用视觉变压器精准分割肠道肌层，助力先天性巨结肠诊断
Segmentation of Muscularis Propria in Colon Histopathology Images Using Vision Transformers for Hirschsprung's Disease
- 采用视觉变压器捕捉图像全局依赖关系进行肌层分割
- 分割精度达DICE 89.9%，肌层神经丛包含率100%
- 适合病理医生辅助诊断及医学图像分析研究者参考
先天性巨结肠（HD）通过检测结肠肌层中神经节细胞缺失来确诊，尤其在肌间神经丛区域。对组织病理图像进行定量分析，如统计神经节数量及空间分布，虽具价值，但耗时、成本高且存在评价者间与内部差异。此前研究已证明深度学习可自动化组织病理图像分析，包括使用卷积神经网络（CNNs）分割肌层。最近，视觉变压器（ViTs）凭借自注意力机制展现出强大潜力。本研究探索了ViT在钙结合蛋白染色的结肠组织病理图像中对肌层的分割性能，并与CNN和浅层学习方法对比。ViT模型取得89.9%的DICE分数和100%的肌层神经丛包含率（PIR），优于CNN（DICE 89.2%，PIR 96.0%）及k均值聚类方法（DICE 80.7%，PIR 77.4%）。结果表明，ViT是推动HD相关图像分析的有力工具。
原文摘要 · Abstract (English)
Hirschsprung's disease (HD) is a congenital birth defect diagnosed by identifying the lack of ganglion cells within the colon's muscularis propria, specifically within the myenteric plexus regions. There may be advantages for quantitative assessments of histopathology images of the colon, such as counting the ganglion and assessing their spatial distribution; however, this would be time-intensive for pathologists, costly, and subject to inter- and intra-rater variability. Previous research has demonstrated the potential for deep learning approaches to automate histopathology image analysis, including segmentation of the muscularis propria using convolutional neural networks (CNNs). Recently, Vision Transformers (ViTs) have emerged as a powerful deep learning approach due to their self-attention. This study explores the application of ViTs for muscularis propria segmentation in calretinin-stained histopathology images and compares their performance to CNNs and shallow learning methods. The ViT model achieved a DICE score of 89.9% and Plexus Inclusion Rate (PIR) of 100%, surpassing the CNN (DICE score of 89.2%; PIR of 96.0%) and k-means clustering method (DICE score of 80.7%; PIR 77.4%). Results assert that ViTs are a promising tool for advancing HD-related image analysis.
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。