Work

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

Year: 2026

Type: software

Abstract: This repository contains all the code (winning team solutions, analysis for manuscript) and trained model weights (for top-5 winning teams) associated with the Kaggle competition "SenNet + HOA - Hacking the Human Vasculature in 3D", and is part of the paper "Vasculature segmentation in 3D hierarchical phase-contrast tomography images of human kidneys". It is structured as follows: code-github-snapshot: Contains the snapshot of two GitHub repositories containing code solutions from top-5 winning teams, as well as analysis code for the paper. top5-teams-trained-model-weights: Contains trained model weights for the models from top-5 winning teams. The code is also available on GitHub: https://github.com/cns-iu/hra-sennet-hoa-kaggle-2024 https://github.com/HiPCTProject/Kaggle_skeleton_analyses The associated manuscript can be found at https://doi.org/10.1101/2024.08.25.609595.

Source: Zenodo (CERN European Organization for Nuclear Research)

DOI: 10.5281/zenodo.19685078

Authors: Jain, Yashvardhan, Walsh, Claire L., Yagis, Ekin, Aslani, Shahab, Nandanwar, Sonal, Zhou, Yang, Ha, Juhyung, Gustilo, Katherine S., Brunet, Joseph, Rahmani, Shahrokh, Tafforeau, Paul, Bellier, Alexandre, Weber, Griffin M., Lee, Peter D., Börner, Katy

Institutions: Indiana University Bloomington, Indiana University, University College London, Imperial College London, European Synchrotron Radiation Facility, Beth Israel Deaconess Medical Center, Harvard University

Language: English

Topic: Medical Image Segmentation Techniques

Subfield: Computer Vision and Pattern Recognition

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7155041996

Cites:

Cited by:

Related to: 10