Expert-validated estimation of diagnostic uncertainty for deep neural networks in diabetic retinopathy detection
Expert-validated estimation of diagnostic uncertainty for deep neural networks in diabetic retinopathy detection
复制标题
糖尿病视网膜病变检测中深度神经网络诊断不确定性的专家验证估计
DOI：
10.1016/j.media.2020.101724
复制
发表时间：
2020-08-01
影响因子：
10.9
通讯作者：
Berens, Philipp
中科院分区：
文献类型：
--
作者：
Ayhan, Murat Seckin;Kuhlewein, Laura;Berens, Philipp
基于深度学习的系统可以在各种医疗用例中实现与医生相当的诊断性能，包括糖尿病视网膜病变的诊断。为了在临床实践中有用，有必要对这些系统报告其决策的不确定性进行良好校准。然而，深度神经网络（DNN）通常对它们的预测过于自信，并且不适合直接的概率处理。在这里，我们描述了一个直观的框架，基于测试时间数据增强，用于量化最先进的DNN诊断糖尿病视网膜病变的诊断不确定性。我们表明，所得出的测量不确定性是校准良好的，经验丰富的医生也发现不确定的诊断难以评估的情况下。这为基于DNN的诊断系统中的不确定性的综合处理铺平了道路。(C)2020 Elsevier B.V.保留所有权利。
Deep learning-based systems can achieve a diagnostic performance comparable to physicians in a variety of medical use cases including the diagnosis of diabetic retinopathy. To be useful in clinical practice, it is necessary to have well calibrated measures of the uncertainty with which these systems report their decisions. However, deep neural networks (DNNs) are being often overconfident in their predictions, and are not amenable to a straightforward probabilistic treatment. Here, we describe an intuitive framework based on test-time data augmentation for quantifying the diagnostic uncertainty of a state-of-the-art DNN for diagnosing diabetic retinopathy. We show that the derived measure of uncertainty is well-calibrated and that experienced physicians likewise find cases with uncertain diagnosis difficult to evaluate. This paves the way for an integrated treatment of uncertainty in DNN-based diagnostic systems. (C) 2020 Elsevier B.V. All rights reserved.