|
Bento M, Fantini I, Park J, Rittner L, Frayne R. Deep Learning in Large and Multi-Site Structural Brain MR Imaging Datasets. Front Neuroinform 2022; 15:805669. [PMID: 35126080 PMCID: PMC8811356 DOI: 10.3389/fninf.2021.805669] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2021] [Accepted: 12/27/2021] [Indexed: 12/22/2022] Open
Abstract
Large, multi-site, heterogeneous brain imaging datasets are increasingly required for the training, validation, and testing of advanced deep learning (DL)-based automated tools, including structural magnetic resonance (MR) image-based diagnostic and treatment monitoring approaches. When assembling a number of smaller datasets to form a larger dataset, understanding the underlying variability between different acquisition and processing protocols across the aggregated dataset (termed “batch effects”) is critical. The presence of variation in the training dataset is important as it more closely reflects the true underlying data distribution and, thus, may enhance the overall generalizability of the tool. However, the impact of batch effects must be carefully evaluated in order to avoid undesirable effects that, for example, may reduce performance measures. Batch effects can result from many sources, including differences in acquisition equipment, imaging technique and parameters, as well as applied processing methodologies. Their impact, both beneficial and adversarial, must be considered when developing tools to ensure that their outputs are related to the proposed clinical or research question (i.e., actual disease-related or pathological changes) and are not simply due to the peculiarities of underlying batch effects in the aggregated dataset. We reviewed applications of DL in structural brain MR imaging that aggregated images from neuroimaging datasets, typically acquired at multiple sites. We examined datasets containing both healthy control participants and patients that were acquired using varying acquisition protocols. First, we discussed issues around Data Access and enumerated the key characteristics of some commonly used publicly available brain datasets. Then we reviewed methods for correcting batch effects by exploring the two main classes of approaches: Data Harmonization that uses data standardization, quality control protocols or other similar algorithms and procedures to explicitly understand and minimize unwanted batch effects; and Domain Adaptation that develops DL tools that implicitly handle the batch effects by using approaches to achieve reliable and robust results. In this narrative review, we highlighted the advantages and disadvantages of both classes of DL approaches, and described key challenges to be addressed in future studies.
Collapse
Affiliation(s)
- Mariana Bento
- Electrical and Software Engineering, Schulich School of Engineering, University of Calgary, Calgary, AB, Canada
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
- Calgary Image Processing and Analysis Centre, Foothills Medical Centre, Calgary, AB, Canada
- *Correspondence: Mariana Bento
| | - Irene Fantini
- School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil
| | - Justin Park
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
- Calgary Image Processing and Analysis Centre, Foothills Medical Centre, Calgary, AB, Canada
- Radiology and Clinical Neurosciences, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada
| | - Leticia Rittner
- School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil
| | - Richard Frayne
- Hotchkiss Brain Institute, University of Calgary, Calgary, AB, Canada
- Calgary Image Processing and Analysis Centre, Foothills Medical Centre, Calgary, AB, Canada
- Radiology and Clinical Neurosciences, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada
- Seaman Family MR Research Centre, Foothills Medical Centre, Calgary, AB, Canada
| |
Collapse
|
11
|
Prostate Cancer Radiogenomics-From Imaging to Molecular Characterization. Int J Mol Sci 2021; 22:ijms22189971. [PMID: 34576134 PMCID: PMC8465891 DOI: 10.3390/ijms22189971] [Citation(s) in RCA: 51] [Impact Index Per Article: 17.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/30/2021] [Revised: 09/06/2021] [Accepted: 09/10/2021] [Indexed: 12/24/2022] Open
Abstract
Radiomics and genomics represent two of the most promising fields of cancer research, designed to improve the risk stratification and disease management of patients with prostate cancer (PCa). Radiomics involves a conversion of imaging derivate quantitative features using manual or automated algorithms, enhancing existing data through mathematical analysis. This could increase the clinical value in PCa management. To extract features from imaging methods such as magnetic resonance imaging (MRI), the empiric nature of the analysis using machine learning and artificial intelligence could help make the best clinical decisions. Genomics information can be explained or decoded by radiomics. The development of methodologies can create more-efficient predictive models and can better characterize the molecular features of PCa. Additionally, the identification of new imaging biomarkers can overcome the known heterogeneity of PCa, by non-invasive radiological assessment of the whole specific organ. In the future, the validation of recent findings, in large, randomized cohorts of PCa patients, can establish the role of radiogenomics. Briefly, we aimed to review the current literature of highly quantitative and qualitative results from well-designed studies for the diagnoses, treatment, and follow-up of prostate cancer, based on radiomics, genomics and radiogenomics research.
Collapse
|
12
|
Kontopodis EE, Papadaki E, Trivizakis E, Maris TG, Simos P, Papadakis GZ, Tsatsakis A, Spandidos DA, Karantanas A, Marias K. Emerging deep learning techniques using magnetic resonance imaging data applied in multiple sclerosis and clinical isolated syndrome patients (Review). Exp Ther Med 2021; 22:1149. [PMID: 34504594 PMCID: PMC8393268 DOI: 10.3892/etm.2021.10583] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2021] [Accepted: 07/29/2021] [Indexed: 12/18/2022] Open
Abstract
Computer-aided diagnosis systems aim to assist clinicians in the early identification of abnormal signs in order to optimize the interpretation of medical images and increase diagnostic precision. Multiple sclerosis (MS) and clinically isolated syndrome (CIS) are chronic inflammatory, demyelinating diseases affecting the central nervous system. Recent advances in deep learning (DL) techniques have led to novel computational paradigms in MS and CIS imaging designed for automatic segmentation and detection of areas of interest and automatic classification of anatomic structures, as well as optimization of neuroimaging protocols. To this end, there are several publications presenting artificial intelligence-based predictive models aiming to increase diagnostic accuracy and to facilitate optimal clinical management in patients diagnosed with MS and/or CIS. The current study presents a thorough review covering DL techniques that have been applied in MS and CIS during recent years, shedding light on their current advances and limitations.
Collapse
Affiliation(s)
- Eleftherios E Kontopodis
- Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology-Hellas, 70013 Heraklion, Greece.,Department of Radiology, Medical School, University of Crete, 70013 Heraklion, Greece
| | - Efrosini Papadaki
- Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology-Hellas, 70013 Heraklion, Greece.,Department of Radiology, Medical School, University of Crete, 70013 Heraklion, Greece
| | - Eleftherios Trivizakis
- Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology-Hellas, 70013 Heraklion, Greece.,Department of Radiology, Medical School, University of Crete, 70013 Heraklion, Greece
| | - Thomas G Maris
- Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology-Hellas, 70013 Heraklion, Greece.,Department of Radiology, Medical School, University of Crete, 70013 Heraklion, Greece
| | - Panagiotis Simos
- Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology-Hellas, 70013 Heraklion, Greece.,Department of Psychiatry and Behavioral Sciences, Medical School, University of Crete, 70013 Heraklion, Greece
| | - Georgios Z Papadakis
- Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology-Hellas, 70013 Heraklion, Greece.,Department of Radiology, Medical School, University of Crete, 70013 Heraklion, Greece
| | - Aristidis Tsatsakis
- Centre of Toxicology Science and Research, Faculty of Medicine, University of Crete, 71003 Heraklion, Greece
| | - Demetrios A Spandidos
- Laboratory of Clinical Virology, Medical School, University of Crete, 71003 Heraklion, Greece
| | - Apostolos Karantanas
- Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology-Hellas, 70013 Heraklion, Greece.,Department of Radiology, Medical School, University of Crete, 70013 Heraklion, Greece
| | - Kostas Marias
- Computational BioMedicine Laboratory, Institute of Computer Science, Foundation for Research and Technology-Hellas, 70013 Heraklion, Greece.,Department of Electrical and Computer Engineering, Hellenic Mediterranean University, 71410 Heraklion, Greece
| |
Collapse
|
13
|
Moazami F, Lefevre-Utile A, Papaloukas C, Soumelis V. Machine Learning Approaches in Study of Multiple Sclerosis Disease Through Magnetic Resonance Images. Front Immunol 2021; 12:700582. [PMID: 34456913 PMCID: PMC8385534 DOI: 10.3389/fimmu.2021.700582] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2021] [Accepted: 07/26/2021] [Indexed: 11/13/2022] Open
Abstract
Multiple sclerosis (MS) is one of the most common autoimmune diseases which is commonly diagnosed and monitored using magnetic resonance imaging (MRI) with a combination of clinical manifestations. The purpose of this review is to highlight the main applications of Machine Learning (ML) models and their performance in the MS field using MRI. We reviewed the articles of the last decade and grouped them based on the applications of ML in MS using MRI data into four categories: 1) Automated diagnosis of MS, 2) Prediction of MS disease progression, 3) Differentiation of MS stages, 4) Differentiation of MS from similar disorders.
Collapse
Affiliation(s)
- Faezeh Moazami
- Université de Paris, Institut de Recherche Saint-Louis, Institut National de la Santé et de la Recherche Médicale (INSERM) U976, Hôpital Saint-Louis, Paris, France
| | - Alain Lefevre-Utile
- Université de Paris, Institut de Recherche Saint-Louis, Institut National de la Santé et de la Recherche Médicale (INSERM) U976, Hôpital Saint-Louis, Paris, France.,Université Paris-Saclay, Saint Aubin, France.,Assistance Publique Hopitaux de Paris (APHP), General Pediatric and Pediatric Emergency Department, Jean Verdier Hospital, Bondy, France
| | - Costas Papaloukas
- Department of Biological Applications and Technology, University of Ioannina, Ioannina, Greece
| | - Vassili Soumelis
- Université de Paris, Institut de Recherche Saint-Louis, Institut National de la Santé et de la Recherche Médicale (INSERM) U976, Hôpital Saint-Louis, Paris, France.,Assistance Publique Hopitaux de Paris (APHP), Hôpital Saint-Louis, Immunology-Histocompatibility Department, Paris, France
| |
Collapse
|
14
|
Song X, Zeng Y, Tong L, Shu J, Bao G, Yan B. P3-MSDA: Multi-Source Domain Adaptation Network for Dynamic Visual Target Detection. Front Hum Neurosci 2021; 15:685173. [PMID: 34434096 PMCID: PMC8381600 DOI: 10.3389/fnhum.2021.685173] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/24/2021] [Accepted: 07/07/2021] [Indexed: 11/13/2022] Open
Abstract
Single-trial electroencephalogram detection has been widely applied in brain-computer interface (BCI) systems. Moreover, an individual generalized model is significant for applying the dynamic visual target detection BCI system in real life because of the time jitter of the detection latency, the dynamics and complexity of visual background. Hence, we developed an unsupervised multi-source domain adaptation network (P3-MSDA) for dynamic visual target detection. In this network, a P3 map-clustering method was proposed for source domain selection. The adversarial domain adaptation was conducted for domain alignment to eliminate individual differences, and prediction probabilities were ranked and returned to guide the input of target samples for imbalanced data classification. The results showed that individuals with a strong P3 map selected by the proposed P3 map-clustering method perform best on the source domain. Compared with existing schemes, the proposed P3-MSDA network achieved the highest classification accuracy and F1 score using five labeled individuals with a strong P3 map as the source domain. These findings can have a significant meaning in building an individual generalized model for dynamic visual target detection.
Collapse
Affiliation(s)
- Xiyu Song
- Henan Key Laboratory of Imaging and Intelligent Processing, Chinese People's Liberation Army (PLA) Strategic Support Force Information Engineering University, Zhengzhou, China
| | - Ying Zeng
- Henan Key Laboratory of Imaging and Intelligent Processing, Chinese People's Liberation Army (PLA) Strategic Support Force Information Engineering University, Zhengzhou, China.,Key Laboratory for NeuroInformation of Ministry of Education, School of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, China
| | - Li Tong
- Henan Key Laboratory of Imaging and Intelligent Processing, Chinese People's Liberation Army (PLA) Strategic Support Force Information Engineering University, Zhengzhou, China
| | - Jun Shu
- Henan Key Laboratory of Imaging and Intelligent Processing, Chinese People's Liberation Army (PLA) Strategic Support Force Information Engineering University, Zhengzhou, China
| | - Guangcheng Bao
- Henan Key Laboratory of Imaging and Intelligent Processing, Chinese People's Liberation Army (PLA) Strategic Support Force Information Engineering University, Zhengzhou, China
| | - Bin Yan
- Henan Key Laboratory of Imaging and Intelligent Processing, Chinese People's Liberation Army (PLA) Strategic Support Force Information Engineering University, Zhengzhou, China
| |
Collapse
|
15
|
Shoeibi A, Khodatars M, Jafari M, Moridian P, Rezaei M, Alizadehsani R, Khozeimeh F, Gorriz JM, Heras J, Panahiazar M, Nahavandi S, Acharya UR. Applications of deep learning techniques for automated multiple sclerosis detection using magnetic resonance imaging: A review. Comput Biol Med 2021; 136:104697. [PMID: 34358994 DOI: 10.1016/j.compbiomed.2021.104697] [Citation(s) in RCA: 50] [Impact Index Per Article: 16.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/11/2021] [Revised: 07/22/2021] [Accepted: 07/25/2021] [Indexed: 11/18/2022]
Abstract
Multiple Sclerosis (MS) is a type of brain disease which causes visual, sensory, and motor problems for people with a detrimental effect on the functioning of the nervous system. In order to diagnose MS, multiple screening methods have been proposed so far; among them, magnetic resonance imaging (MRI) has received considerable attention among physicians. MRI modalities provide physicians with fundamental information about the structure and function of the brain, which is crucial for the rapid diagnosis of MS lesions. Diagnosing MS using MRI is time-consuming, tedious, and prone to manual errors. Research on the implementation of computer aided diagnosis system (CADS) based on artificial intelligence (AI) to diagnose MS involves conventional machine learning and deep learning (DL) methods. In conventional machine learning, feature extraction, feature selection, and classification steps are carried out by using trial and error; on the contrary, these steps in DL are based on deep layers whose values are automatically learn. In this paper, a complete review of automated MS diagnosis methods performed using DL techniques with MRI neuroimaging modalities is provided. Initially, the steps involved in various CADS proposed using MRI modalities and DL techniques for MS diagnosis are investigated. The important preprocessing techniques employed in various works are analyzed. Most of the published papers on MS diagnosis using MRI modalities and DL are presented. The most significant challenges facing and future direction of automated diagnosis of MS using MRI modalities and DL techniques are also provided.
Collapse
Affiliation(s)
- Afshin Shoeibi
- Faculty of Electrical Engineering, Biomedical Data Acquisition Lab (BDAL), K. N. Toosi University of Technology, Tehran, Iran.
| | - Marjane Khodatars
- Faculty of Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran
| | - Mahboobeh Jafari
- Electrical and Computer Engineering Faculty, Semnan University, Semnan, Iran
| | - Parisa Moridian
- Faculty of Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran
| | - Mitra Rezaei
- Electrical and Computer Engineering Dept., Tarbiat Modares University, Tehran, Iran
| | - Roohallah Alizadehsani
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, Australia
| | - Fahime Khozeimeh
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, Australia
| | - Juan Manuel Gorriz
- Department of Signal Theory, Networking and Communications, Universidad de Granada, Spain; Department of Psychiatry. University of Cambridge, UK
| | - Jónathan Heras
- Department of Mathematics and Computer Science, University of La Rioja, La Rioja, Spain
| | | | - Saeid Nahavandi
- Institute for Intelligent Systems Research and Innovation (IISRI), Deakin University, Geelong, Australia
| | - U Rajendra Acharya
- Department of Biomedical Engineering, School of Science and Technology, Singapore University of Social Sciences, Singapore; Dept. of Electronics and Computer Engineering, Ngee Ann Polytechnic, 599489, Singapore; Department of Bioinformatics and Medical Engineering, Asia University, Taiwan
| |
Collapse
|
16
|
Kushibar K, Salem M, Valverde S, Rovira À, Salvi J, Oliver A, Lladó X. Transductive Transfer Learning for Domain Adaptation in Brain Magnetic Resonance Image Segmentation. Front Neurosci 2021; 15:608808. [PMID: 33994917 PMCID: PMC8116893 DOI: 10.3389/fnins.2021.608808] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2020] [Accepted: 03/26/2021] [Indexed: 11/13/2022] Open
Abstract
Segmentation of brain images from Magnetic Resonance Images (MRI) is an indispensable step in clinical practice. Morphological changes of sub-cortical brain structures and quantification of brain lesions are considered biomarkers of neurological and neurodegenerative disorders and used for diagnosis, treatment planning, and monitoring disease progression. In recent years, deep learning methods showed an outstanding performance in medical image segmentation. However, these methods suffer from generalisability problem due to inter-centre and inter-scanner variabilities of the MRI images. The main objective of the study is to develop an automated deep learning segmentation approach that is accurate and robust to the variabilities in scanner and acquisition protocols. In this paper, we propose a transductive transfer learning approach for domain adaptation to reduce the domain-shift effect in brain MRI segmentation. The transductive scenario assumes that there are sets of images from two different domains: (1) source-images with manually annotated labels; and (2) target-images without expert annotations. Then, the network is jointly optimised integrating both source and target images into the transductive training process to segment the regions of interest and to minimise the domain-shift effect. We proposed to use a histogram loss in the feature level to carry out the latter optimisation problem. In order to demonstrate the benefit of the proposed approach, the method has been tested in two different brain MRI image segmentation problems using multi-centre and multi-scanner databases for: (1) sub-cortical brain structure segmentation; and (2) white matter hyperintensities segmentation. The experiments showed that the segmentation performance of a pre-trained model could be significantly improved by up to 10%. For the first segmentation problem it was possible to achieve a maximum improvement from 0.680 to 0.799 in average Dice Similarity Coefficient (DSC) metric and for the second problem the average DSC improved from 0.504 to 0.602. Moreover, the improvements after domain adaptation were on par or showed better performance compared to the commonly used traditional unsupervised segmentation methods (FIRST and LST), also achieving faster execution time. Taking this into account, this work presents one more step toward the practical implementation of deep learning algorithms into the clinical routine.
Collapse
Affiliation(s)
- Kaisar Kushibar
- Institute of Computer Vision and Robotics, University of Girona, Girona, Spain
| | - Mostafa Salem
- Institute of Computer Vision and Robotics, University of Girona, Girona, Spain.,Computer Science Department, Faculty of Computers and Information, Assiut University, Asyut, Egypt
| | - Sergi Valverde
- Institute of Computer Vision and Robotics, University of Girona, Girona, Spain
| | - Àlex Rovira
- Magnetic Resonance Unit, Department of Radiology, Vall d'Hebron University Hospital, Barcelona, Spain
| | - Joaquim Salvi
- Institute of Computer Vision and Robotics, University of Girona, Girona, Spain
| | - Arnau Oliver
- Institute of Computer Vision and Robotics, University of Girona, Girona, Spain
| | - Xavier Lladó
- Institute of Computer Vision and Robotics, University of Girona, Girona, Spain
| |
Collapse
|
17
|
Valverde JM, Imani V, Abdollahzadeh A, De Feo R, Prakash M, Ciszek R, Tohka J. Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review. J Imaging 2021; 7:66. [PMID: 34460516 PMCID: PMC8321322 DOI: 10.3390/jimaging7040066] [Citation(s) in RCA: 30] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2021] [Revised: 03/26/2021] [Accepted: 03/29/2021] [Indexed: 11/25/2022] Open
Abstract
(1) Background: Transfer learning refers to machine learning techniques that focus on acquiring knowledge from related tasks to improve generalization in the tasks of interest. In magnetic resonance imaging (MRI), transfer learning is important for developing strategies that address the variation in MR images from different imaging protocols or scanners. Additionally, transfer learning is beneficial for reutilizing machine learning models that were trained to solve different (but related) tasks to the task of interest. The aim of this review is to identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging; (2) Methods: We performed a systematic literature search for articles that applied transfer learning to MR brain imaging tasks. We screened 433 studies for their relevance, and we categorized and extracted relevant information, including task type, application, availability of labels, and machine learning methods. Furthermore, we closely examined brain MRI-specific transfer learning approaches and other methods that tackled issues relevant to medical imaging, including privacy, unseen target domains, and unlabeled data; (3) Results: We found 129 articles that applied transfer learning to MR brain imaging tasks. The most frequent applications were dementia-related classification tasks and brain tumor segmentation. The majority of articles utilized transfer learning techniques based on convolutional neural networks (CNNs). Only a few approaches utilized clearly brain MRI-specific methodology, and considered privacy issues, unseen target domains, or unlabeled data. We proposed a new categorization to group specific, widely-used approaches such as pretraining and fine-tuning CNNs; (4) Discussion: There is increasing interest in transfer learning for brain MRI. Well-known public datasets have clearly contributed to the popularity of Alzheimer's diagnostics/prognostics and tumor segmentation as applications. Likewise, the availability of pretrained CNNs has promoted their utilization. Finally, the majority of the surveyed studies did not examine in detail the interpretation of their strategies after applying transfer learning, and did not compare their approach with other transfer learning approaches.
Collapse
Affiliation(s)
| | | | | | | | | | | | - Jussi Tohka
- A.I. Virtanen Institute for Molecular Sciences, University of Eastern Finland, 70150 Kuopio, Finland; (J.M.V.); (V.I.); (A.A.); (R.D.F.); (M.P.); (R.C.)
| |
Collapse
|
18
|
Zeng C, Gu L, Liu Z, Zhao S. Review of Deep Learning Approaches for the Segmentation of Multiple Sclerosis Lesions on Brain MRI. Front Neuroinform 2020; 14:610967. [PMID: 33328949 PMCID: PMC7714963 DOI: 10.3389/fninf.2020.610967] [Citation(s) in RCA: 34] [Impact Index Per Article: 8.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/28/2020] [Accepted: 10/26/2020] [Indexed: 11/18/2022] Open
Abstract
In recent years, there have been multiple works of literature reviewing methods for automatically segmenting multiple sclerosis (MS) lesions. However, there is no literature systematically and individually review deep learning-based MS lesion segmentation methods. Although the previous review also included methods based on deep learning, there are some methods based on deep learning that they did not review. In addition, their review of deep learning methods did not go deep into the specific categories of Convolutional Neural Network (CNN). They only reviewed these methods in a generalized form, such as supervision strategy, input data handling strategy, etc. This paper presents a systematic review of the literature in automated multiple sclerosis lesion segmentation based on deep learning. Algorithms based on deep learning reviewed are classified into two categories through their CNN style, and their strengths and weaknesses will also be given through our investigation and analysis. We give a quantitative comparison of the methods reviewed through two metrics: Dice Similarity Coefficient (DSC) and Positive Predictive Value (PPV). Finally, the future direction of the application of deep learning in MS lesion segmentation will be discussed.
Collapse
Affiliation(s)
- Chenyi Zeng
- School of Intelligent Systems Engineering, Sun Yat-Sen University, Guangzhou, China
| | - Lin Gu
- RIKEN AIP, Tokyo, Japan
- The University of Tokyo, Tokyo, Japan
| | - Zhenzhong Liu
- Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control, School of Mechanical Engineering, Tianjin University of Technology, Tianjin, China
- National Demonstration Center for Experimental Mechanical and Electrical Engineering Education, Tianjin University of Technology, Tianjin, China
| | - Shen Zhao
- School of Intelligent Systems Engineering, Sun Yat-Sen University, Guangzhou, China
| |
Collapse
|
19
|
Ackaouy A, Courty N, Vallée E, Commowick O, Barillot C, Galassi F. Unsupervised Domain Adaptation With Optimal Transport in Multi-Site Segmentation of Multiple Sclerosis Lesions From MRI Data. Front Comput Neurosci 2020; 14:19. [PMID: 32210780 PMCID: PMC7075308 DOI: 10.3389/fncom.2020.00019] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/23/2019] [Accepted: 02/12/2020] [Indexed: 12/31/2022] Open
Abstract
Automatic segmentation of Multiple Sclerosis (MS) lesions from Magnetic Resonance Imaging (MRI) images is essential for clinical assessment and treatment planning of MS. Recent years have seen an increasing use of Convolutional Neural Networks (CNNs) for this task. Although these methods provide accurate segmentation, their applicability in clinical settings remains limited due to a reproducibility issue across different image domains. MS images can have highly variable characteristics across patients, MRI scanners and imaging protocols; retraining a supervised model with data from each new domain is not a feasible solution because it requires manual annotation from expert radiologists. In this work, we explore an unsupervised solution to the problem of domain shift. We present a framework, Seg-JDOT, which adapts a deep model so that samples from a source domain and samples from a target domain sharing similar representations will be similarly segmented. We evaluated the framework on a multi-site dataset, MICCAI 2016, and showed that the adaptation toward a target site can bring remarkable improvements in a model performance over standard training.
Collapse
Affiliation(s)
| | - Nicolas Courty
- Panama/Obélix, INRIA, IRISA, Université de Bretagne Sud, Vannes, France
| | | | | | | | | |
Collapse
|