Vasculature segmentation in 3D hierarchical phase-contrast tomography images of human kidneys.
Authors
Affiliations (11)
Affiliations (11)
- Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA. [email protected].
- Department of Mechanical Engineering, University College London, London, UK. [email protected].
- Department of Mechanical Engineering, University College London, London, UK.
- Faculty of Medicine, Department of Surgery & Cancer, Imperial College London, London, UK.
- UCL Centre for Medical Image Computing, London, UK.
- Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA.
- European Synchrotron Radiation Facility, Grenoble, France.
- Faculty of Medicine, National Heart and Lung Institute, Imperial College London, London, UK.
- Department of Anatomy (LADAF), Université Grenoble Alpes, Grenoble, France.
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA.
- Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN, USA. [email protected].
Abstract
Efficient algorithms are needed to segment vasculature in new 3D medical imaging datasets at scale for research and clinical applications. Manual segmentation of vessels in images is time-consuming and expensive whereas computational approaches have limited accuracy. We organize a global machine learning competition, engaging 1,401 participants, to promote development of deep learning methods for 3D blood vessel segmentation in Hierarchical Phase-Contrast Tomography (HiP-CT) datasets. This paper presents a meta-analysis of the top-performing solutions, focusing on segmentation accuracy and morphological analysis. The competition and subsequent analysis reveal convergent methodological innovations: pseudo-labeling approaches that exploit data distributions, metrics and loss functions that optimize for vessel surface and topology, and multi-scale approaches that handle data heterogeneity. Additionally, the paper presents techniques for building deep learning models for the defined task, metrics to assess and compare algorithm performance, and a dataset with manually annotated and curated gold standard segmentations for future studies in blood vessel segmentation within HiP-CT imaging.