Pathologist-level classification of histopathological melanoma images with deep neural networks
Pathologist-level classification of histopathological melanoma images with deep neural networks
复制标题
DOI：
10.1016/j.ejca.2019.04.021
复制
发表时间：
2019-07-01
影响因子：
8.4
通讯作者：
Brinker, Titus Josef
中科院分区：
文献类型：
--
作者：
Hekler, Achim;Utikal, Jochen Sven;Brinker, Titus Josef
背景：大多数癌症的诊断是由委员会认证的病理学家根据显微镜下的组织活检做出的。最近的研究揭示了个体病理学家之间的高度不一致。对于黑色素瘤，文献报道良性痣与恶性黑色素瘤的分类存在 25-26% 的不一致。深度学习成功实施，提高了肺癌和乳腺癌诊断的准确性。本研究的目的是说明深度学习协助人类评估组织病理学黑色素瘤诊断的潜力。方法：组织病理学家专家根据现行指南对 695 个病变进行分类（350 个痣和 345 个黑色素瘤）。使用载玻片扫描仪仅对这些病变的苏木精和伊红染色 (H&E) 载玻片进行数字化，然后随机裁剪。所得图像中的 595 张用于训练卷积神经网络 (CNN)。额外的 100 个 H&E 图像切片用于测试 CNN 的结果，并与原始类别标签进行比较。结果：黑色素瘤与组织病理学家的总不一致率为 18%（95% 置信区间 [CI]：7.4-28.6%），痣为 20%（95% CI：8.9-31.1%），整组图像为 19%（95% CI： 11.3-26.7%）。解读：即使在最坏的情况下，CNN 的不一致与文献报道的人类病理学家之间的不一致也大致相同。尽管与病理学家相比，数据量、诊断所需时间和成本大大减少，但我们的 CNN 仍表现出同等性能。总之，CNN 是辅助人类黑色素瘤诊断的宝贵工具。 (C) 2019 作者。由爱思唯尔有限公司出版
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. (C) 2019 The Author(s). Published by Elsevier Ltd.