Home › Research › Brain scans and imaging
Decoupling Alzheimer Disease Pathologic Abnormalities at PET with Improved Clinical Relevance by Interpretable Adversarial Decomposition Learning
Cheng Tang, Xun Sun, Xun Sun, Anqi Tang, Weiwei Ruan, Hanyi Fang, Hanyi Fang, Yongkang Gai et al.. Radiology, 2026-04-01
Topic: Amyloid, tau and blood-test diagnosis
Background Template-based PET metrics quantify Alzheimer disease (AD) amyloid-β (Aβ) and tau burden but compress whole-brain data into a single scalar, overlooking disease heterogeneity and sometimes causing imaging-clinical discordance. Artificial intelligence (AI) approaches capture richer patterns but often lack biologic interpretability. Purpose To develop and validate an interpretable deep-learning framework that separates AD-specific abnormalities from physiologic uptake using pathophysiologic constraints, generating a clinically meaningful AI biomarker. Materials and Methods In this retrospective study, Aβ and tau PET scans from the Alzheimer's Disease Neuroimaging Initiative, Australian Imaging Biomarkers and Lifestyle study, Global Alzheimer's Association Interactive Network, and the authors' center were analyzed. An adversarial decomposition learning (ADL) network generated voxel-level pathologic maps and an AD adversarial decomposition (ADAD) score. Discriminatory performance for clinical AD versus cognitively normal individuals was evaluated using the area under the curve (AUC). Clinical relevance was assessed with cognitive, hippocampal volume, cerebrospinal fluid (CSF), and neuropathologic measures using longitudinal mixed-effects models and Spearman correlations. Results The study included 7457 Aβ PET scans from 3595 patients (median age, 71.4 years; IQR, 65.7-77.0 years; 1637 female patients) and 1894 tau PET scans from 1127 patients (median age, 72.0 years; IQR, 66.9-78.5 years; 545 female patients). External testing AUCs were 0.94 (95% CI: 0.89, 0.98) for Aβ and 0.98 (95% CI: 0.95, 1.00) for tau. ADL generated interpretable pathologic attribution maps that correlated with expert rankings (Aβ and tau, Spearman ρ = 0.79 and 0.63, respectively). Although Centiloid and CenTauRz showed numerically higher correlations with postmortem neuropathologic structure and stronger associations with CSF biomarkers, the ADAD score demonstrated independent baseline and longitudinal associations with cognitive outcomes and hippocampal atrophy after adjustment. Conclusion Pathophysiologic-constrained ADL provided interpretable, personalized pathologic maps and an AI-derived ADAD score that more closely linked PET pathologic abnormalities with multimodal clinical measures. © RSNA, 2026
Key findings
- Discriminatory performance for clinical AD versus cognitively normal individuals was evaluated using the area under the curve (AUC).
- Results The study included 7457 Aβ PET scans from 3595 patients (median age, 71.4 years; IQR, 65.7-77.0 years; 1637 female patients) and 1894 tau PET scans from 1127 patients (median age, 72.0 years; IQR, 66.9-78.5 years; 545 female patients).
- Although Centiloid and CenTauRz showed numerically higher correlations with postmortem neuropathologic structure and stronger associations with CSF biomarkers, the ADAD score demonstrated independent baseline and longitudinal associations with cognitive outcomes and hippocampal atrophy after adjustment.
Why it matters
This study developed a deep-learning method to separate Alzheimer's-related amyloid and tau abnormalities from normal brain uptake on PET scans, creating a score that may better match clinical findings. It is a diagnostic and monitoring tool and does not test any treatment, cure, or prevention.
New to this subject? Start with our plain-English guide: Brain scans & tests →
Study details
- Study designlongitudinal study
- Participants7,457
- Evidence strengthModerate
How this study scored 53/100
Published in a peer-reviewed journal, and it is a longitudinal study following the same people over time. Scored zero for effect reported and randomised / blinded because the record does not state it. We have no data on senior author's track record, so that was left out: it earned 51 of the 96 points we could judge it on, which is 53 out of 100.
| Component | Points | Why |
|---|---|---|
| Journal tier | 7 / 10 | Tier 3 — peer-reviewed journal (Radiology) |
| Journal's citation record | 3 / 4 | Radiology: journal h-index 431 (OpenAlex, 2026-10-29) |
| Study design | 7 / 12 | A longitudinal study following the same people over time |
| Strength of evidence | 3 / 5 | Rated “moderate” in our summary |
| Peer-review validation | 10 / 10 | Peer-reviewed. Published as an article in a named peer-reviewed journal. |
| How recent | 5 / 5 | 2026 — within 1 year(s) of the newest study here |
| Sample size | 3 / 4 | 7,457 participants |
| Effect reported | 0 / 3 | No effect size reported — scores zero (not stated in the record — scored 0) |
| Studied in people | 3 / 3 | Studied in people (participant count stated) |
| Randomised / blinded | 0 / 2 | No randomisation or blinding stated — scores zero (not stated in the record — scored 0) |
| Times cited | 1 / 7 | Cited 1 times (OpenAlex, 2026-10-10) |
| Citations per year | 0 / 5 | 0.5 citations a year over 2 year(s) since 2026 |
| Impact for its field and year | 3 / 6 | Cited 4.7× the average for papers of its field and year (OpenAlex FWCI) |
| Cited by studies here | 0 / 6 | No other study in this library cites it |
| Still being cited | 0 / 4 | Cited 1 times in 2024–2026 (2026 still in progress; OpenAlex) |
| Senior author's track record | — / 4 | OpenAlex's profile for last-listed author for the Australian Imaging Biomarkers and Lifestyle Flagship Study of Aging Group holds only 1 work(s), too few to judge a track record — left out of this score |
| Institution's track record | 1 / 3 | Huazhong University of Science and Technology: institution h-index 934 (OpenAlex) |
| Multi-centre collaboration | 1 / 3 | OpenAlex lists 2 institution(s) in 1 country |
| Indexed in PubMed | 2 / 2 | Indexed in PubMed (PMID 41944723) |
| Free to read | 2 / 2 | Free to read |
| Points | 51 / 96 | Scored on 19 of 20 parts. We have no data for the rest, so they are left out: 51 of the 96 points we could judge it on is 53 out of 100. |
| Total | 53 / 100 | — |
What each of these 20 components measures, and what this score is not →
Read the original
Full text: free to read — OpenAlex lists this copy as free to read: the link above (checked 6 Feb 1020).
Cite this study APA, Vancouver, BibTeX · download .bib or .ris
Built from the record alzhub holds for this paper, not looked up. Volume, issue and page numbers are not held in the record. The record's author list ends in “et al.”, so not every author is named. Check the citation against the original before you use it.
APA 7th
Tang, C., Sun, X., Tang, A., Ruan, W., Fang, H., Gai, Y., et al. (2026). Decoupling Alzheimer Disease Pathologic Abnormalities at PET with Improved Clinical Relevance by Interpretable Adversarial Decomposition Learning. Radiology. https://doi.org/10.1148/radiol.252321
Vancouver
Tang C, Sun X, Tang A, Ruan W, Fang H, Gai Y, et al. Decoupling Alzheimer Disease Pathologic Abnormalities at PET with Improved Clinical Relevance by Interpretable Adversarial Decomposition Learning. Radiology. 2026. doi:10.1148/radiol.252321. PMID: 41944723.
BibTeX
@article{tang2026-41944723,
author = {Tang, Cheng and Sun, Xun and Tang, Anqi and Ruan, Weiwei and Fang, Hanyi and Gai, Yongkang and others},
title = {{Decoupling Alzheimer Disease Pathologic Abnormalities at PET with Improved Clinical Relevance by Interpretable Adversarial Decomposition Learning}},
journal = {Radiology},
year = {2026},
doi = {10.1148/radiol.252321},
pmid = {41944723},
url = {https://doi.org/10.1148/radiol.252321}
}
Studies this one cites
Referenced by this study and also in the alzhub library, so you can read them here.
Related studies in Brain scans and imaging
Also tagged “classification”
835 studies in the library carry the topic tag “classification”; these are this study's neighbours in a fixed, alphabetical-by-hash tour of them, not the closest in content. All 835 tagged studies.