Zheng Zhaohui, Zhang Xiangsen, Ding Jin, Zhang Dingwen, Cui Jihong, Fu Xianghui, Han Junwei, Zhu Ping
Department of Clinical Immunology, Xijing Hospital, Fourth Military Medical University, Xi'an 710032, China.
School of Automation, Northwestern Polytechnical University, Xi'an 710072, China.
Diagnostics (Basel). 2021 Oct 26;11(11):1983. doi: 10.3390/diagnostics11111983.
Accurate assessment of renal histopathology is crucial for the clinical management of patients with lupus nephritis (LN). However, the current classification system has poor interpathologist agreement. This paper proposes a deep convolutional neural network (CNN)-based system that detects and classifies glomerular pathological findings in LN. A dataset of 349 renal biopsy whole-slide images (WSIs) (163 patients with LN, periodic acid-Schiff stain, 3906 glomeruli) annotated by three expert nephropathologists was used. The CNN models YOLOv4 and VGG16 were employed to localise the glomeruli and classify glomerular lesions (slight/severe impairments or sclerotic lesions). An additional 321 unannotated WSIs from 161 patients were used for performance evaluation at the per-patient kidney level. The proposed model achieved an accuracy of 0.951 and Cohen's kappa of 0.932 (95% CI 0.915-0.949) for the entire test set for classifying the glomerular lesions. For multiclass detection at the glomerular level, the mean average precision of the CNN was 0.807, with 'slight' and 'severe' glomerular lesions being easily identified (F1: 0.924 and 0.952, respectively). At the per-patient kidney level, the model achieved a high agreement with nephropathologist (linear weighted kappa: 0.855, 95% CI: 0.795-0.916, < 0.001; quadratic weighted kappa: 0.906, 95% CI: 0.873-0.938, < 0.001). The results suggest that deep learning is a feasible assistive tool for the objective and automatic assessment of pathological LN lesions.
准确评估肾脏组织病理学对于狼疮性肾炎（LN）患者的临床管理至关重要。然而，当前的分类系统在病理学家之间的一致性较差。本文提出了一种基于深度卷积神经网络（CNN）的系统，用于检测和分类LN中的肾小球病理表现。使用了一个由三位专家肾病病理学家注释的349例肾活检全切片图像（WSIs）数据集（163例LN患者，过碘酸-希夫染色，3906个肾小球）。采用CNN模型YOLOv4和VGG16对肾小球进行定位并对肾小球病变（轻度/重度损伤或硬化性病变）进行分类。另外，来自161例患者的321张未注释的WSIs用于在患者肾脏水平上进行性能评估。所提出的模型在对肾小球病变进行分类的整个测试集中，准确率达到0.951，科恩kappa系数为0.932（95%CI 0.915 - 0.949）。对于肾小球水平的多类检测，CNN的平均平均精度为0.807，“轻度”和“重度”肾小球病变易于识别（F1分别为0.924和0.952）。在患者肾脏水平上，该模型与肾病病理学家达成了高度一致（线性加权kappa：0.855，95%CI：0.795 - 0.916，<0.001；二次加权kappa：0.906，95%CI：0.873 - 0.938，<0.001）。结果表明，深度学习是客观自动评估LN病理病变的一种可行辅助工具。
