用草图标注提升医学图像分割精度，兼顾边界细节与模型效率。
QMaxViT-Unet+: A Query-Based MaxViT-Unet with Edge Enhancement for Scribble-Supervised Segmentation of Medical Images
- 基于查询的Transformer解码器+边缘增强模块，弥补草图标签信息不足。
- 在4个公开数据集上平均达89.1%的Dice系数，边界误差低至1.316mm。
- 适合标注成本高的医疗场景，性能接近全监督方法。
深度学习模型在医学图像分割中的应用常受限于大量标注数据的需求。弱监督学习通过允许不精确标签成为解决此问题的可行方案。本文提出QMaxViT-Unet+，一种面向草图监督的医学图像分割新框架。该框架基于U-Net结构，将编码器和解码器替换为多轴视觉变换器（MaxViT）块，以高效学习局部与全局特征。同时引入基于查询的Transformer解码器以优化特征表示，并设计边缘增强模块来弥补草图标签中边界信息的缺失。在针对心脏结构、结直肠息肉和乳腺癌的四个公开数据集（ACDC、MS-CMRSeg、SUN-SEG、BUSI）上进行评估，采用Dice相似系数（DSC）与95百分位豪斯多夫距离（HD95）作为指标。实验结果表明，该方法在ACDC上取得89.1% DSC与1.316mm HD95，MS-CMRSeg上为88.4% DSC与2.226mm HD95，SUN-SEG上为71.4% DSC与4.996mm HD95，BUSI上为69.4% DSC与50.122mm HD95。结果表明，本方法在准确性、鲁棒性与效率方面均优于现有技术，且与全监督方法相当，适用于高质量标注稀缺的医疗图像分析场景。代码已开源：https://github.com/anpc849/QMaxViT-Unet
原文摘要 · Abstract (English)
The deployment of advanced deep learning models for medical image segmentation is often constrained by the requirement for extensively annotated datasets. Weakly-supervised learning, which allows less precise labels, has become a promising solution to this challenge. Building on this approach, we propose QMaxViT-Unet+, a novel framework for scribble-supervised medical image segmentation. This framework is built on the U-Net architecture, with the encoder and decoder replaced by Multi-Axis Vision Transformer (MaxViT) blocks. These blocks enhance the model's ability to learn local and global features efficiently. Additionally, our approach integrates a query-based Transformer decoder to refine features and an edge enhancement module to compensate for the limited boundary information in the scribble label. We evaluate the proposed QMaxViT-Unet+ on four public datasets focused on cardiac structures, colorectal polyps, and breast cancer: ACDC, MS-CMRSeg, SUN-SEG, and BUSI. Evaluation metrics include the Dice similarity coefficient (DSC) and the 95th percentile of Hausdorff distance (HD95). Experimental results show that QMaxViT-Unet+ achieves 89.1\% DSC and 1.316mm HD95 on ACDC, 88.4\% DSC and 2.226mm HD95 on MS-CMRSeg, 71.4\% DSC and 4.996mm HD95 on SUN-SEG, and 69.4\% DSC and 50.122mm HD95 on BUSI. These results demonstrate that our method outperforms existing approaches in terms of accuracy, robustness, and efficiency while remaining competitive with fully-supervised learning approaches. This makes it ideal for medical image analysis, where high-quality annotations are often scarce and require significant effort and expense. The code is available at: https://github.com/anpc849/QMaxViT-Unet
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。