Scholarlink

<p>Accurately distinguishing between primary and gastrointestinal metastatic mucinous ovarian carcinoma (MOC) is crucial but remains highly challenging. We developed and validated the MOC Origin Prediction Model (MOCOPM), the deep learning model specifically designed to predict the origin of MOC from histopathology images. Cases of primary or gastrointestinal metastatic MOC were collected from three hospitals and divided into internal and external cohorts. Three neural networks were trained using the area under the receiver operating characteristic curve (AUROC) as the primary performance metric. After five-fold cross-validation on the internal cohort, the best-performing model was selected to construct MOCOPM, which was then externally validated. In total, 167 MOC patients were included. MOCOPM achieved an average AUROC of 0.91 internally and 0.96 externally. This model offers a promising tool to support clinical decision-making in MOC diagnosis.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Distinction between primary and metastatic mucinous ovarian carcinoma from histopathology images using deep learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月24日

查看全文
  • Ming-Yi Zhang,
  • Bin Liu,
  • Zhao-Juan Qin,
  • Yue-Di Zhang,
  • Zhi-Qian Li,
  • Rui-Zhi Liu,
  • Zhi-Xiang Xia,
  • Qiong-Xian Long,
  • Jia Xu,
  • Xiao-Li Mou,
  • Lian-Sha Tang,
  • Hong-Shuai Li,
  • Wen-Jun Meng,
  • Ai Zheng,
  • Yang-Mei Shen,
  • Ji-Yan Liu

摘要

Accurately distinguishing between primary and gastrointestinal metastatic mucinous ovarian carcinoma (MOC) is crucial but remains highly challenging. We developed and validated the MOC Origin Prediction Model (MOCOPM), the deep learning model specifically designed to predict the origin of MOC from histopathology images. Cases of primary or gastrointestinal metastatic MOC were collected from three hospitals and divided into internal and external cohorts. Three neural networks were trained using the area under the receiver operating characteristic curve (AUROC) as the primary performance metric. After five-fold cross-validation on the internal cohort, the best-performing model was selected to construct MOCOPM, which was then externally validated. In total, 167 MOC patients were included. MOCOPM achieved an average AUROC of 0.91 internally and 0.96 externally. This model offers a promising tool to support clinical decision-making in MOC diagnosis.