Syrykh Charlotte, Abreu Arnaud, Amara Nadia, Siegfried Aurore, Maisongrosse Véronique, Frenois François X, Martin Laurent, Rossi Cédric, Laurent Camille, Brousset Pierre
1Department of Pathology, University Cancer Institute of Toulouse-Oncopole, Toulouse, France.
Roche Institute, Boulogne-Billancourt, France.
NPJ Digit Med. 2020 May 1;3:63. doi: 10.1038/s41746-020-0272-0. eCollection 2020.
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.
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,并且在很大程度上取决于组织切片的技术过程。因此,我们开发了一种创新的深度学习框架,该框架具有确定性估计水平,专为苏木精和伊红染色切片分析而设计,特别侧重于滤泡性淋巴瘤(FL)的诊断。受FL或滤泡增生影响的淋巴结全切片图像用于训练、验证,最终测试贝叶斯神经网络(BNN)。这些BNN提供诊断预测并结合有效的确定性估计,并生成准确的诊断,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来自外部中心的不熟悉数据,如其他小B细胞淋巴瘤或技术上异质的病例。我们证明机器学习技术对组织病理学切片的预处理敏感,并且需要适当的训练来构建辅助诊断的通用工具。