文献速递骨软组织肉瘤与黑色素瘤

深度神经网络对组织病理学黑色素瘤图像进行病理学家级分类

Pathologist-level classification of histopathological melanoma images with deep neural networks.
PubMed 文献 · Eur J Cancer · 2019-05-23

研究将695个黑色素瘤或痣的H&E染色切片图像随机裁剪,595张用于训练卷积神经网络(CNN),100张用于测试,并与专家病理学家的分类标签比较。CNN与病理学家的总体不一致率为19%(95%CI 11.3-26.7%),黑色素瘤为18%(95%CI 7.4-28.6%),痣为20%(95%CI 8.9-31.1%)。作者认为CNN是辅助人类黑色素瘤诊断的有价值工具。

要点

  • CNN与病理学家分类黑色素瘤的不一致率为18%(95%CI 7.4-28.6%)。
  • CNN与病理学家分类痣的不一致率为20%(95%CI 8.9-31.1%)。
  • CNN在数据量、诊断时间和成本远低于病理学家的情况下达到相当性能。

核心结论

  • CNN与病理学家分类黑色素瘤的不一致率约为文献报道的病理学家间不一致率。
  • CNN在数据量、诊断时间和成本远低于病理学家的情况下达到相当性能。
  • 作者认为CNN是辅助人类黑色素瘤诊断的有价值工具。

研究设计与样本

  • 研究纳入695个病变,由专家病理学家根据现行指南分类为350个痣和345个黑色素瘤。
  • 仅对H&E染色切片进行数字化扫描并随机裁剪图像。
  • 595张图像用于训练卷积神经网络(CNN),100张H&E图像切片用于测试CNN结果并与原始分类标签比较。

主要发现

  • CNN与病理学家分类黑色素瘤的不一致率为18%(95%CI 7.4-28.6%)。
  • CNN与病理学家分类痣的不一致率为20%(95%CI 8.9-31.1%)。
  • CNN与病理学家分类全部图像的不一致率为19%(95%CI 11.3-26.7%)。

临床怎么用

  • 作者认为CNN是辅助人类黑色素瘤诊断的有价值工具。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

BACKGROUND: The diagnosis of most cancers is made by a board-certified pathologist based on a tissue biopsy under the microscope. Recent research reveals a high discordance between individual pathologists. For melanoma, the literature reports 25-26% of discordance for classifying a benign nevus versus malignant melanoma. Deep learning was successfully implemented to enhance the precision of lung and breast cancer diagnoses. The aim of this study is to illustrate the potential of deep learning to assist human assessment for a histopathologic melanoma diagnosis. METHODS: Six hundred ninety-five lesions were classified by an expert histopathologist in accordance with current guidelines (350 nevi and 345 melanomas). Only the haematoxylin and eosin stained (H&E) slides of these lesions were digitalised using a slide scanner and then randomly cropped. Five hundred ninety-five of the resulting images were used for the training of a convolutional neural network (CNN). The additional 100 H&E image sections were used to test the results of the CNN in comparison with the original class labels. FINDINGS: The total discordance with the histopathologist was 18% for melanoma (95% confidence interval [CI]: 7.4-28.6%), 20% for nevi (95% CI: 8.9-31.1%) and 19% for the full set of images (95% CI: 11.3-26.7%). INTERPRETATION: Even in the worst case, the discordance of the CNN was about the same compared with the discordance between human pathologists as reported in the literature. Despite the vastly reduced amount of data, time necessary for diagnosis and cost compared with the pathologist, our CNN archived on-par performance. Conclusively, CNNs indicate to be a valuable tool to assist human melanoma diagnoses.

来源:Eur J Cancer,查看原文。版权归原作者所有。

引用

  1. Hekler A, Utikal JS, Enk AH, et al. Pathologist-level classification of histopathological melanoma images with deep neural networks. Eur J Cancer. 2019. PMID: 31129383. doi:10.1016/j.ejca.2019.04.021

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。