Volumetric Axial Disentanglement Enabling Advancing in Medical Image Segmentation

Huang, Xingru; Huang, Jian; Guo, Yihao; Zhang, Tianyun; Huang, Zhao; Wang, Yaqi; Tang, Ruipu; Cheng, Guangliang; Jiang, Shaowei; Zheng, Zhiwen; Liu, Jin; Ruan, Renjie; Zhang, Xiaoshuai

doi:10.24963/ijcai.2025/134

Volumetric Axial Disentanglement Enabling Advancing in Medical Image Segmentation

Xingru Huang, Jian Huang, Yihao Guo, Tianyun Zhang, Zhao Huang, Yaqi Wang, Ruipu Tang, Guangliang Cheng, Shaowei Jiang, Zhiwen Zheng, Jin Liu, Renjie Ruan, Xiaoshuai Zhang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 1197-1205.

https://doi.org/10.24963/ijcai.2025/134

Keywords

Multidisciplinary Topics and Applications: MTA: Health and medicine
Multidisciplinary Topics and Applications: MTA: Bioinformatics
Computer Vision: CV: Biomedical image analysis

Abstract

Information retrieved from three dimensions is treated uniformly in CNN-based volumetric segmentation methods. However, such neglect of axial disparities fails to capture true spatio-temporal variations. This paper introduces the volumetric axial disentanglement to address the disparities in spatial information along different axial dimensions. Building on this concept, we propose the Post-Axial Refiner (PaR) module to refine segmentation masks by implementing axial disentanglement on the specific axis of the volumetric medical sequences. As a plug-and-play enhancement to existing volumetric segmentation architecture, PaR further utilizes specialized attention approaches to learn disentangled post-decoding features, enhancing spatial representation and structural detail. Validation on various datasets demonstrates PaR's consistent elevation of segmentation precision and boundary clarity across 11 baselines and different imaging modalities, achieving state-of-the-art performance on multiple datasets. Experimental tests demonstrate the ability of volumetric axial disentanglement to refine the segmentation of volumetric medical images. Code is released at https://github.com/IMOP-lab/PaR-Pytorch.

Xingru Huang, Jian Huang, Yihao Guo, Tianyun Zhang, Zhao Huang, Yaqi Wang, Ruipu Tang, Guangliang Cheng, Shaowei Jiang, Zhiwen Zheng, Jin Liu, Renjie Ruan, and Xiaoshuai Zhang. 2025. Volumetric Axial Disentanglement Enabling Advancing in Medical Image Segmentation. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 1197–1205. https://doi.org/10.24963/ijcai.2025/134

@inproceedings{ijcai2025p134,
  title     = {Volumetric Axial Disentanglement Enabling Advancing in Medical Image Segmentation},
  author    = {Huang, Xingru and Huang, Jian and Guo, Yihao and Zhang, Tianyun and Huang, Zhao and Wang, Yaqi and Tang, Ruipu and Cheng, Guangliang and Jiang, Shaowei and Zheng, Zhiwen and Liu, Jin and Ruan, Renjie and Zhang, Xiaoshuai},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {1197--1205},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/134},
  url       = {https://doi.org/10.24963/ijcai.2025/134},
}

TY  - CPAPER
TI  - Volumetric Axial Disentanglement Enabling Advancing in Medical Image Segmentation
AU  - Huang, Xingru
AU  - Huang, Jian
AU  - Guo, Yihao
AU  - Zhang, Tianyun
AU  - Huang, Zhao
AU  - Wang, Yaqi
AU  - Tang, Ruipu
AU  - Cheng, Guangliang
AU  - Jiang, Shaowei
AU  - Zheng, Zhiwen
AU  - Liu, Jin
AU  - Ruan, Renjie
AU  - Zhang, Xiaoshuai
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 1197
EP  - 1205
DO  - 10.24963/ijcai.2025/134
UR  - https://doi.org/10.24963/ijcai.2025/134
ER  -