# 3D U2-Net: A 3D Universal U-Net for Multi-Domain Medical Image Segmentation

arXiv: https://arxiv.org/abs/1909.06012 · HTML: https://mlsanity.com/paper/1909.06012/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Sep 2019.

## Built on by (most cited first, 15 of 15)

- [ImageCAS: A Large-Scale Dataset and Benchmark for Coronary Artery Segmentation based on Computed Tomography Angiography Images](https://mlsanity.com/paper/2211.01607/) (2022)
- [Efficient Medical Image Segmentation Based on Knowledge Distillation](https://mlsanity.com/paper/2108.09987/) (2021)
- [You Only Learn Once: Universal Anatomical Landmark Detection](https://mlsanity.com/paper/2103.04657/) (2021)
- [Universal Undersampled MRI Reconstruction](https://mlsanity.com/paper/2103.05214/) (2021)
- [Semi-Supervised Segmentation of Radiation-Induced Pulmonary Fibrosis from Lung CT Scans with Multi-Scale Guided Dense Attention](https://mlsanity.com/paper/2109.14172/) (2021)
- [Incremental Learning for Multi-organ Segmentation with Partially Labeled Datasets](https://mlsanity.com/paper/2103.04526/) (2021)
- [Automated liver tissues delineation techniques: A systematic survey on machine learning current trends and future orientations](https://mlsanity.com/paper/2103.06384/) (2021)
- [Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond](https://mlsanity.com/paper/2203.05709/) (2022)
- [SGDA: Towards 3D Universal Pulmonary Nodule Detection via Slice Grouped Domain Attention](https://mlsanity.com/paper/2303.03625/) (2023)
- [Supervised Segmentation with Domain Adaptation for Small Sampled Orbital CT Images](https://mlsanity.com/paper/2107.00418/) (2021)
- [Multi-Domain Learning From Insufficient Annotations](https://mlsanity.com/paper/2305.02757/) (2023)
- [Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms](https://mlsanity.com/paper/2409.19371/) (2024)
- [Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions](https://mlsanity.com/paper/2107.11517/) (2021)
- [External Attention Assisted Multi-Phase Splenic Vascular Injury Segmentation with Limited Data](https://mlsanity.com/paper/2201.00942/) (2022)
- [A deep local attention network for pre-operative lymph node metastasis prediction in pancreatic cancer via multiphase CT imaging](https://mlsanity.com/paper/2301.01448/) (2023)

## Abstract (arXiv)

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-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-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% 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-Net into public domain. urlhttps://github.com/huangmozhilv/u2nettorch/