Integrating uncertainty in deep neural networks for MRI based stroke analysis

Abstract

At present, the majority of the proposed Deep Learning (DL) methods provide point predictions without quantifying the model's 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 patientlevel 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.

Review of deep learning: concepts, CNN architectures, challenges, applications, future directions

“…In biology, the confidence score reduces the resources and time expended in proving the outcomes of the misleading prediction. Generally speaking, in healthcare or similar applications, the uncertainty scaling is frequently very significant; it helps in evaluating automated clinical decisions and the reliability of machine learning-based disease-diagnosis [176,177]. Because overconfident prediction can be the output of different DL models, the score of probability (achieved from the softmax output of the direct-DL) is often not in the correct scale [178].…”

A review of medical image data augmentation techniques for deep learning applications

“…If an image has one or more contours associated with it, the same transformation is applied to the contours. Geometric transformations are so common that they were utilised by 92 of the 93 basic augmentation studies 15–106 …”

“…Patches are generated from the under‐represented class to even the balance. 30 articles made use of cropping 15–17,19,23,32,33,35,41,43,48,50,58,59,66,68,69,71,74,78,80,82,84,85,90,97,98,102,104,105 …”

Timing the Ischemic Stroke by Multiparametric Quantitative Magnetic Resonance Imaging

“…Fortunately, there is extensive ongoing research focused on developing interpretability methods tailored to ML algorithms of imaging data (53). The clinician' s trust could also be enhanced by including uncertainty information about the reliability of predictions made at the patient level (55). Herzog et al (55) incorporated Bayesian uncertainty into CNNs developed for diagnosing ischemia using MRI, which showed improved prediction accuracy and higher uncertainty measures for false patient classifications enabling filtering of patients requiring closer examination.…”

“…The clinician' s trust could also be enhanced by including uncertainty information about the reliability of predictions made at the patient level (55). Herzog et al (55) incorporated Bayesian uncertainty into CNNs developed for diagnosing ischemia using MRI, which showed improved prediction accuracy and higher uncertainty measures for false patient classifications enabling filtering of patients requiring closer examination. A similar component that provides uncertainty estimates associated with the predicted time window or extent of viable tissue, according to T 2 MRI, is required.…”