Kidney Level Lupus Nephritis Classification Using Uncertainty Guided Bayesian Convolutional Neural Networks
Kidney Level Lupus Nephritis Classification Using Uncertainty Guided Bayesian Convolutional Neural Networks
复制标题
DOI：
10.1109/jbhi.2020.3039162
复制
发表时间：
2021-02-01
影响因子：
7.7
通讯作者：
Hien Van Nguyen
中科院分区：
文献类型：
--
作者：
Cicalese, Pietro Antonio;Mobiny, Aryan;Hien Van Nguyen
基于肾活检的狼疮性肾炎（LN）诊断的特点是观察者间一致性低，误诊与患者发病率和死亡率增加有关。虽然各种计算机辅助诊断（CAD）系统已开发用于其他肾组织病理学应用，几乎没有做过准确分类肾脏的基础上，他们的肾脏水平狼疮性肾小球肾炎（LGN）评分。CAD系统的成功实施也受到了诊断医生的感知分类器的优势和劣势的阻碍，这已被证明对患者的结果有负面影响。我们提出了一种不确定性指导贝叶斯分类（UGBC）方案，旨在准确地分类控制，I/II类和III/IV类LGN（3类）在肾小球水平的分类任务（26,634分割肾小球图像）和肾脏水平的分类任务（87 MRL/Ipr小鼠肾脏切片）。使用高通量批量标记方案执行数据注释，该方案旨在利用深度神经网络（或DNN）对标签噪声的抵抗力。我们的增强UGBC方案实现了94.5%的加权肾小球水平准确度，同时实现了96.6%的加权肾脏水平准确度，分别比标准卷积神经网络（CNN）架构提高了11.8%和3.5%。
The kidney biopsy based diagnosis of Lupus Nephritis (LN) is characterized by low inter-observer agreement, with misdiagnosis being associated with increased patient morbidity and mortality. Although various Computer Aided Diagnosis (CAD) systems have been developed for other nephrohistopathological applications, little has been done to accurately classify kidneys based on their kidney level Lupus Glomerulonephritis (LGN) scores. The successful implementation of CAD systems has also been hindered by the diagnosing physician's perceived classifier strengths and weaknesses, which has been shown to have a negative effect on patient outcomes. We propose an Uncertainty-Guided Bayesian Classification (UGBC) scheme that is designed to accurately classify control, class I/II, and class III/IV LGN (3 class) at both the glomerular-level classification task (26,634 segmented glomerulus images) and the kidney-level classification task (87 MRL/Ipr mouse kidney sections). Data annotation was performed using a high throughput, bulk labeling scheme that is designed to take advantage of Deep Neural Network's (or DNNs) resistance to label noise. Our augmented UGBC scheme achieved a 94.5% weighted glomerular-level accuracy while achieving a weighted kidney-level accuracy of 96.6%, improving upon the standard Convolutional Neural Network (CNN) architecture by 11.8% and 3.5% respectively.