Accurate diagnosis of lymphoma on whole-slide histopathology images using deep learning
Accurate diagnosis of lymphoma on whole-slide histopathology images using deep learning
复制标题
基于深度学习的全切片组织病理学图像上淋巴瘤的准确诊断
DOI：
10.1038/s41746-020-0272-0
复制
发表时间：
2020-05-01
影响因子：
15.2
通讯作者：
Brousset, Pierre
中科院分区：
文献类型：
--
作者：
Syrykh, Charlotte;Abreu, Arnaud;Brousset, Pierre
淋巴瘤的组织病理学诊断是一项挑战，需要专业知识或集中审查，并在很大程度上取决于组织切片的技术过程。因此，我们开发了一个创新的深度学习框架，赋予了确定性估计水平，专为血红素和伊红染色玻片分析而设计，特别关注滤泡性淋巴瘤（FL）的诊断。淋巴结受滤泡增生或滤泡增生影响的整片图像用于训练、验证和最终测试贝叶斯神经网络（BNN）。这些BNN提供了诊断预测和有效的确定性估计，并产生了准确的诊断，曲线下面积达到0.99。通过其不确定性估计，我们的网络还能够检测到不熟悉的数据，如其他小B细胞淋巴瘤或来自外部中心的技术异质性病例。我们证明机器学习技术对组织病理学切片的预处理很敏感，需要适当的培训来构建通用工具来帮助诊断。
Histopathological diagnosis of lymphomas represents a challenge requiring either expertise or centralised review, and greatly depends on the technical process of tissue sections. Hence, we developed an innovative deep-learning framework, empowered with a certainty estimation level, designed for haematoxylin and eosin-stained slides analysis, with special focus on follicular lymphoma (FL) diagnosis. Whole-slide images of lymph nodes affected by FL or follicular hyperplasia were used for training, validating, and finally testing Bayesian neural networks (BNN). These BNN provide a diagnostic prediction coupled with an effective certainty estimation, and generate accurate diagnosis with an area under the curve reaching 0.99. Through its uncertainty estimation, our network is also able to detect unfamiliar data such as other small B cell lymphomas or technically heterogeneous cases from external centres. We demonstrate that machine-learning techniques are sensitive to the pre-processing of histopathology slides and require appropriate training to build universal tools to aid diagnosis.