With the significantly increasing incidence and prevalence of abdominal diseases, there is a need to embrace greater use of new innovations and technology for the diagnosis and treatment of patients. Although deep-learning methods have notably been developed to assist radiologists in diagnosing abdominal diseases, existing models have the restricted ability to segment common lesions in the abdomen due to missing annotations for typical abdominal pathologies in their training datasets. To address the limitation, we introduce MSWAL, the first 3D Multi-class Segmentation of the Whole Abdominal Lesions dataset, which broadens the coverage of various common lesion types, such as gallstones, kidney stones, liver tumors, kidney tumors, pancreatic cancer, liver cysts, and kidney cysts. With CT scans collected from 694 patients (191,417 slices) of different genders across various scanning phases, MSWAL demonstrates strong robustness and generalizability. The transfer learning experiment from MSWAL to two public datasets, LiTS and KiTS, effectively demonstrates consistent improvements, with Dice Similarity Coefficient (DSC) increase of 3.00% for liver tumors and 0.89% for kidney tumors, demonstrating that the comprehensive annotations and diverse lesion types in MSWAL facilitate effective learning across different domains and data distributions. Furthermore, we propose Inception nnU-Net, a novel segmentation framework that effectively integrates an Inception module with the nnU-Net architecture to extract information from different receptive fields, achieving significant enhancement in both voxel-level DSC and region-level F1 compared to the cutting-edge public algorithms on MSWAL. Our dataset will be released after being accepted, and the code is publicly released atthis https URL.
View on arXiv@article{wu2025_2503.13560,
title={ MSWAL: 3D Multi-class Segmentation of Whole Abdominal Lesions Dataset },
author={ Zhaodong Wu and Qiaochu Zhao and Ming Hu and Yulong Li and Haochen Xue and Kang Dang and Zhengyong Jiang and Angelos Stefanidis and Qiufeng Wang and Imran Razzak and Zongyuan Ge and Junjun He and Yu Qiao and Zhong Zheng and Feilong Tang and Jionglong Su },
journal={arXiv preprint arXiv:2503.13560},
year={ 2025 }
}