Helmholtz Gemeinschaft

Search
Browse
Statistics
Feeds

Uncovering convolutional neural network decisions for diagnosing multiple sclerosis on conventional MRI using layer-wise relevance propagation

[img]
Preview
PDF (Original Article) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB
[img]
Preview
PDF (Supplementary data) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB

Item Type:Article
Title:Uncovering convolutional neural network decisions for diagnosing multiple sclerosis on conventional MRI using layer-wise relevance propagation
Creators Name:Eitel, F. and Soehler, E. and Bellmann-Strobl, J. and Brandt, A.U. and Ruprecht, K. and Giess, R.M. and Kuchling, J. and Asseyer, S. and Weygandt, M. and Haynes, J.D. and Scheel, M. and Paul, F. and Ritter, K.
Abstract:Machine learning-based imaging diagnostics has recently reached or even surpassed the level of clinical experts in several clinical domains. However, classification decisions of a trained machine learning system are typically non-transparent, a major hindrance for clinical integration, error tracking or knowledge discovery. In this study, we present a transparent deep learning framework relying on 3D convolutional neural networks (CNNs) and layer-wise relevance propagation (LRP) for diagnosing multiple sclerosis (MS), the most widespread autoimmune neuroinflammatory disease. MS is commonly diagnosed utilizing a combination of clinical presentation and conventional magnetic resonance imaging (MRI), specifically the occurrence and presentation of white matter lesions in T2-weighted images. We hypothesized that using LRP in a naive predictive model would enable us to uncover relevant image features that a trained CNN uses for decision-making. Since imaging markers in MS are well-established this would enable us to validate the respective CNN model. First, we pre-trained a CNN on MRI data from the Alzheimer's Disease Neuroimaging Initiative (n = 921), afterwards specializing the CNN to discriminate between MS patients (n = 76) and healthy controls (n = 71). Using LRP, we then produced a heatmap for each subject in the holdout set depicting the voxel-wise relevance for a particular classification decision. The resulting CNN model resulted in a balanced accuracy of 87.04% and an area under the curve of 96.08% in a receiver operating characteristic curve. The subsequent LRP visualization revealed that the CNN model focuses indeed on individual lesions, but also incorporates additional information such as lesion location, non-lesional white matter or gray matter areas such as the thalamus, which are established conventional and advanced MRI markers in MS. We conclude that LRP and the proposed framework have the capability to make diagnostic decisions of CNN models transparent, which could serve to justify classification decisions for clinical review, verify diagnosis-relevant features and potentially gather new disease knowledge.
Keywords:Convolutional Neural Networks, Deep Learning, Multiple Sclerosis, MRI, Layer-Wise Relevance Propagation, Visualization, Transfer Learning
Source:NeuroImage: Clinical
ISSN:2213-1582
Publisher:Elsevier (U.K.)
Volume:24
Page Range:102003
Date:6 September 2019
Official Publication:https://doi.org/10.1016/j.nicl.2019.102003
PubMed:View item in PubMed

Repository Staff Only: item control page

Downloads

Downloads per month over past year

Open Access
MDC Library