Integrating uncertainty in deep neural networks for MRI based stroke analysis
This work addresses the critical need for reliable automated diagnosis in medicine, particularly for ischemic stroke, by providing a framework that quantifies uncertainty to aid physicians in treatment decisions, though it is incremental as it builds on existing Bayesian methods.
The authors tackled the problem of deep learning models lacking uncertainty quantification in medical image analysis by integrating Bayesian uncertainty into a convolutional neural network for stroke lesion diagnosis on MRI images, achieving 95.33% accuracy at the image-level and 95.89% at the patient-level with improved uncertainty measures for false classifications.
At present, the majority of the proposed Deep Learning (DL) methods provide point predictions without quantifying the models uncertainty. However, a quantification of the reliability of automated image analysis is essential, in particular in medicine when physicians rely on the results for making critical treatment decisions. In this work, we provide an entire framework to diagnose ischemic stroke patients incorporating Bayesian uncertainty into the analysis procedure. We present a Bayesian Convolutional Neural Network (CNN) yielding a probability for a stroke lesion on 2D Magnetic Resonance (MR) images with corresponding uncertainty information about the reliability of the prediction. For patient-level diagnoses, different aggregation methods are proposed and evaluated, which combine the single image-level predictions. Those methods take advantage of the uncertainty in image predictions and report model uncertainty at the patient-level. In a cohort of 511 patients, our Bayesian CNN achieved an accuracy of 95.33% at the image-level representing a significant improvement of 2% over a non-Bayesian counterpart. The best patient aggregation method yielded 95.89% of accuracy. Integrating uncertainty information about image predictions in aggregation models resulted in higher uncertainty measures to false patient classifications, which enabled to filter critical patient diagnoses that are supposed to be closer examined by a medical doctor. We therefore recommend using Bayesian approaches not only for improved image-level prediction and uncertainty estimation but also for the detection of uncertain aggregations at the patient-level.