From the Department of Neuroscience, Mayo Clinic, Jacksonville, Florida, USA.
J Neuropathol Exp Neurol. 2021 Mar 22;80(4):306-312. doi: 10.1093/jnen/nlab005.
This study aimed to develop a deep learning-based image classification model that can differentiate tufted astrocytes (TA), astrocytic plaques (AP), and neuritic plaques (NP) based on images of tissue sections stained with phospho-tau immunohistochemistry. Phospho-tau-immunostained slides from the motor cortex were scanned at 20× magnification. An automated deep learning platform, Google AutoML, was used to create a model for distinguishing TA in progressive supranuclear palsy (PSP) from AP in corticobasal degeneration (CBD) and NP in Alzheimer disease (AD). A total of 1500 images of representative tau lesions were captured from 35 PSP, 27 CBD, and 33 AD patients. Of those, 1332 images were used for training, and 168 images for cross-validation. We tested the model using 100 additional test images taken from 20 patients of each disease. In cross-validation, precision and recall for each individual lesion type were 100% and 98.0% for TA, 98.5% and 98.5% for AP, and 98.0% and 100% for NP, respectively. In a test set, all images of TA and NP were correctly predicted. Only eleven images of AP were predicted to be TA or NP. Our data indicate the potential usefulness of deep learning-based image classification methods to assist in differential diagnosis of tauopathies.
本研究旨在开发一种基于深度学习的图像分类模型，该模型可以根据磷酸化 tau 免疫组织化学染色的组织切片图像来区分丛状星形胶质细胞（TA）、星形胶质斑块（AP）和神经原纤维缠结（NP）。使用 20×放大倍数扫描磷酸化 tau 免疫染色的运动皮层载玻片。使用自动化深度学习平台 Google AutoML 为区分进行性核上性麻痹（PSP）中的 TA、皮质基底节变性（CBD）中的 AP 和阿尔茨海默病（AD）中的 NP 创建了一个模型。从 35 名 PSP、27 名 CBD 和 33 名 AD 患者中捕获了 1500 张具有代表性的 tau 病变图像。其中，1332 张图像用于训练，168 张图像用于交叉验证。我们使用来自每个疾病的 20 名患者的 100 张额外测试图像来测试模型。在交叉验证中，每个病变类型的精度和召回率分别为 100%和 98.0%的 TA、98.5%和 98.5%的 AP，以及 98.0%和 100%的 NP。在测试集中，所有 TA 和 NP 的图像均被正确预测。只有 11 张 AP 图像被预测为 TA 或 NP。我们的数据表明，基于深度学习的图像分类方法具有辅助 tau 病鉴别诊断的潜力。
