使用动量对比框架在组织病理学图像中检测口腔鳞状细胞癌的方案。

Protocol for detecting oral squamous cell carcinoma in histopathology images using the momentum contrast framework.

作者信息

Zhang Xiaoyun, Fang Yue, Liao Weibin, Ma Junyi, Gao Xin, Gao Min, Zhao Junfeng

机构信息

School and Hospital of Stomatology, Peking University, Beijing 100081, China.

Key Laboratory of High Confidence Software Technologies, Ministry of Education, Peking University, Beijing 100871, China.

出版信息

STAR Protoc. 2025 Jul 30;6(3):103937. doi: 10.1016/j.xpro.2025.103937.

DOI:10.1016/j.xpro.2025.103937

PMID:40748764

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC12336802/

Abstract

The detection of oral squamous cell carcinoma (OSCC) in histopathology images is crucial for improving diagnostic accuracy and patient outcomes. Here, we present a protocol for detecting OSCC in histopathology images using transfer learning. We describe steps for installing software and prerequisites, preparing datasets, and pretraining a model on images from various tissue types using the momentum contrast (MoCo) framework. We then detail procedures for evaluating the fine-tuned HistoMOCO model's performance on a test dataset.

摘要

在组织病理学图像中检测口腔鳞状细胞癌（OSCC）对于提高诊断准确性和患者治疗效果至关重要。在此，我们提出了一种使用迁移学习在组织病理学图像中检测OSCC的方案。我们描述了安装软件和先决条件、准备数据集以及使用动量对比（MoCo）框架在来自各种组织类型的图像上预训练模型的步骤。然后，我们详细介绍了在测试数据集上评估微调后的HistoMOCO模型性能的程序。