Using AI to create synthetic PET images for diagnosing Alzheimer's disease

Modelling Tau Deposition and Distribution From Diffusion Tensor Imaging With Generative Adversarial Network for Alzheimer's Disease Diagnosis

Observational Chinese University of Hong Kong · NCT05020626

This study is testing a new way to use AI to create brain images that can help doctors diagnose Alzheimer's disease without the need for expensive scans.

Quick facts

Study typeObservational
Enrollment250 (estimated)
Ages55 Years and up
SexAll
SponsorChinese University of Hong Kong Academic / other
Drugs / interventionsradiation
Locations1 site (Hong Kong, Shatin)
Trial IDNCT05020626 on ClinicalTrials.gov

What this trial studies

This project aims to develop a novel generative adversarial network (GAN) that can automatically generate synthetic PET images reflecting tau deposition from brain diffusion tensor imaging (DTI) data. By simulating the pattern of tau accumulation in the brain, this approach seeks to provide a non-invasive, cost-effective alternative to traditional PET imaging for Alzheimer's disease diagnosis. The framework is designed to enhance accessibility and generalizability in clinical settings, potentially transforming how tau pathology is assessed in patients. If successful, it could lead to a significant advancement in the early detection and diagnosis of Alzheimer's disease.

Who should consider this trial

Good fit: Ideal candidates for this study are individuals aged 55 and above with a clinically confirmed diagnosis of Alzheimer's disease, mild cognitive impairment, or normal cognition.

Not a fit: Patients with mixed dementia, non-Alzheimer's dementia, or a history of severe brain injuries or illnesses may not benefit from this study.

Why it matters

Potential benefit: If successful, this approach could provide a more accessible and non-invasive method for diagnosing Alzheimer's disease, improving patient outcomes.

How similar studies have performed: While this approach is innovative, similar studies using AI for imaging in Alzheimer's diagnosis have shown promise, indicating potential for success.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

* With the age of 55 years and above
* With brain MRI taken within ±6 months from the date of clinically confirmed diagnosis of AD, MCI or normal cognition.

Exclusion Criteria:

* AD with mixed dementia
* Non-AD dementia
* History of severe traumatic brain injury, severe depression, stroke, brain tumors, and incident major systemic illness

Where this trial is running

Hong Kong, Shatin

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Alzheimer's Disease DiagnosisGenerative Adversarial NetworkTauDiffusion Tensor Imaging
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.