主动脏分支与区段的多类分割：AortaSeg24 挑战
图像与视频处理
2025-02-11 v1 人工智能
计算机视觉与模式识别
机器学习
摘要
对主动脏在运动断层造影（CTA）扫描的多类分割对于诊断和规划具有复杂内科治疗的患者至关重要。然而,现有方法将主动脏分割简化为二元问题,限制了其在不同分支和区段上测量直径的能力。此外,目前没有可支持开发多类主动脏分割方法的开源数据集。为填补这一空白,我们组织了 AortaSeg24 MICCAI 挑战,引入首个包含 100 个 CTA 体积、标注 23 个临床相关主动脏分支和区段的数据集。该数据集旨在促进模型开发和验证。挑战吸引了来自世界各地的 121 支队伍,参赛者利用诸如 nnU-Net 等最新框架,并探索新的技术,包括级联模型、数据增强策略和自定义损失函数。我们采用 Dice 相似系数（DSC）和归一化表面距离（NSD）评估提交的算法,概述前五名最佳队伍所采用的方法。本文介绍挑战设计、数据集细节、评估指标以及对前五名最佳算法的深入分析。标注后的数据集、评估代码和领先方法的实现均公开可用,以支持进一步研究。所有资源可访问 https://aortaseg24.grand-challenge.org。
引用
@article{arxiv.2502.05330,
title = {Multi-Class Segmentation of Aortic Branches and Zones in Computed Tomography Angiography: The AortaSeg24 Challenge},
author = {Muhammad Imran and Jonathan R. Krebs and Vishal Balaji Sivaraman and Teng Zhang and Amarjeet Kumar and Walker R. Ueland and Michael J. Fassler and Jinlong Huang and Xiao Sun and Lisheng Wang and Pengcheng Shi and Maximilian Rokuss and Michael Baumgartner and Yannick Kirchhof and Klaus H. Maier-Hein and Fabian Isensee and Shuolin Liu and Bing Han and Bong Thanh Nguyen and Dong-jin Shin and Park Ji-Woo and Mathew Choi and Kwang-Hyun Uhm and Sung-Jea Ko and Chanwoong Lee and Jaehee Chun and Jin Sung Kim and Minghui Zhang and Hanxiao Zhang and Xin You and Yun Gu and Zhaohong Pan and Xuan Liu and Xiaokun Liang and Markus Tiefenthaler and Enrique Almar-Munoz and Matthias Schwab and Mikhail Kotyushev and Rostislav Epifanov and Marek Wodzinski and Henning Muller and Abdul Qayyum and Moona Mazher and Steven A. Niederer and Zhiwei Wang and Kaixiang Yang and Jintao Ren and Stine Sofia Korreman and Yuchong Gao and Hongye Zeng and Haoyu Zheng and Rui Zheng and Jinghua Yue and Fugen Zhou and Bo Liu and Alexander Cosman and Muxuan Liang and Chang Zhao and Gilbert R. Upchurch and Jun Ma and Yuyin Zhou and Michol A. Cooper and Wei Shao},
journal= {arXiv preprint arXiv:2502.05330},
year = {2025}
}