Abstract
Segmentation of mesenteric arteries in abdominal CT is important for characterizing the anatomical relationship between the mesenteric vasculature and the small bowel, yet it remains challenging due to their small caliber, complex branching patterns, proximity to veins, and limited availability of annotated data. In this work, we introduce a three-step semi-automatic pipeline for constructing mesenteric arterial vessel masks on 3D abdominal CT scans, spanning from the superior mesenteric artery to distal branches near the small bowel. Our method combines iterative-learning-based preliminary mask generation, anatomy-guided distal vessel generation, and topology-aware post-processing. Using the generated annotations as labels, we evaluate existing state-of-the-art segmentation models on the Dice score and establish a standard for mesenteric arterial vessel segmentation. Our proposed annotation pipeline provides a foundation for automatic vessel segmentation and topology-aware analysis of small-bowel diseases in abdominal CT.
Links to Paper and Supplementary Materials
Main Paper (Open Access Version): https://papers.miccai.org/miccai-2026-sat/paper/AMAI_031.pdf
SharedIt Link: Not yet available
SpringerLink (DOI): Not yet available
Supplementary Material: Not Submitted
Link to Open Review
Open Review Page: https://openreview.net/profile?id=%7ERonald_Summers1
BibTex
@InProceedings{ChoHyu_Mesenteric_MICCAISAT2026,
author = { Cho, Hyuna AND Mathai, Tejas S. AND Summers, Ronald M.},
title = { { Mesenteric Arterial Vessel Segmentation in Abdominal CT with Small Bowel Obstruction } },
booktitle = {Medical Image Computing and Computer Assisted Intervention -- MICCAI 2026 Workshops and Challenges},
year = {2026},
publisher = {Springer Nature Switzerland},
volume = {LNCS 17273},
month = {pending},
page = {pending}
}