Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer’s disease
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index.
Abstract
Background: Although convolutional neural networks (CNNs) achieve high diagnostic accuracy for detecting Alzheimer’s disease (AD) dementia based on magnetic resonance imaging (MRI) scans, they are not yet applied in clinical routine. One important reason for this is a lack of model comprehensibility. Recently developed visualization methods for deriving CNN relevance maps may help to fill this gap as they allow the visualization of key input image features that drive the decision of the model. We investigated whether models with higher accuracy also rely more on discriminative brain regions predefined by prior knowledge. Methods: We trained a CNN for the detection of AD in N = 663 T1-weighted MRI scans of patients with dementia and amnestic mild cognitive impairment (MCI) and verified the accuracy of the models via cross-validation and in three independent samples including in total N = 1655 cases. We evaluated the association of relevance scores and hippocampus volume to validate the clinical utility of this approach. To improve model comprehensibility, we implemented an interactive visualization of 3D CNN relevance maps, thereby allowing intuitive model inspection. Results: Across the three independent datasets, group separation showed high accuracy for AD dementia versus controls (AUC ≥ 0.91) and moderate accuracy for amnestic MCI versus controls (AUC ≈ 0.74). Relevance maps indicated that hippocampal atrophy was considered the most informative factor for AD detection, with additional contributions from atrophy in other cortical and subcortical regions. Relevance scores within the hippocampus were highly correlated with hippocampal volumes (Pearson’s r ≈ −0.86, p < 0.001). Conclusion: The relevance maps highlighted atrophy in regions that we had hypothesized a priori. This strengthens the comprehensibility of the CNN models, which were trained in a purely data-driven manner based on the scans and diagnosis labels. The high hippocampus relevance scores as well as the high performance achieved in independent samples support the validity of the CNN models in the detection of AD-related MRI abnormalities. The presented data-driven and hypothesis-free CNN modeling approach might provide a useful tool to automatically derive discriminative features for complex diagnostic tasks where clear clinical criteria are still missing, for instance for the differential diagnosis between various types of dementia.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
Bach, S., Binder, A., Montavon, G., Klauschen, F., Müller, K.-R., & Samek, W. (2015) · PLOS ONE · doi:10.1371/journal.pone.0130140 · Cited by 4,524 · cited 16×
“Recently, three studies compared LRP with other CNN visualization methods for the detection of Alzheimer’s disease in T1-weighted MRI scans [11, 12, 14].”
BackgroundMethodInfluentialStriving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
Advancing research diagnostic criteria for Alzheimer's disease: the IWG-2 criteria
Dubois, B., Feldman, H. H., Jacova, C., Hampel, H., Molinuevo, J. L., Blennow, K., DeKosky, S. T., Gauthier, S., Selkoe, D., Bateman, R., et al. (2014) · The Lancet Neurology · doi:10.1016/s1474-4422(14)70090-0 · Cited by 3,321
Methods for interpreting and understanding deep neural networks
Montavon, G., Samek, W., & Müller, K.-R. (2018) · Digital Signal Processing · doi:10.1016/j.dsp.2017.10.011 · Cited by 2,665
Jack, C. R., Albert, M. S., Knopman, D. S., McKhann, G. M., Sperling, R. A., Carrillo, M. C., Thies, B., & Phelps, C. H. (2011) · Alzheimer's & Dementia · doi:10.1016/j.jalz.2011.03.004 · Cited by 2,042 · cited 6×
“Therefore, hippocampus volume is currently the best-established MRI marker for diagnosing Alzheimer’s disease at the dementia stage as well as at its prodromal stage amnestic mild cognitive impairment (MCI) [1, 2].”
BackgroundMethodInfluentialExplainable AI: Interpreting, Explaining and Visualizing Deep Learning
(2019) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-28954-6 · Cited by 1,377
The Centiloid Project: standardizing quantitative amyloid plaque estimation by PET
Klunk, W. E., Koeppe, R. A., Price, J. C., Benzinger, T. L., Devous, M. D., Jagust, W. J., Johnson, K. A., Mathis, C. A., Minhas, D., Pontecorvo, M. J., et al. (2015) · Alzheimer's & Dementia · doi:10.1016/j.jalz.2014.07.003 · Cited by 1,348 · cited 1×
“The PET scans were processed using the Centiloid SPM pipeline and converted to Centiloid values as recommended for the different amyloid PET traces [33-35].”
MethodSanity Checks for Saliency Maps
Adebayo, J., Gilmer, J., Muelly, M., Goodfellow, I., Hardt, M., & Kim, B. (2018) · arXiv · doi:10.48550/arxiv.1810.03292 · Cited by 1,294
Evaluating the Visualization of What a Deep Neural Network Has Learned
Samek, W., Binder, A., Montavon, G., Lapuschkin, S., & Muller, K.-R. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2599820 · Cited by 1,164
Cited by
Interpretable machine learning for dementia: a systematic review
Martin, S. A., Townend, F. J., Barkhof, F., & Cole, J. H. (2023) · Alzheimer's & Dementia · doi:10.1002/alz.12948 · Cited by 149
Moguilner, S., Whelan, R., Adams, H., Valcour, V., Tagliazucchi, E., & Ibáñez, A. (2023) · eBioMedicine · doi:10.1016/j.ebiom.2023.104540 · Cited by 39
Ten years of image analysis and machine learning competitions in dementia
Bron, E. E., Klein, S., Reinke, A., Papma, J. M., Maier-Hein, L., Alexander, D. C., & Oxtoby, N. P. (2022) · NeuroImage · doi:10.1016/j.neuroimage.2022.119083 · Cited by 17
Li, Q., Koehler, S., Koenig, A., Dyrba, M., Mallik, E., Linz, N., Priller, J., Spruth, E., Altenstein, S., Wiltfang, J., et al. (2025) · Journal of Alzheimer’s Disease · doi:10.1177/13872877251359967 · Cited by 6
Self-citation
Metadata
- Authors
- Dyrba, M., Hanzig, M., Altenstein, S., Bader, S., Ballarini, T., Brosseron, F., Buerger, K., Cantré, D., Dechent, P., Dobisch, L., Düzel, E., Ewers, M., Fliessbach, K., Glanz, W., Haynes, J.-D., Heneka, M. T., Janowitz, D., Keles, D. B., Kilimann, I., Laske, C., Maier, F., Metzger, C. D., Munk, M. H., Perneczky, R., Peters, O., Preis, L., Priller, J., Rauchmann, B., Roy, N., Scheffler, K., Schneider, A., Schott, B. H., Spottke, A., Spruth, E. J., Weber, M.-A., Ertl-Wagner, B., Wagner, M., Wiltfang, J., Jessen, F., Teipel, S. J., & for the ADNI, A.
- Venue
- Alzheimer's Research & Therapy
- Published
- 2021-11-23
- Volume
- 13
- Issue
- 1
- Pages
- 191-191
- ISSN
- 1758-9193 (ISSN-L)
- OpenAlex
- W3114255343
- Cited by
- 66
- References
- 18
- FWCI
- 6.66
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer’s disease. https://app.cochat.ai/papers/10.1186/s13195-021-00924-2
- The paper
- Dyrba, M., Hanzig, M., Altenstein, S., Bader, S., Ballarini, T., Brosseron, F., Buerger, K., Cantré, D., Dechent, P., Dobisch, L., Düzel, E., Ewers, M., Fliessbach, K., Glanz, W., Haynes, J.-D., Heneka, M. T., Janowitz, D., Keles, D. B., Kilimann, I., . . . for the ADNI, A. (2021). Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: evaluation in Alzheimer’s disease. Alzheimer's Research & Therapy. https://doi.org/10.1186/s13195-021-00924-2
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.