English

3D U$^2$-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation

Image and Video Processing 2019-09-16 v1 Computer Vision and Pattern Recognition

Abstract

Fully convolutional neural networks like U-Net have been the state-of-the-art methods in medical image segmentation. Practically, a network is highly specialized and trained separately for each segmentation task. Instead of a collection of multiple models, it is highly desirable to learn a universal data representation for different tasks, ideally a single model with the addition of a minimal number of parameters steered to each task. Inspired by the recent success of multi-domain learning in image classification, for the first time we explore a promising universal architecture that handles multiple medical segmentation tasks and is extendable for new tasks, regardless of different organs and imaging modalities. Our 3D Universal U-Net (3D U2^2-Net) is built upon separable convolution, assuming that {\it images from different domains have domain-specific spatial correlations which can be probed with channel-wise convolution while also share cross-channel correlations which can be modeled with pointwise convolution}. We evaluate the 3D U2^2-Net on five organ segmentation datasets. Experimental results show that this universal network is capable of competing with traditional models in terms of segmentation accuracy, while requiring only about 1%1\% of the parameters. Additionally, we observe that the architecture can be easily and effectively adapted to a new domain without sacrificing performance in the domains used to learn the shared parameterization of the universal network. We put the code of 3D U2^2-Net into public domain. \url{https://github.com/huangmozhilv/u2net_torch/}

Keywords

Cite

@article{arxiv.1909.06012,
  title  = {3D U$^2$-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation},
  author = {Chao Huang and Hu Han and Qingsong Yao and Shankuan Zhu and S. Kevin Zhou},
  journal= {arXiv preprint arXiv:1909.06012},
  year   = {2019}
}
R2 v1 2026-06-23T11:14:09.978Z