Department of Electrical Engineering, National Chung Hsing University, Taichung 40227, Taiwan, ROC.
Section of Nephrology, Department of Medicine, Taichung Veterans General Hospital, Taichung 40705, Taiwan, ROC; Graduate Institute of Biomedical Sciences, College of Medicine, China Medical University, Taichung 406040, Taiwan, ROC; School of Medicine, College of Medicine, China Medical University, Taichung 406040, Taiwan, ROC; Department of Post-Baccalaureate Medicine, College of Medicine, National Chung Hsing University, Taichung 40227, Taiwan, ROC.
Comput Med Imaging Graph. 2024 Jul;115:102375. doi: 10.1016/j.compmedimag.2024.102375. Epub 2024 Mar 29.
Glomerulus morphology on renal pathology images provides valuable diagnosis and outcome prediction information. To provide better care, an efficient, standardized, and scalable method is urgently needed to optimize the time-consuming and labor-intensive interpretation process by renal pathologists. This paper proposes a deep convolutional neural network (CNN)-based approach to automatically detect and classify glomeruli with different stains in renal pathology images. In the glomerulus detection stage, this paper proposes a flattened Xception with a feature pyramid network (FX-FPN). The FX-FPN is employed as a backbone in the framework of faster region-based CNN to improve glomerulus detection performance. In the classification stage, this paper considers classifications of five glomerulus morphologies using a flattened Xception classifier. To endow the classifier with higher discriminability, this paper proposes a generative data augmentation approach for patch-based glomerulus morphology augmentation. New glomerulus patches of different morphologies are generated for data augmentation through the cycle-consistent generative adversarial network (CycleGAN). The single detection model shows the F score up to 0.9524 in H&E and PAS stains. The classification result shows that the average sensitivity and specificity are 0.7077 and 0.9316, respectively, by using the flattened Xception with the original training data. The sensitivity and specificity increase to 0.7623 and 0.9443, respectively, by using the generative data augmentation. Comparisons with different deep CNN models show the effectiveness and superiority of the proposed approach.
肾小球形态在肾脏病理图像中提供了有价值的诊断和预后预测信息。为了提供更好的护理，迫切需要一种高效、标准化和可扩展的方法，通过肾脏病理学家来优化耗时且劳动密集型的解释过程。本文提出了一种基于深度卷积神经网络（CNN）的方法，用于自动检测和分类肾脏病理图像中具有不同染色的肾小球。在肾小球检测阶段，本文提出了一种带有特征金字塔网络（Feature Pyramid Network，FPN）的扁平 Xception（Flattened Xception with FPN，FX-FPN）。将 FX-FPN 作为更快区域卷积神经网络（Faster Region-based Convolutional Neural Network，Faster R-CNN）框架中的骨干网络，以提高肾小球检测性能。在分类阶段，本文考虑了五种肾小球形态的分类，使用了扁平 Xception 分类器。为了赋予分类器更高的辨别能力，本文提出了一种基于补丁的肾小球形态增强的生成式数据扩充方法。通过循环一致性生成对抗网络（CycleGAN），为数据扩充生成不同形态的新肾小球补丁。单检测模型在 H&E 和 PAS 染色中 F 分数高达 0.9524。分类结果表明，使用原始训练数据的扁平 Xception 分类器的平均灵敏度和特异性分别为 0.7077 和 0.9316。通过使用生成式数据扩充，灵敏度和特异性分别提高到 0.7623 和 0.9443。与不同的深度 CNN 模型的比较表明了所提出方法的有效性和优越性。
