Volltext-Downloads (blau) und Frontdoor-Views (grau)
  • search hit 1 of 1
Back to Result List

Integrating uncertainty in deep neural networks for MRI based stroke analysis

  • 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 patient-level diagnoses, different aggregation methods are proposed and evaluated, which combine the individual image-level predictions. Those methods take advantage of the uncertainty in the 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.

Export metadata

Additional Services

Search Google Scholar


Author:Lisa Herzog, Elvis Murina, Oliver DürrORCiDGND, Susanne Wegener, Beate SickGND
Parent Title (English):Medical Image Analysis
Document Type:Article
Year of Publication:2020
Release Date:2021/01/18
Tag:Bayesian convolutional neural networks; Uncertainty; Magnetic resonance imaging; Ischemic stroke
Issue:Vol. 65, Art. 101790
Page Number:21
Institutes:Institut für Optische Systeme - IOS
DDC functional group:500 Naturwissenschaften und Mathematik
Relevance:Peer reviewed Publikation in Master Journal List
Open Access?:Nein
Licence (German):License LogoUrheberrechtlich geschützt