Differential Diagnosis of Frontotemporal Dementia, Alzheimer's Disease, and Normal Aging Using a Multi-Scale Multi-Type Feature Generative Adversarial Deep Neural Network on Structural Magnetic Resonance Images
Open accessAbstract
Purpose: Alzheimer's disease and Frontotemporal dementia are the first and third most common forms of dementia. Due to their similar clinical symptoms, they are easily misdiagnosed as each other even with sophisticated clinical guidelines. For disease-specific intervention and treatment, it is essential to develop a computer-aided system to improve the accuracy of their differential diagnosis. Recent advances in deep learning have delivered some of the best performance for medical image recognition tasks. However, its application to the differential diagnosis of AD and FTD pathology has not been explored. Methods: In this study, we proposed a novel deep learning based framework to distinguish between brain images of normal aging individuals and subjects with AD and FTD. Specifically, we combined the multiscale and multitype MRI-base image features with Generative Adversarial Network data augmentation technique to improved the differential diagnosis accuracy. Results: Each of the multiscale, mutitype and data augmentation method improved the ability for differential diagnosis for both AD and FTD. A 10-fold cross validation experiment performed on a large sample of 1,954 images using the proposed framework achieved a high overall accuracy of 88.28%. Conclusions: The salient contributions of this study are three fold: 1) our experiments demonstrate that the combination of multiple structural features extracted at different scales with our proposed deep neural network yields superior performance than individual features; 2) we show that the use of Generative Adversarial Network for data augmentation could further improve the discriminant ability of the network regarding challenging tasks such as differentiating dementia sub-types; 3) and finally, we show that ensemble classifier strategy could make the network more robust and stable.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Numerous groups have taken on the challenge of nADD diagnosis using deep learning, but even these tasks were constructed as simple binary classifications between disease subtypes.
“Though numerous groups have taken on the challenge of nADD diagnosis using deep learning18–20,25,26, even these tasks were constructed as simple binary classifications between disease subtypes.”
From Multimodal deep learning for Alzheimer's disease dementia assessment (2022) · cites this paper as [20]
The Introduction says most previous dementia-classification studies used binary tasks, but it also describes this paper’s own deep-learning approach as classifying normal controls, Alzheimer’s disease, and frontotemporal dementia. The Discussion likewise identifies it as a differential diagnosis framework for all three groups. Thus this cited study was not constructed as a simple binary classification. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredMa et al. found a deep learning framework achieved an overall accuracy of 88.28% in differentiating AD from FTD.
“Ma et al. found that a proposed deep learning framework achieved an overall accuracy of 88.28% in differentiating AD from FTD [17]”
From The use of neuroimaging techniques in the early and differential diagnosis of dementia (2023) · cites this paper as [17]
The Abstract (Results) reports 88.28% overall accuracy in a 10-fold cross-validation of 1,954 images, but the framework classified normal aging, AD, and FTD—not just AD versus FTD. The Discussion separately notes only three misdiagnoses between AD and FTD; it does not give 88.28% as the accuracy for that pair alone. (LLM, conf=0.89)
Experimental — accuracy not yet measuredOthers have demonstrated the efficacy of deep learning in discriminating AD from specific types of non-AD dementia.
“Others have also demonstrated the efficacy of deep learning in discriminating AD from specific types of nADD18–20.”
From Multimodal deep learning for Alzheimer's disease dementia assessment (2022) · cites this paper as [20]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Hierarchical Feature Representation and Multimodal Fusion with Deep Learning for AD/MCI Diagnosis
Suk, H.-I., Lee, S.-W., & Shen, D. (2014) · NeuroImage · doi:10.1016/j.neuroimage.2014.06.077 · Cited by 968 · see citing works
Focal cortical presentations of Alzheimer's disease
Alladi, S., Xuereb, J., Bak, T., Nestor, P., Knibb, J., Patterson, K., & Hodges, J. R. (2007) · Brain · doi:10.1093/brain/awm213 · Cited by 581 · cited 1× · see citing works
“This is due to the similarities in their clinical presentation, cognitive domains impairment, brain atrophy, and progressive alterations in language ability, behavior, and personality (Neary et al., 2005; Alladi et al., 2007; Womack et al., 2011).”
BackgroundA meta-analysis of diffusion tensor imaging in mild cognitive impairment and Alzheimer's disease
Sexton, C. E., Kalu, U. G., Filippini, N., Mackay, C. E., & Ebmeier, K. P. (2011) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2010.05.019 · Cited by 410 · see citing works
Kim, J. P., Kim, J., Park, Y. H., Park, S. B., Lee, J. S., Yoo, S., Kim, E.-J., Kim, H. J., Na, D. L., Brown, J. A., et al. (2019) · NeuroImage: Clinical · doi:10.1016/j.nicl.2019.101811 · Cited by 100 · see citing works
Womack, K. B., Diaz-Arrastia, R., Aizenstein, H. J., Arnold, S. E., Barbas, N. R., Boeve, B. F., Clark, C. M., DeCarli, C. S., Jagust, W. J., Leverenz, J. B., et al. (2011) · Archives of Neurology · doi:10.1001/archneurol.2010.295 · Cited by 85 · see citing works
Tong, T., Ledig, C., Guerrero, R., Schuh, A., Koikkalainen, J., Tolonen, A., Rhodius, H., Barkhof, F., Tijms, B., Lemstra, A. W., et al. (2017) · NeuroImage: Clinical · doi:10.1016/j.nicl.2017.06.012 · Cited by 54 · see citing works
Flagged first, then by citations
Research works printed but not linked: 42
- Almahairi A. Rajeswar S. Sordoni A. Bachman P. Courville A. (2018). Augmented cyclegan: learning many-to-many mappings from unpaired data. arXiv [Preprint]. arXiv:1802.10151. · arXiv
- Arjovsky M. Bottou L. (2017). Towards principled methods for training generative adversarial networks. arXiv [Preprint]. arXiv:1701.04862. · arXiv
- Arjovsky M. Chintala S. Bottou L. (2017). Wasserstein gan. arXiv [Preprint]. arXiv:1701.07875. · arXiv
- Association A. (2011). 2011 Alzheimer's Disease Facts and Figures. Alzheimer's Dement. 7: 208. 10.1016/j.jalz.2011.02.004 21414557 · DOI
- Awate S. P. Leahy R. M. Joshi A. A. (2017). Kernel methods for Riemannian analysis of robust descriptors of the cerebral cortex, in Lecture Notes in Computer Science, Vol. 6533 (Springer International Publishing), 28– 40. 10.1007/978-3-319-59050-9_3 PMC5794037 29398876 · DOI
- Bang J. Spina S. Miller B. L. (2015). Frontotemporal dementia. Lancet 386, 1672– 1682. 10.1016/S0140-6736(15)00461-4 26595641 PMC5970949 · DOI · Paper page
- Beg M. F. Miller M. I. Trouvé A. Younes L. (2005). Computing large deformation metric mappings via geodesic flows of diffeomorphisms. Int. J. Comput. Vis. 61, 139– 157. 10.1023/B:VISI.0000043755.93987.aa · DOI
- Bruun M. Koikkalainen J. Rhodius-Meester H. F. M. Baroni M. Gjerum L. Van Gils M.. (2019). Detecting frontotemporal dementia syndromes using MRI biomarkers. NeuroImage 22: 101711. 10.1016/j.nicl.2019.101711 30743135 PMC6369219 · DOI
- Cash D. M. Melbourne A. Modat M. Cardoso M. J. Clarkson M. J. Fox N. C.. (2012). Cortical folding analysis on patients with Alzheimer's disease and mild cognitive impairment, in Medical Image Computing and Computer-Assisted Intervention - MICCAI 2012, eds Ayache N. Delingette H. Goll P. Mori K. (Berlin; Heidelberg: Springer), 289– 296. 10.1007/978-3-642-33454-2_36 23286142 · DOI
- Dale A. M. Fischl B. S. M. (1999). Cortical surface-based analysis. II: Inflation, flattening, and a surface-based coordinate system. Neuroimage, 9, 195– 207. 10.1006/nimg.1998.0396 9931269 · DOI · Paper page
- Davatzikos C. Bhatt P. Shaw L. M. Batmanghelich K. N. Trojanowski J. Q. (2011). Prediction of MCI to AD conversion, via MRI, CSF biomarkers, and pattern classification. Neurobiol. Aging 32, 2322– e19. 10.1016/j.neurobiolaging.2010.05.023 20594615 PMC2951483 · DOI
- Davatzikos C. Resnick S. M. Wu X. Parmpi P. Clark C. M. (2008). Individual patient diagnosis of AD and FTD via high-dimensional pattern classification of MRI. Neuroimage 41, 1220– 1227. 10.1016/j.neuroimage.2008.03.050 18474436 PMC2528893 · DOI
- Du A.-T. Schuff N. Kramer J. H. Rosen H. J. Gorno-Tempini M. L. Rankin K.. (2007). Different regional patterns of cortical thinning in Alzheimer's disease and frontotemporal dementia. Brain 130, 1159– 1166. 10.1093/brain/awm016 17353226 PMC1853284 · DOI
- Goodfellow I. Pouget-Abadie J. Mirza M. Xu B. Warde-Farley D. Ozair S. (2014). Generative adversarial nets, in Advances in Neural Information Processing Systems, 27, eds Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence and K. Q. Weinberger (Curran Associates, Inc.) 2672– 2680. Available online at: http://papers.nips.cc/paper/5423-generative-adversarial-nets.pdf
- He K. Zhang X. Ren S. Sun J. (2016). Deep residual learning for image recognition, in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770– 778. 10.1109/CVPR.2016.90 · DOI · Paper page
- Hinton G. E. Salakhutdinov R. R. (2006). Reducing the dimensionality of data with neural networks. Science 313, 504– 507. 10.1126/science.1127647 16873662 · DOI · Paper page
- Jiskoot L. C. Panman J. L. Meeter L. H. Dopper E. G. Donker Kaat L. Franzen S.. (2018). Longitudinal multimodal MRI as prognostic and diagnostic biomarker in presymptomatic familial frontotemporal dementia. Brain 142, 193– 208. 10.1093/brain/awy288 30508042 PMC6308313 · DOI
- Krizhevsky A. Sutskever I. Hinton G. E. (2012). Imagenet classification with deep convolutional neural networks, in Advances in Neural Information Processing Systems (Curran Associates, Inc.), 1097– 1105. Available online at: http://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf
- Lata K. Dave M. Nishanth K. N. (2019). Data augmentation using generative adversarial network. Proceedings of 2nd International Conference on Advanced Computing and Software Engineering (ICACSE) 2019. Available online at: SSRN: https://ssrn.com/abstract=3349576 or 10.2139/ssrn.3349576 · DOI
- Litjens G. Kooi T. Bejnordi B. E. Setio A. A. A. Ciompi F. Ghafoorian M.. (2017). A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60– 88. 10.1016/j.media.2017.07.005 28778026 · DOI · Paper page
- Looi J. C. L. Walterfang M. Styner M. Svensson L. Lindberg O. Östberg P.. (2010). Shape analysis of the neostriatum in frontotemporal lobar degeneration, Alzheimer's disease, and controls. Neuroimage 51, 970– 986. 10.1016/j.neuroimage.2010.02.017 20156566 · DOI
- Lu D. Popuri K. Ding G. W. Balachandar R. Beg M. F. (2018a). Multimodal and multiscale deep neural networks for the early diagnosis of Alzheimer's disease using structural MR and FDG-PET images. Sci. Rep. 8: 5697. 10.1038/s41598-018-22871-z 29632364 PMC5890270 · DOI
- Lu D. Popuri K. Ding G. W. Balachandar R. Beg M. F. (2018b). Multiscale deep neural network based analysis of FDG-PET images for the early diagnosis of Alzheimer's disease. Med. Image Anal. 46, 26– 34. 10.1016/j.media.2018.02.002 29502031 · DOI
- Ma D. Popuri K. Bhalla M. Sangha O. Lu D. Cao J.. (2018). Quantitative assessment of field strength, total intracranial volume, sex, and age effects on the goodness of harmonization for volumetric analysis on the ADNI database. Hum. Brain Mapp. 40, 1507– 1527 10.1002/hbm.24463 30431208 PMC6449147 · DOI
- Neary D. Snowden J. Mann D. (2005). Frontotemporal dementia. Lancet Neurol. 4, 771– 780. 10.1016/S1474-4422(05)70223-4 16239184 · DOI
- Neary D. Snowden J. S. Gustafson L. Passant U. Stuss D. Black S.. (1998). Frontotemporal lobar degeneration A consensus on clinical diagnostic criteria. Neurology 51, 1546– 1554. 10.1212/WNL.51.6.1546 9855500 · DOI · Paper page
- Pasquier F. (2005). Telling the difference between frontotemporal dementia and Alzheimer's disease. Curr. Opin. Psychiatry 18, 628– 632. 10.1097/01.yco.0000185988.05741.2a 16639086 · DOI
- Raamana P. R. Rosen H. Miller B. Weiner M. W. Wang L. Beg M. F. (2014). Three-class differential diagnosis among Alzheimer disease, frontotemporal dementia, and controls. Front. Neurol. 5: 71. 10.3389/fneur.2014.00071 24860545 PMC4026692 · DOI · Paper page
- Raamana P. R. Weiner M. W. Wang L. Beg M. F. Initiative A. D. N. (2015). Thickness network features for prognostic applications in dementia. Neurobiol. Agin 36, S91– S102. 10.1016/j.neurobiolaging.2014.05.040 25444603 PMC5849081 · DOI
- Rabinovici G. Seeley W. Kim E. Gorno-Tempini M. Rascovsky K. Pagliaro T.. (2008). Distinct MRI atrophy patterns in autopsy-proven Alzheimer's disease and frontotemporal lobar degeneration. Am. J. Alzheimer's Dis. 22, 474– 488. 10.1177/1533317507308779 18166607 PMC2443731 · DOI
- Ronneberger O. Fischer P. Brox T. (2015). U-net: convolutional networks for biomedical image segmentation, in International Conference on Medical Image Computing and Computer-Assisted Intervention (Munich: Springer), 234– 241. 10.1007/978-3-319-24574-4_28 · DOI · Paper page
- Sandfort V. Yan K. Pickhardt P. J. Summers R. M. (2019). Data augmentation using generative adversarial networks (CycleGAN) to improve generalizability in CT segmentation tasks. Sci. Rep. 9, 1– 9. 10.1038/s41598-019-52737-x 31729403 PMC6858365 · DOI · Paper page
- Seiffert C. Khoshgoftaar T. M. Van Hulse J. Napolitano A. (2010). Rusboost: A hybrid approach to alleviating class imbalance. IEEE Trans. Syst. Man Cybern. Part A 40, 185– 197. 10.1109/TSMCA.2009.2029559 · DOI
- Shao S. Wang P. Yan R. (2019). Generative adversarial networks for data augmentation in machine fault diagnosis. Comput. Indus. 106, 85– 93. 10.1016/j.compind.2019.01.001 · DOI
- Shi H. Wang L. Ding G. Yang F. Li X. A. (2018). Data augmentation with improved generative adversarial networks, in 2018 24th International Conference on Pattern Recognition (ICPR) (Beijing: IEEE). 10.1109/ICPR.2018.8545894 · DOI
- Simonyan K. Zisserman A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv [Preprint]. arXiv:1409.1556. · arXiv
- Szegedy C. Ioffe S. Vanhoucke V. Alemi A. A. (2017). Inception-v4, inception-resnet and the impact of residual connections on learning, in Thirty-First AAAI Conference on Artificial Intelligence (San Francisco, CA).
- Varma A. Snowden J. Lloyd J. Talbot P. Mann D. Neary D. (1999). Evaluation of the NINCDS-ADRDA criteria in the differentiation of Alzheimer's disease and frontotemporal dementia. J. Neurol. Neurosurg. Psychiatry 66, 184– 188. 10.1136/jnnp.66.2.184 10071097 PMC1736233 · DOI
- Wang Y. Necus J. Kaiser M. Mota B. A. (2016). Universality in human cortical folding in health and disease. Proc. Natl. Acad. Sci. U.S.A. 113, 12820– 12825. 10.1073/pnas.1610175113 27791126 PMC5111660 · DOI
- Zheng Y. Guo H. Zhang L. Wu J. Li Q. Lv F. A. (2019). Machine learning-based framework for differential diagnosis between vascular dementia and Alzheimer's disease using structural MRI Features. Front. Neurol. 10: 1097. 10.3389/fneur.2019.01097 31708854 PMC6823227 · DOI · Paper page
- Popuri K. Ma D. Wang L. Beg M. F. (2020). Using machine learning to quantify structural MRI neurodegeneration patterns of Alzheimer's disease into dementia score: Independent validation on 8,834 images from ADNI, AIBL, OASIS, and MIRIAD databases. Human Brain Mapping, e25115. 10.1002/hbm.25115 32614505 PMC7469784 · DOI · Paper page
- Yee E. Ma D. Popuri K. Want L. Beg M. F. (2020). Construction of MRI-based alzheimer's disease score based on efficient 3D convolutional neural network – comprehensive validation on 7209 multi-centre dataset. J. Alzheimer's Dis. (Accepted) PMC9159475 33252079
Cited by
Sorted by citations
Multimodal deep learning for Alzheimer's disease dementia assessment
Qiu, S., Miller, M. I., Joshi, P. S., Lee, J. C., Xue, C., Ni, Y., Wang, Y., De Anda-Duran, I., Hwang, P. H., Cramer, J. A., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-31037-5 · Cited by 420 · see citing works
The use of neuroimaging techniques in the early and differential diagnosis of dementia
Chouliaras, L., & O’Brien, J. T. (2023) · Molecular Psychiatry · doi:10.1038/s41380-023-02215-8 · Cited by 186 · see citing works
“Ma et al. found that a proposed deep learning framework achieved an overall accuracy of 88.28% in differentiating AD from FTD [17] while Yu et al. showed that an AD atrophy index could identify AD and FTD from controls with an AUC of 0.88 and an FTD atrophy index could identify FTD from AD with an…”
ResultInfluentialDeep grading for MRI-based differential diagnosis of Alzheimer’s disease and frontotemporal dementia
Nguyen, H.-D., Clément, M., Planche, V., Mansencal, B., & Coupé, P. (2023) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2023.102636 · Cited by 35 · see citing works
Barnard, L., Botha, H., Corriveau-Lecavalier, N., Graff-Radford, J., Dicks, E., Gogineni, V., Zhang, G., Burkett, B. J., Johnson, D. R., Huls, S. J., et al. (2025) · Neurology · doi:10.1212/wnl.0000000000213831 · Cited by 25 · see citing works
Di Benedetto, M., Carrara, F., Tafuri, B., Nigro, S., De Blasi, R., Falchi, F., Gennaro, C., Gigli, G., Logroscino, G., & Amato, G. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105937 · Cited by 14 · see citing works
Gonzalez-Gomez, R., Ibañez, A., & Moguilner, S. (2023) · Network Neuroscience · doi:10.1162/netn_a_00285 · Cited by 10 · see citing works
Ma, D., Stocks, J., Rosen, H., Kantarci, K., Lockhart, S. N., Bateman, J. R., Craft, S., Gurcan, M. N., Popuri, K., Beg, M. F., et al. (2024) · Frontiers in Neuroscience · doi:10.3389/fnins.2024.1331677 · Cited by 9 · see citing works
Self-citation
- Authors
- Ma, D., Lu, D., Popuri, K., Wang, L., Beg, M. F., & Initiative, A. D. N.
- Affiliations
- Simon Fraser University (CA)
- Northwestern University (US)
- Corresponding author
- Lu, Donghuan
- Beg, Mirza Faisal
- Venue
- Frontiers in Neuroscience
- Publisher
- Frontiers Media SA
- Published
- 2020-10-22
- Volume
- 14
- Pages
- 853-853
- ISSN
- 1662-453X (ISSN-L)
- PMC
- PMC7643018
- OpenAlex
- W3094064442
- Cited by
- 56
- References
- 6
- Citations by year
- 2026: 1 · 2025: 13 · 2024: 10 · 2023: 8 · 2022: 14 · 2021: 8 · 2020: 2
- FWCI
- 5.84
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Frontiers in Neuroscience (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Summit (Simon Fraser University) (submittedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Summit (Simon Fraser University) (submittedVersion, cc-by)
- Funders
- Natural Sciences and Engineering Research Council of Canada
- Canadian Institutes of Health Research
- Michael Smith Foundation for Health Research
- Fondation Brain Canada
- Alzheimer Society Research Program
- Alzheimer Society
- Alzheimer Society of B.C.
- National Institutes of Health (R01 EB020062, R01 AG055121)
- National Science Foundation (NSF 1734853, NSF 1636893)
- Alzheimer's Disease Neuroimaging Initiative
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Retinal Imaging and Analysis
- Keywords
- frontotemporal dementia, Alzheimer's disease, differential diagnosis, normal aging, structural MRI, multi-scale feature extraction, generative adversarial network data augmentation, computer-aided diagnosis, ensemble classifiers
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
