Code for "Vasculature segmentation in 3D hierarchical phase-contrast tomography images of human kidneys"

Yashvardhan Jain^1*+, Claire L. Walsh^2*+, Ekin Yagis², Shahab Aslani², Sonal Nandanwar², Yang Zhou², Juhyung Ha¹, Katherine S. Gustilo¹, Joseph Brunet^2,3, Shahrokh Rahmani^2,4, Paul Tafforeau³, Alexandre Bellier⁵, Griffin Weber⁶, Peter D. Lee², Katy Börner^1*

¹ Department of Intelligent Systems Engineering, Luddy School of Informatics, Computing, and Engineering, Indiana University, Bloomington, IN 47408, USA

² Department of Mechanical Engineering, University College London, London, UK

³ European Synchrotron Radiation Facility, Grenoble, France

⁴ National Heart and Lung Institute, Faculty of Medicine, Imperial College London, London, UK

⁵ Univ. Grenoble Alpes, Department of Anatomy (LADAF), Grenoble, France

⁶ Department of Biomedical Informatics, Harvard Medical School, Boston, MA, United States

⁺These authors contributed equally

^*Corresponding authors

Yashvardhan Jain ([email protected])

Claire Walsh ([email protected])

Katy Börner ([email protected])

Abstract

Efficient algorithms are needed to segment vasculature in new three-dimensional (3D) medical imaging datasets at scale for a wide range of research and clinical applications. Manual segmentation of vessels in images is time-consuming and expensive. Computational approaches are more scalable but have limitations in accuracy. We organized a global machine learning competition, engaging 1,401 participants, to help develop new deep learning methods for 3D blood vessel segmentation. This paper presents a detailed analysis of the top-performing solutions using manually curated 3D Hierarchical Phase-Contrast Tomography datasets of the human kidney, focussing on the segmentation accuracy and morphological analysis, thereby establishing a benchmark for future studies in blood vessel segmentation within phase-contrast tomography imaging.

Link to competition website: https://www.kaggle.com/competitions/blood-vessel-segmentation

Link to Skeleton Analysis files: https://github.com/HiPCTProject/Kaggle_skeleton_analyses