Deep learning improves utility of tau PET in the study of Alzheimer's disease
Open accessAbstract
Introduction: Positron emission tomography (PET) imaging targeting neurofibrillary tau tangles is increasingly used in the study of Alzheimer's disease (AD), but its utility may be limited by conventional quantitative or qualitative evaluation techniques in earlier disease states. Convolutional neural networks (CNNs) are effective in learning spatial patterns for image classification. Methods: 18F‐MK6240 (n = 320) and AV‐1451 (n = 446) PET images were pooled from multiple studies. We performed iterations with differing permutations of radioligands, heuristics, and architectures. Performance was compared to a standard region of interest (ROI)‐based approach on prediction of memory impairment. We visualized attention of the network to illustrate decision making. Results: Overall, models had high accuracy (> 80%) with good average sensitivity and specificity (75% and 82%, respectively), and had comparable or higher accuracy to the ROI standard. Visualizations of model attention highlight known characteristics of tau radioligand binding. Discussion: CNNs could improve tau PET's role in early disease and extend the utility of tau PET across generations of radioligands.
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?
CNNs applied to PET scans may achieve high area-under-the-curve scores, but their saliency maps frequently fail to align with known pathological regions, reducing clinician trust.
“Convolutional neural networks applied to PET scans may achieve high area-under-the-curve scores, but their saliency maps frequently fail to align with known pathological regions, reducing clinician trust.”
From Artificial intelligence-driven multi-omics approaches in Alzheimer's disease: Progress, challenges, and future directions (2025) · cites this paper as [256]
The Results (Model performance; page unavailable) report model accuracy of at least 80% and evaluation by AUC, but do not give a CNN AUC value in the retrieved passage. Contrary to the claim about frequent misalignment, the Discussion (page unavailable) says the sensitivity analysis found expected binding patterns in regions affected by Alzheimer’s disease; our copy does not link the maps to reduced clinician trust. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredBenchmarking studies indicate that outputs of XAI techniques can be inconsistent and model-dependent.
“Techniques such as attention layers, SHAP, and patch-based visualizations aim to localize voxel- or gene-level contribution, yet benchmarking studies indicate that their outputs can be inconsistent and model-dependent256,282,289.”
From Artificial intelligence-driven multi-omics approaches in Alzheimer's disease: Progress, challenges, and future directions (2025) · cites this paper as [256]
The Discussion (page unavailable) says the paper’s occlusion sensitivity analysis did not consistently implicate a specific brain region, supporting a limited claim about variability in its visualizations. The Methods > Visualization and Results > Occlusion sensitivity analyses (pages unavailable) describe analyses of the authors’ tau PET models, not a benchmark of XAI techniques or evidence that outputs are model-dependent across techniques. (LLM, conf=0.77)
Experimental — accuracy not yet measured
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
Scikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · see citing works
Rethinking the Inception Architecture for Computer Vision
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.308 · Cited by 32,138 · see citing works
DeLong, E. R., DeLong, D. M., & Clarke-Pearson, D. L. (1988) · Biometrics · doi:10.2307/2531595 · Cited by 22,649 · see citing works
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · see citing works
Data Structures for Statistical Computing in Python
McKinney, W. (2010) · Proceedings of the Python in Science Conferences · doi:10.25080/majora-92bf1922-00a · Cited by 11,511 · see citing works
Estimation of the Youden Index and its Associated Cutoff Point
Fluss, R., Faraggi, D., & Reiser, B. (2005) · Biometrical Journal · doi:10.1002/bimj.200410135 · Cited by 2,604 · see citing works
The Mini-Mental State Examination
Folstein, M. F. (1983) · Archives of General Psychiatry · doi:10.1001/archpsyc.1983.01790060110016 · Cited by 1,975 · see citing works
Palmqvist, S., Janelidze, S., Quiroz, Y. T., Zetterberg, H., Lopera, F., Stomrud, E., Su, Y., Chen, Y., Serrano, G. E., Leuzy, A., et al. (2020) · JAMA · doi:10.1001/jama.2020.12134 · Cited by 1,603 · see citing works
An english translation of alzheimer’s 1907 paper, “über eine eigenartige erkankung der hirnrinde”
Stelzmann, R. A., Norman Schnitzlein, H., & Reed Murtagh, F. (1995) · Clinical Anatomy · doi:10.1002/ca.980080612 · Cited by 1,455 · see citing works
Halekoh, U., & Højsgaard, S. (2014) · Journal of Statistical Software · doi:10.18637/jss.v059.i09 · Cited by 1,324 · see citing works
PET Imaging of Tau Deposition in the Aging Human Brain
Schöll, M., Lockhart, S. N., Schonhaut, D. R., O’Neil, J. P., Janabi, M., Ossenkoppele, R., Baker, S. L., Vogel, J. W., Faria, J., Schwimmer, H. D., et al. (2016) · Neuron · doi:10.1016/j.neuron.2016.01.028 · Cited by 1,214 · see citing works
The pathological process underlying Alzheimer’s disease in individuals under thirty
Braak, H., & Del Tredici, K. (2011) · Acta Neuropathologica · doi:10.1007/s00401-010-0789-4 · Cited by 812 · see citing works
Four distinct trajectories of tau deposition identified in Alzheimer’s disease
Initiative, T. A. D. N., Vogel, J. W., Young, A. L., Oxtoby, N. P., Smith, R., Ossenkoppele, R., Strandberg, O. T., La Joie, R., Aksman, L. M., Grothe, M. J., et al. (2021) · Nature Medicine · doi:10.1038/s41591-021-01309-6 · Cited by 741 · see citing works
Ding, Y., Sohn, J. H., Kawczynski, M. G., Trivedi, H., Harnish, R., Jenkins, N. W., Lituiev, D., Copeland, T. P., Aboian, M. S., Mari Aparici, C., et al. (2019) · Radiology · doi:10.1148/radiol.2018180958 · Cited by 577 · see citing works
Clinical core of the Alzheimer's disease neuroimaging initiative: Progress and plans
Aisen, P. S. S., Petersen, R. C., Donohue, M., Gamst, A. C., Raman, R., Thomas, R. G., Walter, S., Trojanowski, J. Q., Shaw, L. M. J., Beckett, L. A., et al. (2010) · Alzheimer s & Dementia · doi:10.1016/j.jalz.2010.03.006 · Cited by 516 · see citing works
Weiner, M. W., Veitch, D. P., Aisen, P. S. S., Beckett, L. A., Cairns, N. J., Green, R. C., Harvey, D. J., Jack, C. R., Jagust, W. J., Morris, J. C., et al. (2016) · Alzheimer s & Dementia · doi:10.1016/j.jalz.2016.10.006 · Cited by 497 · see citing works
Longitudinal tau PET in ageing and Alzheimer’s disease
Jack, C. R., Wiste, H. J., Schwarz, C. G., Lowe, V. J., Senjem, M. L., Vemuri, P., Weigand, S. D., Therneau, T. M., Knopman, D. S., Gunter, J. L., et al. (2018) · Brain · doi:10.1093/brain/awy059 · Cited by 452 · see citing works
Manly, J. J., Bell-McGinty, S., Tang, M.-X., Schupf, N., Stern, Y., & Mayeux, R. (2005) · Archives of Neurology · doi:10.1001/archneur.62.11.1739 · Cited by 266 · see citing works
18F-MK-6240 PET for early and late detection of neurofibrillary tangles
Pascoal, T. A., Therriault, J., Benedet, A. L., Savard, M., Lussier, F. Z., Chamoun, M., Tissot, C., Qureshi, M. N. I., Kang, M. S., Mathotaarachchi, S. S., et al. (2020) · Brain · doi:10.1093/brain/awaa180 · Cited by 257 · see citing works
Predicting cognitive decline with deep learning of brain metabolism and amyloid imaging
Choi, H., & Jin, K. H. (2018) · Behavioural Brain Research · doi:10.1016/j.bbr.2018.02.017 · Cited by 255 · see citing works
Evaluation of volume-based and surface-based brain image registration methods
Klein, A., Ghosh, S. S., Avants, B., Yeo, B. T. T., Fischl, B., Ardekani, B., Gee, J. C., Mann, J. J., & Parsey, R. V. (2010) · NeuroImage · doi:10.1016/j.neuroimage.2010.01.091 · Cited by 255 · see citing works
Free and Cued Selective Reminding Identifies Very Mild Dementia in Primary Care
Grober, E. H., Sanders, A. E., Hall, C. B., & Lipton, R. B. (2010) · Alzheimer Disease & Associated Disorders · doi:10.1097/wad.0b013e3181cfc78b · Cited by 205 · see citing works
Amyloid and tau imaging biomarkers explain cognitive decline from late middle-age
Betthauser, T. J., Koscik, R. L., Jonaitis, E. M., Allison, S. L., Cody, K. A., Erickson, C. M., Rowley, H. A., Stone, C. K., Mueller, K. D., Clark, L. R., et al. (2019) · Brain · doi:10.1093/brain/awz378 · Cited by 174 · see citing works
Diagnosing Mild Cognitive Impairment (MCI) in clinical trials: a systematic review
Stephan, B. C. M., Minett, T., Pagett, E., Siervo, M., Brayne, C., & McKeith, I. G. (2013) · BMJ Open · doi:10.1136/bmjopen-2012-001909 · Cited by 148 · see citing works
Braak, H., Zetterberg, H., Tredici, K. D., & Blennow, K. (2013) · Acta Neuropathologica · doi:10.1007/s00401-013-1139-0 · Cited by 141 · see citing works
Bullich, S., Seibyl, J. P., Catafau, A. M., Jovalekic, A., Koglin, N., Barthel, H., Sabri, O., & Santi, S. D. (2017) · NeuroImage Clinical · doi:10.1016/j.nicl.2017.04.025 · Cited by 123 · see citing works
Dronse, J., Fließbach, K., Bischof, G. N., von Reutern, B., Faber, J., Hammes, J., Kuhnert, G., Neumaier, B., Onur, O. A., Kukolja, J., et al. (2016) · Journal of Alzheimer s Disease · doi:10.3233/jad-160316 · Cited by 118 · see citing works
Deep learning detection of informative features in tau PET for Alzheimer’s disease classification
Jo, T., Nho, K. T., Risacher, S. L., Saykin, A. J., & Initiative, A. D. N. (2020) · BMC Bioinformatics · doi:10.1186/s12859-020-03848-0 · Cited by 105 · see citing works
Feng, X., Lipton, Z. C., Yang, J., Small, S. A., & Provenzano, F. A. (2020) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2020.02.009 · Cited by 96 · see citing works
Self-citationLeuzy, A., Pascoal, T. A., Strandberg, O. T., Insel, P. S., Smith, R. A., Mattsson, N., Benedet, A. L., Cho, H., Lyoo, C. H., Joie, R. L., et al. (2021) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-021-05401-4 · Cited by 86 · see citing works
A Comparison of Partial Volume Correction Techniques for Measuring Change in Serial Amyloid PET SUVR
Schwarz, C. G., Gunter, J. L., Lowe, V. J., Weigand, S. D., Vemuri, P., Senjem, M. L., Petersen, R. C., Knopman, D. S., & Jack, C. R. (2018) · Journal of Alzheimer s Disease · doi:10.3233/jad-180749 · Cited by 85 · see citing works
Devanand, D. P., Andrews, H., Kreisl, W. C., Razlighi, Q. R., Gershon, A. A., Stern, Y., Mintz, A., Wısnıewskı, T., Acosta, E. P., Pollina, J., et al. (2020) · BMJ Open · doi:10.1136/bmjopen-2019-032112 · Cited by 83 · see citing works
Self-citationTowards clinical application of tau PET tracers for diagnosing dementia due to Alzheimer's disease
Ossenkoppele, R., & Hansson, O. (2021) · Alzheimer's & Dementia · doi:10.1002/alz.12356 · Cited by 62 · see citing works
Harn, N. R., Hunt, S. L., Hill, J., Vidoni, E. D., Perry, M., & Burns, J. M. (2017) · Clinical Nuclear Medicine · doi:10.1097/rlu.0000000000001693 · Cited by 54 · see citing works
Son, H. J., Oh, J. S., Oh, M., Kim, S. J., Lee, J., Roh, J. H., & Kim, J. S. (2019) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-019-04595-y · Cited by 54 · see citing works
Zou, J., Tao, S., Johnson, A., Tomljanovic, Z., Polly, K., Klein, J., Razlighi, Q., Brickman, A., Lee, S., Stern, Y., et al. (2019) · Neurobiology of Aging · doi:10.1016/j.neurobiolaging.2019.09.019 · Cited by 50 · see citing works
Self-citationOcasio, E., & Duong, T. Q. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.560 · Cited by 50 · see citing works
Sex differences in off-target binding using tau positron emission tomography
Smith, R. A., Strandberg, O. T., Leuzy, A., Betthauser, T. J., Johnson, S. C., Pereira, J. B., & Hansson, O. (2021) · NeuroImage Clinical · doi:10.1016/j.nicl.2021.102708 · Cited by 46 · see citing works
Evaluation of a visual interpretation method for tau‐PET with 18 F‐flortaucipir
Sonni, I., Lesman‐Segev, O. H., Baker, S. L., Iaccarino, L., Korman, D., Rabinovici, G. D., Jagust, W. J., Landau, S. M., Joie, R. L., & Initiative, A. D. N. (2020) · Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring · doi:10.1002/dad2.12133 · Cited by 42 · see citing works
On the design of convolutional neural networks for automatic detection of Alzheimer's diseasePreprint
Liu, S., Yadav, C., Fernandez‐Granda, C., & Razavian, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.03740 · Cited by 39 · see citing works
Hammes, J., Bischof, G. N., Bohn, K. P., Onur, O. A., Schneider, A., Fließbach, K., Hoenig, M. C., Jessen, F., Neumaier, B., Drzezga, A. E., et al. (2020) · Journal of Nuclear Medicine · doi:10.2967/jnumed.120.244061 · Cited by 36 · see citing works
What Is T+? A Gordian Knot of Tracers, Thresholds, and Topographies
Villemagne, V. L., Lopresti, B. J., Doré, V., Tudorascu, D., Ikonomović, M. D., Burnham, S. C., Minhas, D. S., Pascoal, T. A., Mason, N. S., Snitz, B. E., et al. (2020) · Journal of Nuclear Medicine · doi:10.2967/jnumed.120.245423 · Cited by 35 · see citing works
Kim, J.-Y., Oh, D., Sung, K., Choi, H., Paeng, J. C., Cheon, G. J., Kang, K. W., Lee, D. Y., & Lee, D. S. (2020) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-020-05044-x · Cited by 33 · see citing works
Tanner, J. A., & Rabinovici, G. D. (2020) · Journal of Nuclear Medicine · doi:10.2967/jnumed.120.257824 · Cited by 33 · see citing works
Improved amyloid burden quantification with nonspecific estimates using deep learning
Liu, H., Nai, Y., Saridin, F. N., Tanaka, T., O’Doherty, J., Hilal, S., Gyanwali, B., Chen, C., Robins, E. G., & Reilhac, A. (2021) · European Journal of Nuclear Medicine and Molecular Imaging · doi:10.1007/s00259-020-05131-z · Cited by 28 · see citing works
Sex Differences in in vivo Alzheimer’s Disease Neuropathology in Late Middle-Aged Hispanics
Luchsinger, J. A., Palta, P., Rippon, B., Soto, L., Ceballos, F., Pardo, M., Laing, K. K., Igwe, K. C., Johnson, A. S., Tomljanovic, Z., et al. (2020) · Journal of Alzheimer s Disease · doi:10.3233/jad-191183 · Cited by 18 · see citing works
Self-citationA Deep Learning Approach to MR-less Spatial Normalization for Tau PET Images
Alvén, J., Heurling, K., Smith, R., Strandberg, O., Schöll, M., Hansson, O., & Kahl, F. (2019) · International Conference on Medical Image Computing and Computer-Assisted Intervention · doi:10.1007/978-3-030-32245-8_40 · Cited by 7 · see citing works
Macdonald, T., Chen, K. T., Koran, M. E. I., Moseley, M. E., & Zaharchuk, G. (2020) · Journal of Nuclear Medicine · Cited by 1 · see citing works
Flagged first, then by citations
1 of the 49 references couldn’t be matched to a known paper.
Research works printed but not linked: 1
- [35]Paszke A, Gross S, Chintala S, Chanan G, Yang E & DeVito Z et al. Automatic differentiation in PyTorch. in NIPS‐W (Long Beach, CA). 2017.
Cited by
Sorted by citations
Ren, F., Wei, J., Chen, Q., Hu, M., Yu, L., Mi, J., Zhou, X., Qin, D., Wu, J., & Wu, A. (2025) · Acta Pharmaceutica Sinica B · doi:10.1016/j.apsb.2025.07.030 · Cited by 97 · see citing works
Multimodal 3D Deep Learning for Early Diagnosis of Alzheimer’s Disease
Kim, S. K., Duong, Q. A., & Gahm, J. K. (2024) · IEEE Access · doi:10.1109/access.2024.3381862 · Cited by 55 · see citing works
Application of Deep Learning for Prediction of Alzheimer’s Disease in PET/MR Imaging
Zhao, Y., Guo, Q., Zhang, Y., Zheng, J., Yang, Y., Du, X., Feng, H., & Zhang, S. (2023) · Bioengineering · doi:10.3390/bioengineering10101120 · Cited by 48 · see citing works
Burnham, S. C., Iaccarino, L., Pontecorvo, M. J., Fleisher, A., Lu, M., Collins, E. C., & Devous, M. D. (2023) · Brain Communications · doi:10.1093/braincomms/fcad305 · Cited by 29 · see citing works
Park, S., Yeo, N. Y., Kim, Y., Byeon, G., & Jang, J. (2023) · Scientific Reports · doi:10.1038/s41598-023-35389-w · Cited by 16 · see citing works
Lu, J., Clement, C., Hong, J., Wang, M., Li, X., Cavinato, L., Yen, T., Jiao, F., Wu, P., Wu, J., et al. (2023) · iScience · doi:10.1016/j.isci.2023.107426 · Cited by 10 · see citing works
Ali, I., & Manda, V. K. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-7858-8.ch006 · Cited by 4 · see citing works
Jann, K., Park, G., Ringman, J. M., & Kim, H. (2025) · Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring · doi:10.1002/dad2.70159 · Cited by 3 · see citing works
Li, Y., Wang, X., Ge, Q., Graeber, M. B., Yan, S., Li, J., Li, S., Gu, W., Hu, S., Benzinger, T. L. S., et al. (2025) · EJNMMI Physics · doi:10.1186/s40658-025-00761-4 · Cited by 3 · see citing works
Sousa, G. J. A., Sá, R. A., Gomes, M. A. S. M., Edwards, G. A., Moreno‐González, I., & de Sousa, R. J. A. (2026) · Neuroinformatics · doi:10.1007/s12021-025-09763-0 · Cited by 2 · see citing works
Tsougos, I., Valotassiou, V. J., Tsivaka, D., Σάτρα, Μ., Angelidis, G., Papatriantafyllou, J. D., Panagiotidis, E., Dardiotis, E., Hadjigeorgiou, G. M., & Georgoulias, P. (2026) · Annals of Nuclear Medicine · doi:10.1007/s12149-026-02194-0 · Cited by 2 · see citing works
Lee, Y., & Liu, H. (2025) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic64266.2025.10920644 · Cited by 2 · see citing works
Gebre, R. K., Moscoso, A., Raghavan, S. K., Wiste, H. J., Sparrman, K. J., Heeman, F., Costoya‐Sánchez, A., Schwarz, C. G., Spychalla, A. J., Lowe, V. J., et al. (2023) · Research Square · doi:10.21203/rs.3.rs-3290598/v1 · Cited by 1 · see citing works
Moradi, S., Simyar, D., & Safari, M. (2023) · Biomedical engineering · doi:10.5772/intechopen.109231
- Authors
- Zou, J., Park, D., Johnson, A., Feng, X., Pardo, M., France, J., Tomljanovic, Z., Brickman, A. M., Devanand, D. P., Luchsinger, J. A., Kreisl, W. C., Provenzano, F. A., & Initiative, F. T. A. D. N.
- Affiliations
- The Taub Institute for Research on Alzheimer's Disease and the Aging Brain New York New York USA
- Columbia University Irving Medical Center (US)
- Columbia University (US)
- Department of Medicine Columbia University Medical Center New York New York USA
- Corresponding author
- Provenzano, Frank A.
- ORCID
- Venue
- Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring
- Publisher
- Wiley
- Published
- 2021-01
- Volume
- 13
- Issue
- 1
- Pages
- e12264-e12264
- ISSN
- 2352-8729 (ISSN-L)
- PMC
- PMC8719427
- OpenAlex
- W4206124362
- Cited by
- 15
- References
- 49
- Citations by year
- 2026: 2 · 2025: 5 · 2024: 1 · 2023: 6 · 2021: 1
- FWCI
- 1.44
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Alzheimer s & Dementia Diagnosis Assessment & Disease Monitoring (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Institutes of Health (R01AG050440, R01 AG055422, RF1AG051556, RF1AG051556‐01S2, R01AG055299, K99AG065506, K24AG045334, UL1TR001873)
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Health Sciences › Medicine › Physiology › Alzheimer's disease research and treatments
- Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Medical Imaging Techniques and Applications
- Keywords
- tau PET, Alzheimer's disease, convolutional neural networks, [18F]MK-6240, early disease detection, attention visualization
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
