An Analysis of the Interpretability of Neural Networks trained on Magnetic Resonance Imaging for Stroke Outcome Prediction

Esra Zihni, John D. Kelleher, Bryony McGarry

Research output: Contribution to conferencePaperpeer-review

Abstract

Applying deep learning models to MRI scans of acute stroke patients to extract features that are indicative of short-term outcome could assist a clinician’s treatment decisions. Deep learning models are usually accurate but are not easily interpretable. Here, we trained a convolutional neural network on ADC maps from hyperacute ischaemic stroke patients for prediction of short-term functional outcome and used an interpretability technique to highlight regions in the ADC maps that were most important in the prediction of a bad outcome. Although highly accurate, the model’s predictions were not based on aspects of the ADC maps related to stroke pathophysiology.
Original languageEnglish
DOIs
Publication statusPublished - 2021
EventIntl. Soc. Mag. Reson. Med -
Duration: 1 Jan 2021 → …

Conference

ConferenceIntl. Soc. Mag. Reson. Med
Period1/01/21 → …

Keywords

  • deep learning
  • MRI scans
  • acute stroke
  • short-term outcome
  • clinician’s treatment decisions
  • convolutional neural network
  • ADC maps
  • hyperacute ischaemic stroke
  • functional outcome
  • interpretability technique
  • stroke pathophysiology

Fingerprint

Dive into the research topics of 'An Analysis of the Interpretability of Neural Networks trained on Magnetic Resonance Imaging for Stroke Outcome Prediction'. Together they form a unique fingerprint.

Cite this