A-Eval: A benchmark for cross-dataset and cross-modality evaluation of abdominal multi-organ segmentation

Open Webpage

Ziyan Huang, Zhongying Deng, Jin Ye, Haoyu Wang, Yanzhou Su, Tianbin Li, Hui Sun, Junlong Cheng, Jianpin Chen, Junjun He, Yun Gu, Shaoting Zhang, Lixu Gu, Yu Qiao

Published: 01 Jan 2025, Last Modified: 15 May 2025Medical Image Anal. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•A benchmark for cross-dataset/modality evaluation of abdominal segmentation.•Systematic evaluation of generalization across CT/MRI using 7 datasets.•Studies unlabeled data, multi-modality and joint training for generalization.•Studies different model backbones and scales for generalization.