{"type":"ScholarlyArticle","title":"Volumetric Axial Disentanglement Enabling Advancing in Medical Image Segmentation","authors":[{"name":"Xingru Huang","slug":"xingru-huang","given":"Xingru","family":"Huang","affiliation":""},{"name":"Jian Huang","slug":"jian-huang","given":"Jian","family":"Huang","affiliation":""},{"name":"Yihao Guo","slug":"yihao-guo","given":"Yihao","family":"Guo","affiliation":""},{"name":"Tianyun Zhang","slug":"tianyun-zhang","given":"Tianyun","family":"Zhang","affiliation":""},{"name":"Zhao Huang","slug":"zhao-huang","given":"Zhao","family":"Huang","affiliation":""},{"name":"Yaqi Wang","slug":"yaqi-wang","given":"Yaqi","family":"Wang","affiliation":""},{"name":"Ruipu Tang","slug":"ruipu-tang","given":"Ruipu","family":"Tang","affiliation":""},{"name":"Guangliang Cheng","slug":"guangliang-cheng","given":"Guangliang","family":"Cheng","affiliation":""},{"name":"Shaowei Jiang","slug":"shaowei-jiang","given":"Shaowei","family":"Jiang","affiliation":""},{"name":"Zhiwen Zheng","slug":"zhiwen-zheng","given":"Zhiwen","family":"Zheng","affiliation":""},{"name":"Jin Liu","slug":"jin-liu","given":"Jin","family":"Liu","affiliation":""},{"name":"Renjie Ruan","slug":"renjie-ruan","given":"Renjie","family":"Ruan","affiliation":""},{"name":"Xiaoshuai Zhang","slug":"xiaoshuai-zhang","given":"Xiaoshuai","family":"Zhang","affiliation":""}],"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.","doi":"10.24963/ijcai.2025/134","url":"https://ijcai.org/proceedings/2025/134","pdf":"https://ijcai.org/proceedings/2025/0134.pdf","markdown":"https://ijcai.org/proceedings/2025/134.md","bibtex":"https://ijcai.org/proceedings/2025/bibtex/134","volume":{"slug":"2025","title":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2025","url":"https://ijcai.org/proceedings/2025/","year":2025,"location":"Montreal, Canada","dates":"16-22 August 2025","editors":"James Kwok","isbn":"978-1-956792-06-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2025"},"section":"Computer Vision","track":"Main Track","number":134,"pages":{"first":1197,"last":1205},"keywords":["Multidisciplinary Topics and Applications: MTA: Health and medicine","Multidisciplinary Topics and Applications: MTA: Bioinformatics","Computer Vision: CV: Biomedical image analysis"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}