Implementation of model explainability for a basic brain tumor detection using convolutional neural networks on MRI slices.

Journal: Neuroradiology

Published Date: Jun 4, 2020

Abstract

PURPOSE: While neural networks gain popularity in medical research, attempts to make the decisions of a model explainable are often only made towards the end of the development process once a high predictive accuracy has been achieved.

Authors

Paul Windisch

European CyberKnife Center, Munich, Germany. paul.windisch@ksw.ch.
Pascal Weber

European CyberKnife Center, Munich, Germany.
Christoph Fürweger

Europäisches Cyberknife Zentrum München-Großhadern, Munich, Germany.
Felix Ehret

European CyberKnife Center, Munich, Germany.
Markus Kufeld

Charité CyberKnife Center, Charité Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany.
Daniel Zwahlen

Department of Radiation Oncology, Kantonsspital Winterthur, Winterthur, Switzerland.
Alexander Muacevic

Cyberknife Center, University of Munich Hospitals, Munich, Germany.

Keywords

Bayes Theorem Brain Neoplasms Contrast Media Datasets as Topic Diagnosis, Differential Glioblastoma Humans Image Interpretation, Computer-Assisted Magnetic Resonance Imaging Neural Networks, Computer Neurilemmoma

External Resources

View on PubMed Access via DOI PubMed (32500277)

Implementation of model explainability for a basic brain tumor detection using convolutional neural networks on MRI slices.

Abstract

Authors

Keywords

External Resources

Popular Topics

Recent Journals