Abstract
Relevance maps derived from convolutional neural networks (CNN) indicate the influence of a particular image region on the decision of the CNN model. Individual maps are obtained for each single input 3D MRI image and various visualization options need to be adjusted to improve information content. In the use case of model prototyping and comparison, the common approach to save the 3D relevance maps to disk is impractical given the large number of combinations. Therefore, we developed a web application to aid interactive inspection of CNN relevance maps. For the requirements analysis, we interviewed several people from different stakeholder groups (model/visualization developers, radiology/neurology staff) following a participatory design approach. The visualization software was conceptually designed in a Model–View–Controller paradigm and implemented using the Python visualization library Bokeh. This framework allowed a Python server back-end directly executing the CNN model and related code, and a HTML/Javascript front-end running in any web browser. Slice-based 2D views were realized for each axis, accompanied by several visual guides to improve usability and quick navigation to image areas with high relevance. The interactive visualization tool greatly improved model inspection and comparison for developers. Owing to the well-structured implementation, it can be easily adapted to other CNN models and types of input data.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Samek W, Binder A, Montavon G, et al. Evaluating the visualization of what a deep neural network has learned. IEEE T Neur Net Lear. 2017;28(11):2660–2673.
Alber M, Lapuschkin S, Seegerer P, et al. iNNvestigate neural networks! J Mach Learn Res. 2019;20:1–8.
Böhle M, Eitel F, Weygandt M, et al. Layer-wise relevance propagation for explaining deep neural network decisions in MRI-based Alzheimer's disease classification. Front Aging Neurosci. 2019;11:194.
Dyrba M, Pallath AH, Marzban EN. Comparison of CNN visualization methods to aid model interpretability for detecting Alzheimer's disease. Proc BVM. 2020; p. 307–312.
Dyrba M, Hanzig M, Altenstein S, et al.. Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer's disease; 2020. https://arxiv.org/abs/2012.10294.
Bokeh contributors. The bokeh visualization library; 2020. https://bokeh.org.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Der/die Autor(en), exklusiv lizenziert durch Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature
About this paper
Cite this paper
Dyrba, M., Hanzig, M. (2021). Interactive Visualization of 3D CNN Relevance Maps to Aid Model Comprehensibility. In: Palm, C., Deserno, T.M., Handels, H., Maier, A., Maier-Hein, K., Tolxdorff, T. (eds) Bildverarbeitung für die Medizin 2021. Informatik aktuell. Springer Vieweg, Wiesbaden. https://doi.org/10.1007/978-3-658-33198-6_77
Download citation
DOI: https://doi.org/10.1007/978-3-658-33198-6_77
Published:
Publisher Name: Springer Vieweg, Wiesbaden
Print ISBN: 978-3-658-33197-9
Online ISBN: 978-3-658-33198-6
eBook Packages: Computer Science and Engineering (German Language)