4.7 Review

Identification of misdiagnosis by deep neural networks on a histopathologic review of breast cancer lymph node metastases

期刊

SCIENTIFIC REPORTS
卷 12, 期 1, 页码 -

出版社

NATURE PORTFOLIO
DOI: 10.1038/s41598-022-17606-0

关键词

-

资金

  1. Chinese Academy of Medical Science Initiative for Innovative Medicine [2017-I2M-2-003]
  2. CAMS Innovation Fund for Medical Sciences (CIFMS) [2021-I2M-CT-B-060]

向作者/读者索取更多资源

This study proposes a method using relative risk classification and regression tree to identify misdiagnosed whole-slide images of breast cancer lymph node metastasis and recommend them for review by pathologists. The results show an average accuracy of 0.9851, but a significantly higher misdiagnosis rate compared to pathologists. It is also found that most misdiagnoses from DNN models belong to a low-accuracy group.
The frozen section (FS) diagnoses of pathology experts are used in China to determine whether sentinel lymph nodes of breast cancer have metastasis during operation. Direct implementation of a deep neural network (DNN) in clinical practice may be hindered by misdiagnosis of the algorithm, which affects a patient's treatment decision. In this study, we first obtained the prediction result of the commonly used patch-DNN, then we present a relative risk classification and regression tree (RRC ART) to identify the misdiagnosed whole-slide images (WSIs) and recommend them to be reviewed by pathologists. Applying this framework to 2362 WSIs of breast cancer lymph node metastasis, test on frozen section results in the mean area under the curve (AUC) reached 0.9851. However, the mean misdiagnosis rate (0.0248), was significantly higher than the pathologists' misdiagnosis rate (p < 0.01). The RRCART distinguished more than 80% of the WSIs as a high-accuracy group with an average accuracy reached to 0.995, but the difference with the pathologists' performance was not significant (p > 0.01). However, the other low-accuracy group included most of the misdiagnoses of DNN models. Our research shows that the misdiagnosis from deep learning model can be further enriched by our method, and that the low-accuracy WSIs must be selected for pathologists to review and the high-accuracy ones may be ready for pathologists to give diagnostic reports.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据