CNM-UNet: Continuous Ordinary Differential Equations for Medical Image Segmentation
Tianqi Xu, Yashi Zhu, Quansong He, Yue Cao, Kaishen Wang, Zhang Yi, Tao He
Abstract
Integrating Ordinary Differential Equations (ODEs) with U-shaped neural networks has emerged as a novel direction in medical image segmentation. Current networks predominantly employ discretization methods incorporating ODEs. However, these methods face inherent trade-offs between model compactness, computational accuracy, and efficiency. Continuous ODE solutions were rarely studied because they face three limitations: high computational costs, long training time, and poor generalization ability. To address these limitations, we propose an innovative Continuous Neural Memory ODE UNet (CNM-UNet), which replaces all hierarchical decoder layers in vanilla UNet with a single Continuous Neural Memory ODEs Block (CNM-Block) decoder, significantly reducing computation costs and improving training efficiency. CNM-UNet leverages ODEs
BibTeX
@inproceedings{aaai2026_cnmunetcontinuou,
title = {CNM-UNet: Continuous Ordinary Differential Equations for Medical Image Segmentation},
author = {Tianqi Xu and Yashi Zhu and Quansong He and Yue Cao and Kaishen Wang and Zhang Yi and Tao He},
booktitle = {AAAI 2026},
year = {2026}
}