Multi-center neuroimaging studies face technical variability due to batch differences across sites, which potentially hinders data aggregation and impacts study reliability.Recent efforts in neuroimaging harmonization have aimed to minimize these technical gaps and reduce technical variability across batches. While Generative Adversarial Networks (GAN) has been a prominent method for addressing image harmonization tasks, GAN-harmonized images suffer from artifacts or anatomical distortions. Given the advancements of denoising diffusion probabilistic model which produces high-fidelity images, we have assessed the efficacy of the diffusion model for neuroimaging harmonization. we have demonstrated the diffusion model's superior capability in harmonizing images from multiple domains, while GAN-based methods are limited to harmonizing images between two domains per model. Our experiments highlight that the learned domain invariant anatomical condition reinforces the model to accurately preserve the anatomical details while differentiating batch differences at each diffusion step. Our proposed method has been tested on two public neuroimaging dataset ADNI1 and ABIDE II, yielding harmonization results with consistent anatomy preservation and superior FID score compared to the GAN-based methods. We have conducted multiple analysis including extensive quantitative and qualitative evaluations against the baseline models, ablation study showcasing the benefits of the learned conditions, and improvements in the consistency of perivascular spaces (PVS) segmentation through harmonization.
HACA3: A Unified Approach for Multi-site MR Image Harmonization
Johns Hopkins University（约翰斯·霍普金斯大学）；National Institute on Aging, National Institutes of Health（美国国立卫生研究院国家老龄化研究所）；Johns Hopkins School of Medicine（约翰斯·霍普金斯大学医学院）
Université Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Inserm U1216（法国国家健康与医学研究院 U1216）；Grenoble Institut for Neurosciences（格勒诺布尔神经科学研究所）
ImUnity is an original deep-learning model designed for efficient and flexible MR image harmonization. A VAE-GAN network, coupled with a confusion module and an optional biological preservation module, uses multiple 2D-slices taken from different anatomical locations in each subject of the training database, as well as image contrast transformations for its self-supervised training. It eventually generates 'corrected' MR images that can be used for various multi-center population studies. Using 3 open source databases (ABIDE, OASIS and SRPBS), which contain MR images from multiple acquisition …
University of Basel（巴塞尔大学）；University Hospital Basel（巴塞尔大学医院）
Magnetic resonance (MR) images from multiple sources often show differences in image contrast related to acquisition settings or the used scanner type. For long-term studies, longitudinal comparability is essential but can be impaired by these contrast differences, leading to biased results when using automated evaluation tools. This study presents a diffusion model-based approach for contrast harmonization. We use a data set consisting of scans of 18 Multiple Sclerosis patients and 22 healthy controls. Each subject was scanned in two MR scanners of different magnetic field strengths (1.5 T an…
Harmonization Across Imaging Locations(HAIL): One-Shot Learning for Brain MRI
Children’s National Hospital（美国儿童国家医疗中心）；George Washington University（乔治·华盛顿大学）；Children’s Hospital Colorado（科罗拉多儿童医院）；Children’s Hospital of Philadelphia（费城儿童医院）
University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
Harmonization improves data consistency and is central to effective integration of diverse imaging data acquired across multiple sites. Recent deep learning techniques for harmonization are predominantly supervised in nature and hence require imaging data of the same human subjects to be acquired at multiple sites. Data collection as such requires the human subjects to travel across sites and is hence challenging, costly, and impractical, more so when sufficient sample size is needed for reliable network training. Here we show how harmonization can be achieved with a deep neural network that d…
New York University Tandon School of Engineering（纽约大学坦登工程学院）
Deep networks are now ubiquitous in large-scale multi-center imaging studies. However, the direct aggregation of images across sites is contraindicated for downstream statistical and deep learning-based image analysis due to inconsistent contrast, resolution, and noise. To this end, in the absence of paired data, variations of Cycle-consistent Generative Adversarial Networks have been used to harmonize image sets between a source and target domain. Importantly, these methods are prone to instability, contrast inversion, intractable manipulation of pathology, and steganographic mappings which l…
IHF-Harmony: Multi-Modality Magnetic Resonance Images Harmonization using Invertible Hierarchy Flow Model
Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hong Kong（健康科技与信息技术系，香港理工大学，香港）；School of Integrated Circuits and Electronics, Beijing Institute of Technology, China（集成电路与电子学院，北京理工大学，中国）；Mental Health Research Center, The Hong Kong Polytechnic University, Hong Kong（心理健康研究中心，香港理工大学，香港）；Department of Biomedical Engineering, Johns Hopkins University, USA（生物医学工程系，约翰霍普金斯大学，美国）
The desire to train complex machine learning algorithms and to increase the statistical power in association studies drives neuroimaging research to use ever-larger datasets. The most obvious way to increase sample size is by pooling scans from independent studies. However, simple pooling is often ill-advised as selection, measurement, and confounding biases may creep in and yield spurious correlations. In this work, we combine 35,320 magnetic resonance images of the brain from 17 studies to examine bias in neuroimaging. In the first experiment, Name That Dataset, we provide empirical evidence…
MOX, Department of Mathematics, Politecnico di Milano（MOX数学系，米兰理工大学）；Department of Mathematics, Università di Genova（基因瓦大学数学系）；Department of Neuroscience, Rehabilitation, Ophthalmology, Genetics and Maternal-Child Sciences, Università di Genova（基因瓦大学神经科学、康复、眼科、遗传学和妇产科学系）；Department of Biomedical and Neuromotor Sciences, University of Bologna（博洛尼亚大学生物医学与神经运动科学系）；IRCCS Institute of Neurological Science of Bologna, Bellaria Hospital（博洛尼亚IRCCS神经科学研究所，贝拉里亚医院）；Laboratory of Neuroinformatics, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli（神经信息学实验室，IRCCS福蒂贝拉蒂利中心圣约翰迪奥研究所）；Department of Statistical Sciences, Università Cattolica del Sacro Cuore（圣心大学统计学系）；Health Data Science Centre, Human Technopole（人类技术园区健康数据科学中心）
Wavelet-Fusion Diffusion Model for Multimodal Brain MRI Synthesis with Modality and Metadata Conditioning
Department of Psychology & Neuroscience, Auckland University of Technology（心理学与神经科学系，奥克兰技术大学）；Department of Psychiatry, University of Melbourne（精神病学系，墨尔本大学）
4DLoG: Generative Modeling of Neurodegenerative Brain Anatomy with 4D Longitudinal Diffusion Model
Department of Electrical and Computer Engineering（电气与计算机工程系）；Department of Radiology（放射学系）；Department of Electrical and Computer Engineering, Department of Computer Science（电气与计算机工程系、计算机科学系）
White Matter Geometry-Guided Score-Based Diffusion Model for Tissue Microstructure Imputation in Tractography Imaging
Harvard Medical School（哈佛医学院）；School of Computer Science, The University of Sydney（悉尼大学计算机学院）；Brigham and Women’s Hospital（布里格姆妇女医院）；University of Electronic Science and Technology of China（电子科技大学）
Malong LLC（码隆科技）；Southern University of Science and Technology（南方科技大学）；Inception Institute of Artificial Intelligence（Inception人工智能研究院）
Recent advances in neuroscience have highlighted the effectiveness of multi-modal medical data for investigating certain pathologies and understanding human cognition. However, obtaining full sets of different modalities is limited by various factors, such as long acquisition times, high examination costs and artifact suppression. In addition, the complexity, high dimensionality and heterogeneity of neuroimaging data remains another key challenge in leveraging existing randomized scans effectively, as data of the same modality is often measured differently by different machines. There is a cle…
Inter-vendor harmonization of Computed Tomography (CT) reconstruction kernels using unpaired image translation
Vanderbilt University（范德堡大学）；Vanderbilt University Medical Center（范德堡大学医学中心）；Amsterdam University Medical Center（阿姆斯特丹大学医学中心）；University of Amsterdam（阿姆斯特丹大学）
Phy-Diff: Physics-guided Hourglass Diffusion Model for Diffusion MRI Synthesis
School of Science and Engineering, University of Dundee（邓迪大学科学与工程学院）；University of Cambridge（剑桥大学）；University of Bath（巴斯大学）；School of Medicine, University of Dundee（邓迪大学医学院）
Department of Radiology and Biomedical Research Imaging Center (BRIC), University of North Carolina at Chapel Hill（放射科与生物医学研究成像中心（BRIC）、北卡罗来纳大学教堂山分校）；Lampe Joint Department of Biomedical Engineering, University of North Carolina at Chapel Hill and North Carolina State University（Lampe联合生物医学工程部门、北卡罗来纳大学教堂山分校和北卡罗来纳州立大学）
University of Pennsylvania（宾夕法尼亚大学）；University of Texas San Antonio Health Science Center（德克萨斯大学圣安东尼奥健康科学中心）；Florey Institute of Neuroscience and Mental Health（弗洛里神经科学与心理健康研究所）；University of Melbourne（墨尔本大学）；Nankai University Affiliated Tianjin Anding Hospital（南开大学附属天津安定医院）；Tianjin Medical University（天津医科大学）；University of Greifswald（格赖夫斯瓦尔德大学）；University of Wisconsin School of Medicine and Public Health（威斯康星大学医学与公共卫生学院）；CSIRO Health and Biosecurity（澳大利亚联邦科学与工业研究组织健康与生物安全部）；Ludwig Maximilian University of Munich（慕尼黑大学）；Washington University in St. Louis（圣路易斯华盛顿大学）；Johns Hopkins University School of Medicine（约翰霍普金斯大学医学院）；Ernst-Moritz-Arndt University（恩斯特·莫里茨·阿恩特大学）；National Institute on Aging（美国国家老龄化研究所）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；German Centre for Cardiovascular Research（德国心血管研究中心）
Conventional and deep learning-based methods have shown great potential in the medical imaging domain, as means for deriving diagnostic, prognostic, and predictive biomarkers, and by contributing to precision medicine. However, these methods have yet to see widespread clinical adoption, in part due to limited generalization performance across various imaging devices, acquisition protocols, and patient populations. In this work, we propose a new paradigm in which data from a diverse range of acquisition conditions are "harmonized" to a common reference domain, where accurate model learning and …
Multi-modal MRIs are widely used in neuroimaging applications since different MR sequences provide complementary information about brain structures. Recent works have suggested that multi-modal deep learning analysis can benefit from explicitly disentangling anatomical (shape) and modality (appearance) information into separate image presentations. In this work, we challenge mainstream strategies by showing that they do not naturally lead to representation disentanglement both in theory and in practice. To address this issue, we propose a margin loss that regularizes the similarity in relation…
Imperial College London（帝国理工学院）；ETH Zurich（苏黎世联邦理工学院）
This is an empirical study to investigate the impact of scanner effects when using machine learning on multi-site neuroimaging data. We utilize structural T1-weighted brain MRI obtained from two different studies, Cam-CAN and UK Biobank. For the purpose of our investigation, we construct a dataset consisting of brain scans from 592 age- and sex-matched individuals, 296 subjects from each original study. Our results demonstrate that even after careful pre-processing with state-of-the-art neuroimaging pipelines a classifier can easily distinguish between the origin of the data with very high acc…
Looking deeper into interpretable deep learning in neuroimaging: a comprehensive survey
Georgia State University（佐治亚州立大学）；Georgia Institute of Technology（佐治亚理工学院）；Emory University（埃默里大学）；Tri-institutional Center for Translational Research in Neuroimaging and Data Science（三机构神经影像与数据科学转化研究中心）
Explainable AI Methods for Neuroimaging: Systematic Failures of Common Tools, the Need for Domain-Specific Validation, and a Proposal for Safe Application
Charité – Universitätsmedizin Berlin（夏里特医学院）；Freie Universität Berlin（柏林自由大学）；Humboldt-Universität zu Berlin（柏林洪堡大学）；Berlin Institute of Health（柏林健康研究所）；Hertie Institute for AI in Brain Health（赫蒂脑健康人工智能研究所）；University of Tübingen（图宾根大学）；University College London（伦敦大学学院）；Glenn Biggs Institute for Alzheimer's and Neurodegenerative Diseases（格伦·比格斯阿尔茨海默病与神经退行性疾病研究所）；University of Texas Health Science Center at San Antonio（圣安东尼奥德克萨斯大学健康科学中心）；Bernstein Center for Computational Neuroscience（伯恩斯坦计算神经科学中心）；Technische Universität Berlin（柏林工业大学）；Physikalisch-Technische Bundesanstalt（德国联邦物理技术研究院）；Tübingen AI Center（图宾根人工智能中心）
Beyond the LUMIR challenge: The pathway to foundational registration models
The Russell H. Morgan Department of Radiology（Russell H. Morgan放射科）；Radiological Science, Johns Hopkins Medical School（约翰霍普金斯医学院放射科学）；Department of Computer Science, Aalto University（阿尔托大学计算机科学系）；Cornell University（康奈尔大学）；Canon Medical Systems (China) Co. Ltd.（佳能医疗系统（中国）有限公司）；School of Biomedical Engineering, Shenzhen University Medical School（深圳大学医学院生物医学工程学院）；Department of Imaging Physics, Delft University of Technology（代尔夫特理工大学成像物理系）；Technical University of Munich（慕尼黑技术大学）；Radboud University Medical Center（拉德伯德大学医学中心）；Inria, Paris, France（法国巴黎Inria）
Diffusion Bridge Models for 3D Medical Image Translation
University of California Riverside（加州大学河滨分校）；Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California（加州大学洛杉矶分校医学学院）；Information Sciences Institute, University of Southern California（加州大学洛杉矶分校信息科学研究所）
Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School（阿提诺拉A.马丁诺斯生物医学成像中心、麻省总医院和哈佛医学院）；Department of Neurology, Massachusetts General Hospital（麻省总医院神经科）；Hawkes Institute, University College London（霍克斯研究所、伦敦大学学院）；Danish Research Centre for Magnetic Resonance Department of Radiology and Nuclear Medicine, Copenhagen University Hospital – Amager and Hvidovre（丹麦磁共振研究中心放射科和核医学科、哥本哈根大学医院-阿马格和赫维多雷）；Computer Science & Artificial Intelligence Laboratory (CSAIL), Massachusetts Institute of Technology（计算机科学与人工智能实验室（CSAIL）、麻省理工学院）
Asymmetric Paired-Annotation Learning for Multi-Structure ULF Pediatric Brain MRI Segmentation
VinUniversity；College of Engineering & Computer Science, VinUniversity（VinUniversity工程与计算机科学学院）；Hanoi University of Science and Technology（河内科技大学）；University of Information Technology, VNU-HCM（胡志明市国家大学信息技术大学）；Carnegie Mellon University（卡内基梅隆大学）；Northwestern University（西北大学）；Center for Innovations in Health Sciences, VinUniversity（VinUniversity健康科学创新中心）
针对0.064 T ULF儿科脑部MRI分割难题，提出基于nnU-Net的非对称监督策略AURA，利用两类非等效标注训练，在16例数据上取得优于基线的分割性能。
