Zusammenfassung
Advances in medical imaging and convolutional neural networks (CNNs) have made it possible to achieve excellent diagnostic accuracy from CNNs comparable to human raters. However, CNNs are still not implemented in medical trials as they appear as a black box system and their inner workings cannot be properly explained. Therefore, it is essential to assess CNN relevance maps, which highlight regions that primarily contribute to the prediction. This study focuses on the comparison of algorithms for generating heatmaps to visually explain the learned patterns of Alzheimer’s disease (AD) classification. T1-weighted volumetric MRI data were entered into a 3D CNN. Heatmaps were then generated for different visualization methods using the iNNvestigate and keras-vis libraries. The model reached an area under the curve of 0.93 and 0.75 for separating AD dementia patients from controls and patients with amnestic mild cognitive impairment from controls, respectively. Visualizations for the methods deep Taylor decomposition and layer-wise relevance propagation (LRP) showed most reasonable results for individual patients matching expected brain regions. Other methods, such as Grad-CAM and guided backpropagation showed more scattered activations or random areas. For clinically research, deep Taylor decomposition and LRP showed most valuable network activation patterns.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Literatur
Alber M, Lapuschkin S, Seegerer P, et al. iNNvestigate neural networks! J Mach Learn Res. 2019;20:1–8.
Rieke J, Eitel F, Weygandt M, et al. Visualizing vonvolutional networks for MRIbased diagnosis of Alzheimer’s disease. In: Understanding and Interpreting Machine Learning in Medical Image Computing Applications. Springer; 2018. p. 24–31.
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.
Zintgraf LM, Cohen TS, Adel T, et al. Visualizing deep neural network decisions: prediction difference analysis. In: International Conference on Learning Representations (ICLR); 2017. .
Grothe M, Heinsen H, Teipel S. Longitudinal measures of cholinergic forebrain atrophy in the transition from healthy aging to Alzheimer’s disease. Neurobiol Aging. 2013;34(4):1210–1220.
Dyrba M, Barkhof F, Fellgiebel A, et al. Predicting prodromal Alzheimer’s disease in subjects with mild cognitive impairment using machine learning classification of multimodal multicenter DTI and MRI data. J Neuroimaging. 2015;25(5):738–747.
Kotikalapudi R, contributors. keras-vis. GitHub; 2019.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Fachmedien Wiesbaden GmbH, ein Teil von Springer Nature
About this paper
Cite this paper
Dyrba, M., Pallath, A.H., Marzban, E.N. (2020). Comparison of CNN Visualization Methods to Aid Model Interpretability for Detecting Alzheimer’s Disease. In: Tolxdorff, T., Deserno, T., Handels, H., Maier, A., Maier-Hein, K., Palm, C. (eds) Bildverarbeitung für die Medizin 2020. Informatik aktuell. Springer Vieweg, Wiesbaden. https://doi.org/10.1007/978-3-658-29267-6_68
Download citation
DOI: https://doi.org/10.1007/978-3-658-29267-6_68
Published:
Publisher Name: Springer Vieweg, Wiesbaden
Print ISBN: 978-3-658-29266-9
Online ISBN: 978-3-658-29267-6
eBook Packages: Computer Science and Engineering (German Language)