This study aims to test a new artificial intelligence (AI) method to create brain scan images without needing an extra scan. Currently, patients with memory problems often undergo two types of PET scans (Amyloid PET and FDG PET) to assess Alzheimer's disease. This study will use existing scan data from patients who already had both scans as part of their routine care.

The AI model will try to generate the FDG PET image using only the Amyloid PET scan and an MRI. If successful, this method could reduce radiation exposure, costs, and time for future patients by eliminating the need for a separate FDG injection and scan.

No new scans, injections, or procedures will be performed for this study. All data will be fully anonymized (personal information removed) before analysis. The study involves approximately 35 adult patients (age 50+) whose data were collected between January 2025 and December 2025 at IRCCS Ospedale San Raffaele in Milan, Italy.

This is a retrospective observational study conducted at IRCCS Ospedale San Raffaele, Milan, Italy. The study evaluates the accuracy of synthetic [18F]FDG PET images generated using a SwinUNETR deep learning model compared to native [18F]FDG PET images.

Study Population:

Adults (≥ 50 years) who underwent amyloid PET imaging (using Florbetaben or Flutemetamol), structural MRI, and [18F]FDG PET due to cognitive symptoms between January 2025 and December 2025. Approximately 35 patients meeting inclusion criteria will be included.

Methodology:

All imaging and clinical data were collected as part of routine diagnostic care; thus, no additional procedures, interventions, or interactions with patients are required for this study. All data are fully deidentified before analysis, consistent with GDPR and institutional data protection policy. The SwinUNETR model processes volumetric images to generate synthetic FDG PET images from early-phase amyloid PET and MRI inputs.

Objectives and Endpoints:

Primary Objective: To quantitatively and qualitatively assess the accuracy of synthetic FDG PET images compared with native FDG PET images.

Primary Endpoint: Pearson correlation coefficient and mean absolute error (MAE) of SUVR values obtained from native FDG PET and synthetic FDG PET in Alzheimer relevant areas of interest (precuneus, posterior cingulate, lateral temporal cortex, and frontal cortex).

Secondary Objective: To assess visual interpretability and clinical intuitiveness of synthetic FDG PET images by expert nuclear medicine physicians.

Secondary Endpoint: Inter-rater agreement (Cohen's kappa) among 2 blinded nuclear medicine physicians rating synthetic FDG scans as "clinically acceptable" or not.

Ethical Considerations:

Due to the retrospective and non-interventional nature of this study, no additional informed consent is required. A waiver of informed consent will be requested from the Ethics Committee. The image data will be fully anonymized in accordance with institutional policies.

Inclusion Criteria:

• Age ≥ 50 years at the time of imaging.
• Clinically indicated amyloid PET scan performed with Florbetaben or Flutemetamol between January 1, 2025 and December 31, 2025.
• Availability of paired structural MRI (3D T1-weighted) and real [18F]FDG PET scan acquired within ±6 months of the amyloid PET.
• All three imaging modalities (Amyloid PET, FDG PET, MRI) are of sufficient technical quality for co-registration and quantitative analysis.

Exclusion Criteria:

• Presence of other major neurological disorders that may confound FDG metabolism (e.g., Parkinson's disease, frontotemporal dementia, brain tumor, or recent stroke).
• Severe motion artifacts or technical failures in any of the three imaging modalities that prevent reliable co-registration or SUVR calculation.
• Incomplete or irreversibly corrupted DICOM data preventing anonymization or conversion to analysis-ready format.

Adults (≥50 years) with cognitive symptoms who underwent amyloid PET imaging (Florbetaben or Flutemetamol), structural MRI, and [18F]FDG PET at the Nuclear Medicine Department of IRCCS Ospedale San Raffaele, Milan, Italy, as part of routine diagnostic care between January 1, 2025 and December 31, 2025.

It is not yet decided whether individual participant data will be shared. The research team will consider data sharing requests on a case-by-case basis, subject to institutional approval and data use agreements. Anonymized imaging data (NIfTI format) and analysis scripts may be made available upon reasonable request to the Principal Investigator.