[论文解读] Medical Image Segmentation Review: The success of U-Net

Reza Azad, Ehsan Khodapanah Aghdam+8 more|arXiv (Cornell University)|Nov 27, 2022

Brain Tumor Detection and Classification被引用 96

一句话总结

本文综述了医学图像分割中的 U-Net 及其变体，提出六类分类法，并提供实用资源，包括代码、预训练模型和在线论文清单。

ABSTRACT

Automatic medical image segmentation is a crucial topic in the medical domain and successively a critical counterpart in the computer-aided diagnosis paradigm. U-Net is the most widespread image segmentation architecture due to its flexibility, optimized modular design, and success in all medical image modalities. Over the years, the U-Net model achieved tremendous attention from academic and industrial researchers. Several extensions of this network have been proposed to address the scale and complexity created by medical tasks. Addressing the deficiency of the naive U-Net model is the foremost step for vendors to utilize the proper U-Net variant model for their business. Having a compendium of different variants in one place makes it easier for builders to identify the relevant research. Also, for ML researchers it will help them understand the challenges of the biological tasks that challenge the model. To address this, we discuss the practical aspects of the U-Net model and suggest a taxonomy to categorize each network variant. Moreover, to measure the performance of these strategies in a clinical application, we propose fair evaluations of some unique and famous designs on well-known datasets. We provide a comprehensive implementation library with trained models for future research. In addition, for ease of future studies, we created an online list of U-Net papers with their possible official implementation. All information is gathered in https://github.com/NITR098/Awesome-U-Net repository.

研究动机与目标

• 提供对基于 U-Net 的医学图像分割方法及其模态的全面概述。
• 提出一个分类法，用于根据架构设计变更对 U-Net 变体进行归类。
• 提供实用指导，包括数据集、损失函数、评估指标和对比评估。
• 提供一个实现库，包含训练模型和一个在线 U-Net 论文与实现清单。

提出的方法

• 为 U-Net 变体引入六类别分类法：Skip Connection Enhancements、Backbone Design Enhancements、Bottleneck Enhancements、Transformers、Rich Representation Enhancements、以及 Probabilistic Design。
• 详细说明 2D 与 3D U-Net 架构及其在医学影像模态中的适用性。
• 综述并讨论众多扩展，聚焦跳跃连接、特征图处理和注意力机制。
• 提供在流行数据集上的对比实验，以评估设计选择。
• 提供实用资源，包括带实现和预训练权重的 GitHub 仓库，以及一个在线的 U-Net 论文清单。
• 将讨论组织起来，帮助厂商和研究人员选择合适的 U-Net 变体。

Figure 1 : The number of research works published in the past decade using the U-Net model as their baseline to address various medical image analysis challenges. The visualization shows sumptuous attention from the research/industry community for this architecture, particularly the segmentation tas

实验结果

研究问题

• RQ1 哪些对 U-Net 的设计修改在跨模态的医学图像分割中最有效地提升性能？
• RQ2 跳跃连接、骨干网络、瓶颈、变换器和概率设计如何影响性能和实用性？
• RQ3 哪些数据集和评估实践最能反映在现实世界临床中的实用性？
• RQ4 哪些资源（代码、权重、论文）最能支持研究人员在实践中部署 U-Net 模型？

主要发现

• 论文将 U-Net 变体归纳为六种实用类别，阐明每种修改如何针对分割挑战。
• 回顾了截至 2022 年 9 月超过 100 种基于 U-Net 的分割方法的文献。
• 研究包括在知名数据集上的对比实验，以说明设计在性能趋势上的影响。
• 它提供了一个包含训练模型的全面实现库以及一个带有可用实现的 U-Net 论文在线清单。
• 该工作强调在评估 U-Net 扩展时的临床相关性、数据模态、损失函数和评估指标。

Figure 2 : The proposed U-Net taxonomy categorizes different extensions of the U-Net model based on their underlying design idea. More specifically, our taxonomy takes into account the modular design of the U-Net model and shows where the improvement happens (e.g., skip connection). Due to the clari