基于苏木精和伊红染色切片图像及分子标志物的深度学习进行胶质瘤分类的人工智能病理学家。
Artificial intelligence neuropathologist for glioma classification using deep learning on hematoxylin and eosin stained slide images and molecular markers.
机构信息
Glioma Surgery Division, Neurologic Surgery Department, Huashan Hospital, Fudan University, Shanghai, China.
Shanghai Key laboratory of Brain Function Restoration and Neural Regeneration.
出版信息
Neuro Oncol. 2021 Jan 30;23(1):44-52. doi: 10.1093/neuonc/noaa163.
BACKGROUND
Pathological diagnosis of glioma subtypes is essential for treatment planning and prognosis. Standard histological diagnosis of glioma is based on postoperative hematoxylin and eosin stained slides by neuropathologists. With advancing artificial intelligence (AI), the aim of this study was to determine whether deep learning can be applied to glioma classification.
METHODS
A neuropathological diagnostic platform is designed comprising a slide scanner and deep convolutional neural networks (CNNs) to classify 5 major histological subtypes of glioma to assist pathologists. The CNNs were trained and verified on over 79 990 histological patch images from 267 patients. A logical algorithm is used when molecular profiles are available.
RESULTS
A new model of the squeeze-and-excitation block DenseNet with weighted cross-entropy (named SD-Net_WCE) is developed for the glioma classification task, which learns the recognizable features of glioma histology CNN-based independent diagnostic testing on data from 56 patients with 17 262 histological patch images demonstrated patch level accuracy of 86.5% and patient level accuracy of 87.5%. Histopathological classifications could be further amplified to integrated neuropathological diagnosis by 2 molecular markers (isocitrate dehydrogenase and 1p/19q).
CONCLUSION
The model is capable of solving multiple classification tasks and can satisfactorily classify glioma subtypes. The system provides a novel aid for the integrated neuropathological diagnostic workflow of glioma.
背景
对胶质瘤亚型进行病理诊断对于治疗计划和预后至关重要。胶质瘤的标准组织学诊断基于神经病理学家对术后苏木精和伊红染色切片的评估。随着人工智能（AI）的不断发展，本研究旨在确定深度学习是否可应用于胶质瘤分类。
方法
设计了一个神经病理诊断平台，包括一个幻灯片扫描仪和深度卷积神经网络（CNN），以协助病理学家对 5 种主要的胶质瘤组织学亚型进行分类。该 CNN 在 267 名患者的超过 79990 张组织学斑块图像上进行了训练和验证。当有分子谱数据时，会使用逻辑算法。
结果
针对胶质瘤分类任务，开发了一种新的 squeeze-and-excitation 块 DenseNet 模型（命名为 SD-Net_WCE），该模型基于 CNN 学习胶质瘤组织学的可识别特征，在来自 56 名患者的 17262 张组织学斑块图像的独立数据上进行了基于 CNN 的诊断测试，斑块级别的准确率为 86.5%，患者级别的准确率为 87.5%。通过 2 种分子标志物（异柠檬酸脱氢酶和 1p/19q），可以进一步放大组织病理学分类以实现综合神经病理学诊断。
结论
该模型能够解决多种分类任务，并能令人满意地对胶质瘤亚型进行分类。该系统为胶质瘤的综合神经病理学诊断工作流程提供了一种新的辅助手段。
Zotero 插件