arXiv 1909.060122019-09-04eess.IVcs.CV

3D U $^2$ -Net：一种用于多领域医学图像分割的3D通用U-Net

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

Zhejiang University（浙江大学）；Peng Cheng Laboratory（鹏城实验室）

Chao Huang, Hu Han, Qingsong Yao, Shankuan Zhu, S. Kevin Zhou

摘要：

像U-Net这样的全卷积神经网络已经成为医学图像分割中最先进的方法。实际上，网络是高度专业化的，并为每个分割任务单独训练。代替多个模型的集合，非常希望学习用于不同任务的通用数据表示，理想情况下是添加针对每个任务的最小数量的参数的单个模型。受最近多域学习在图像分类中的成功的启发，我们首次探索了一种有前途的通用架构，该架构可以处理多个医学分割任务，并且可以扩展为新任务，无论不同的器官和成像方式如何。我们的3D通用U-网络（3D U $^2$ -Net）是建立在可分离卷积的基础上的，假设{来自不同域的\it图像具有域特定的空间相关性，可以用逐通道卷积进行探测，同时也共享可以用逐点卷积建模的跨通道相关性}。我们在五个器官分割数据集上评估了3D U $^2$ -Net。实验结果表明，这种通用的网络是能够竞争与传统的模型在分割精度方面，而只需要约$1\%$的参数。此外，我们观察到，该架构可以很容易地和有效地适应一个新的域，而不会牺牲性能的域用于学习的通用网络的共享参数化。我们将3D U $^2$ -Net的代码放到公共领域。\url{https://github.com/huangmozhilv/u2net_torch/}

英文摘要：

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 U$^2$-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 U$^2$-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 $1\%$ 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 U$^2$-Net into public domain. \url{https://github.com/huangmozhilv/u2net_torch/}

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

摘要：

英文摘要：

相关论文