Institute for Ophthalmic Research, University of Tübingen, Tübingen, Germany.
Institute for Ophthalmic Research, University of Tübingen, Tübingen, Germany; University Eye Clinic, University of Tübingen, Tübingen, Germany.
Med Image Anal. 2020 Aug;64:101724. doi: 10.1016/j.media.2020.101724. Epub 2020 May 18.
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.
基于深度学习的系统可以在各种医疗应用案例中实现与医生相当的诊断性能，包括糖尿病性视网膜病变的诊断。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很好的校准。然而，深度神经网络（DNN）经常对其预测过于自信，并且不容易进行直接的概率处理。在这里，我们描述了一个基于测试时数据扩充的直观框架，用于量化用于诊断糖尿病性视网膜病变的最先进的 DNN 的诊断不确定性。我们表明，所得到的不确定性度量是经过校准的，并且有经验的医生也认为具有不确定诊断的病例难以评估。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。
