深度学习神经网络关联病理纤维化与肾脏生存
该研究利用深度学习架构分析171例肾活检三色染色图像,训练卷积神经网络(CNN)模型预测CKD分期、血清肌酐、肾病范围蛋白尿及1、3、5年肾脏生存,并与病理医生估计纤维化评分(PEFS)比较。结果显示CNN模型在各项分类任务中均优于PEFS模型,证明深度学习可应用于常规肾活检图像。
要点
- CNN模型预测CKD分期的κ值为0.519,优于PEFS模型的0.051。
- CNN模型预测肌酐和蛋白尿的AUC分别为0.912和0.867,均高于PEFS模型。
- CNN模型预测1、3、5年肾脏生存的AUC分别为0.878、0.875、0.904,均优于PEFS模型。
核心结论
- 深度学习可应用于常规肾活检图像,CNN模型在预测CKD分期、肌酐、蛋白尿及肾脏生存方面优于病理医生估计纤维化评分。
研究设计与样本
- 研究收集2009至2012年波士顿医疗中心171例患者的肾活检三色染色图像,训练六个CNN模型分别预测CKD分期、血清肌酐、肾病范围蛋白尿及1、3、5年肾脏生存,并与PEFS模型比较。
主要发现
- CNN模型预测CKD分期的κ值为0.519,PEFS模型为0.051。
- CNN模型预测肌酐的AUC为0.912,PEFS模型为0.840;预测蛋白尿的AUC为0.867,PEFS模型为0.702。
- CNN模型预测1、3、5年肾脏生存的AUC分别为0.878、0.875、0.904,PEFS模型分别为0.811、0.800、0.786。
临床怎么用
- 深度学习模型可辅助肾活检图像分析,更准确关联病理纤维化与临床结局,但需进一步验证后用于临床决策。
局限性
- 研究为原理验证性研究,样本量有限(171例),需外部验证。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
INTRODUCTION: Chronic kidney damage is routinely assessed semiquantitatively by scoring the amount of fibrosis and tubular atrophy in a renal biopsy sample. Although image digitization and morphometric techniques can better quantify the extent of histologic damage, we need more widely applicable ways to stratify kidney disease severity. METHODS: We leveraged a deep learning architecture to better associate patient-specific histologic images with clinical phenotypes (training classes) including chronic kidney disease (CKD) stage, serum creatinine, and nephrotic-range proteinuria at the time of biopsy, and 1-, 3-, and 5-year renal survival. Trichrome-stained images processed from renal biopsy samples were collected on 171 patients treated at the Boston Medical Center from 2009 to 2012. Six convolutional neural network (CNN) models were trained using these images as inputs and the training classes as outputs, respectively. For comparison, we also trained separate classifiers using the pathologist-estimated fibrosis score (PEFS) as input and the training classes as outputs, respectively. RESULTS: CNN models outperformed PEFS across the classification tasks. Specifically, the CNN model predicted the CKD stage more accurately than the PEFS model (κ = 0.519 vs. 0.051). For creatinine models, the area under curve (AUC) was 0.912 (CNN) versus 0.840 (PEFS). For proteinuria models, AUC was 0.867 (CNN) versus 0.702 (PEFS). AUC values for the CNN models for 1-, 3-, and 5-year renal survival were 0.878, 0.875, and 0.904, respectively, whereas the AUC values for PEFS model were 0.811, 0.800, and 0.786, respectively. CONCLUSION: The study demonstrates a proof of principle that deep learning can be applied to routine renal biopsy images.
引用
- Kolachalama VB, Singh P, Lin CQ, et al. Association of Pathological Fibrosis With Renal Survival Using Deep Neural Networks. Kidney Int Rep. 2018. PMID: 29725651. doi:10.1016/j.ekir.2017.11.002
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。