文章：

利用多种基于深度学习的算法从子宫内膜癌组织切片图像预测错配修复状态

Prediction of Mismatch Repair Status in Endometrial Cancer from Histological Slide Images Using Various Deep Learning-Based Algorithms

原文发布日期：9 May 2024

DOI: 10.3390/cancers16101810

类型: Article

开放获取: 是

英文摘要：

The application of deep learning algorithms to predict the molecular profiles of various cancers from digital images of hematoxylin and eosin (H&E)-stained slides has been reported in recent years, mainly for gastric and colon cancers. In this study, we investigated the potential use of H&E-stained endometrial cancer slide images to predict the associated mismatch repair (MMR) status. H&E-stained slide images were collected from 127 cases of the primary lesion of endometrial cancer. After digitization using a Nanozoomer virtual slide scanner (Hamamatsu Photonics), we segmented the scanned images into 5397 tiles of 512 × 512 pixels. The MMR proteins (PMS2, MSH6) were immunohistochemically stained, classified into MMR proficient/deficient, and annotated for each case and tile. We trained several neural networks, including convolutional and attention-based networks, using tiles annotated with the MMR status. Among the tested networks, ResNet50 exhibited the highest area under the receiver operating characteristic curve (AUROC) of 0.91 for predicting the MMR status. The constructed prediction algorithm may be applicable to other molecular profiles and useful for pre-screening before implementing other, more costly genetic profiling tests.

摘要翻译： 

近年来，深度学习算法在利用苏木精-伊红（H&E）染色切片数字图像预测多种癌症分子特征方面的应用已有报道，主要集中在胃癌和结肠癌领域。本研究探讨了利用H&E染色子宫内膜癌切片图像预测相关错配修复（MMR）状态的潜在应用价值。研究收集了127例子宫内膜癌原发病灶的H&E染色切片图像，通过滨松光子学Nanozoomer虚拟切片扫描仪数字化处理后，将扫描图像分割为5397个512×512像素的图像区块。通过免疫组化染色检测MMR蛋白（PMS2、MSH6），将病例分为MMR功能正常/缺陷两类，并对每个病例及图像区块进行标注。我们使用标注MMR状态的图像区块训练了包括卷积神经网络和注意力机制网络在内的多种神经网络模型。在测试的网络中，ResNet50模型在预测MMR状态方面表现出最优性能，其受试者工作特征曲线下面积（AUROC）达到0.91。该预测算法可扩展应用于其他分子特征预测，并有望在实施其他成本更高的基因谱检测前发挥预筛作用。

原文链接：

Prediction of Mismatch Repair Status in Endometrial Cancer from Histological Slide Images Using Various Deep Learning-Based Algorithms