Standardized evaluation of automatic methods for perivascular spaces segmentation in MRI - MICCAI 2024 challenge results.
Authors
Affiliations (21)
Affiliations (21)
- Centre for Sleep and Cognition (CSC) & Centre for Translational Magnetic Resonance Research (TMR), Yong Loo Lin School of Medicine, National University of Singapore, Singapore.
- National University Hospital, Singapore.
- Institute for Neuroscience and Cardiovascular Research, Row Fogo Centre for Research into Ageing and the Brain, Department of Neuroimaging Sciences, The University of Edinburgh, Edinburgh, UK; German Centre for Neurodegenerative Diseases (DZNE), Germany; Department Artificial Intelligence in Biomedical Engineering (AIBE), Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany; Faculty of Medicine, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany; Institute of Cognitive Neurology and Dementia Research (IKND), Otto von Guericke University Magdeburg, Magdeburg, Germany.
- Australian e-Health Research Centre, CSIRO Health and Biosecurity, Herston, 4029, Queensland, Australia; South Western Clinical School, University of New South Wales, Sydney, Australia.
- Australian e-Health Research Centre, CSIRO Health and Biosecurity, Herston, 4029, Queensland, Australia.
- Australian e-Health Research Centre, CSIRO Health and Biosecurity, Herston, 4029, Queensland, Australia; School of Electrical Engineering and Robotics, Queensland University of Technology, Brisbane, Australia.
- Central China Normal University, Wuhan, China.
- Fealinx, France.
- Groupe d'Imagerie Neurofonctionnelle (GIN), Institute of Neurodegenerative Diseases (IMN), UMR5293, CNRS, CEA, University of Bordeaux, Bordeaux, France; Bordeaux Population Health, INSERM, U1219, University of Bordeaux, Bordeaux, France.
- Groupe d'Imagerie Neurofonctionnelle (GIN), Institute of Neurodegenerative Diseases (IMN), UMR5293, CNRS, CEA, University of Bordeaux, Bordeaux, France.
- Department of Biomedical Engineering, Hankuk University of Foreign Studies, Yongin, South Korea.
- Research Institute of Computer Vision and Robotics (ViCOROB), Universitat de Girona, Catalonia, Spain.
- School of Mathematics, Nanjing University, Nanjing, China.
- Department of Neurosurgery, Klinikum Rechts der Isar, Technical University of Munich, Germany.
- Longhua Hospital Shanghai University of Traditional Chinese Medicine, Shanghai, China.
- Centre for Clinical Brain Sciences, UK Dementia Research Institute at The University of Edinburgh, The University of Edinburgh, Edinburgh, UK.
- Harvard Medical School, Boston, Massachusetts, USA.
- Healthy Longevity Translational Research Program, Yong Loo Lin School of Medicine, National University of Singapore, Singapore.
- Department of Pharmacology, National University of Singapore, Singapore.
- Centre for Clinical Brain Sciences, UK Dementia Research Institute at The University of Edinburgh, The University of Edinburgh, Edinburgh, UK. Electronic address: [email protected].
- Centre for Sleep and Cognition (CSC) & Centre for Translational Magnetic Resonance Research (TMR), Yong Loo Lin School of Medicine, National University of Singapore, Singapore; Healthy Longevity Translational Research Program, Yong Loo Lin School of Medicine, National University of Singapore, Singapore; Human Potential Translational Research Program and Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore; Department of Electrical and Computer Engineering, National University of Singapore, Singapore. Electronic address: [email protected].
Abstract
Perivascular spaces (PVS), when abnormally enlarged and visible in magnetic resonance imaging (MRI) structural sequences, are important imaging markers of cerebral small vessel disease and potential indicators of neurodegenerative conditions. Despite their clinical significance, automatic enlarged PVS (EPVS) segmentation remains challenging due to their small size, variable morphology, similarity with other pathological features, and limited annotated datasets. This paper presents the EPVS Challenge organized at MICCAI 2024, which aims to advance the development of automated algorithms for EPVS segmentation across multi-site data. We provided a diverse dataset comprising 100 training, 50 validation, and 50 testing scans collected from multiple international sites (UK, Singapore, and China) with varying MRI protocols and demographics. All annotations followed the STRIVE protocol to ensure standardized ground truth and covered the full brain parenchyma. Seven teams completed the full challenge, implementing various deep learning approaches primarily based on U-Net architectures with innovations in multi-modal processing, ensemble strategies, and transformer-based components. Performance was evaluated using dice similarity coefficient, absolute volume difference, recall, and precision metrics. The winning method employed MedNeXt architecture with a dual 2D/3D strategy for handling varying slice thicknesses. The top solutions showed relatively good performance on test data from seen datasets, but significant degradation of performance was observed on the previously unseen Shanghai cohort, highlighting cross-site generalization challenges due to domain shift. This challenge establishes an important benchmark for EPVS segmentation methods and underscores the need for the continued development of robust algorithms that can generalize in diverse clinical settings.