Vasculature segmentation in 3D hierarchical phase-contrast tomography images of human kidneys
Year: 2026
Type: review
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.
Source: Nature Communications
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $6,990
Funders: Silicon Valley Community Foundation, Canadian Institute for Advanced Research, Royal Academy of Engineering, European Synchrotron Radiation Facility, National Institutes of Health, Medical Research Council, National Institute of Mental Health, NIH Office of the Director, National Cancer Institute, National Institute of Diabetes and Digestive and Kidney Diseases, National Institute of Neurological Disorders and Stroke, Common Fund
Awards: 3D Multiscale Biomolecular Human Reference Atlas Construction, Visualization and Usage [4 of 5], G1218620557, Central Hub for Kidney Precision Medicine, Imaging dynamics in biophysical/biochemical processes across the hierarchical scales (BioPro Network), G2259944664, G2947732725, G3081837368, G3718867181, G5496694919, The Human Body Atlas: High-Resolution, Functional Mapping of Voxel, Vector, and Meta Datasets, G7500717991, G808865357, National Institute of Diabetes and Digestive and Kidney Diseases ATLAS (D2K-ATLAS) Center as an accessible, comprehensive data portfolio for renal and genitourinary development and disease, G8547529128, G8857852000, G8904941954, KPMP Kidney Mapping and Atlas Project (KMAP), BRAIN CONNECTS: The center for Large-scale Imaging of Neural Circuits (LINC), Cellular Senescence Network (SenNet) Consortium Organization and Data Coordinating Center (CODCC)
OpenAlex ID: W4401938832