期刊
VIRCHOWS ARCHIV
卷 479, 期 3, 页码 617-621出版社
SPRINGER
DOI: 10.1007/s00428-020-02931-4
关键词
B-cell lymphoma; MYC; H&E; DLBCL; Deep Learning
类别
资金
- Foundation for Polish Science (FNP)
- Dutch Cancer Society [KUN 2015-7970]
- Netherlands Organization for Scientific Research (NWO) [016.186.152]
- Philips Digital Pathology Solutions
A deep learning algorithm was developed to detect MYC rearrangement in scanned histological slides, showing a high sensitivity of 0.93 and specificity of 0.52. This approach could allow for simple and fast prescreening, potentially saving around 34% of genetic tests.
In patients with suspected lymphoma, the tissue biopsy provides lymphoma confirmation, classification, and prognostic factors, including genetic changes. We developed a deep learning algorithm to detect MYC rearrangement in scanned histological slides of diffuse large B-cell lymphoma. The H&E-stained slides of 287 cases from 11 hospitals were used for training and evaluation. The overall sensitivity to detect MYC rearrangement was 0.93 and the specificity 0.52, showing that prediction of MYC translocation based on morphology alone was possible in 93% of MYC-rearranged cases. This would allow a simple and fast prescreening, saving approximately 34% of genetic tests with the current algorithm.
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。
推荐
暂无数据