Making PET-like images from CT to improve lung cancer diagnosis and care
Synthetic PET From CT Improves Precision Diagnosis and Treatment of Lung Cancer: a Prospective, Observational, Multicenter Study
This project will test whether PET-like images generated from routine diagnostic CT scans can help doctors diagnose, stage, and plan treatment for people with non-small cell lung cancer who are having PET-CT and pathology tests.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 10000 (estimated) |
| Ages | 18 Years to 85 Years |
| Sex | All |
| Sponsor | Shanghai Pulmonary Hospital, Shanghai, China Academic / other |
| Locations | 5 sites (Zunyi, Guizhou and 4 other locations) |
| Trial ID | NCT07243873 on ClinicalTrials.gov |
What this trial studies
This prospective, observational multicenter effort develops a method to synthesize FDG-PET–style images from diagnostic CT by learning an anatomical-to-metabolic mapping from paired CT and PET scans. The model is trained on paired diagnostic CT and FDG-PET images and then applied prospectively to patients with non-small cell lung cancer undergoing standard PET-CT and pathological workup. Investigators will compare synthetic PET outputs with real FDG-PET images and with pathology and clinical outcomes to test whether the synthetic images add diagnostic or prognostic value. Because the design is observational, patients receive standard clinical care while the study focuses on image generation and predictive performance across participating hospitals.
Who should consider this trial
Good fit: Adults with suspected or confirmed non-small cell lung cancer who are scheduled for FDG-PET-CT and pathological examination and can give informed consent are the intended participants.
Not a fit: Patients without paired CT and FDG-PET scans, those with significant imaging artifacts, or patients with a history of other malignancies are unlikely to benefit from the model.
Why it matters
Potential benefit: If successful, this approach could provide PET-like metabolic information from routine CT scans, potentially reducing the need for separate PET exams, shortening time to diagnosis, and improving treatment planning.
How similar studies have performed: Previous retrospective and single-center studies of AI-generated synthetic PET from CT have shown promising accuracy in pilot datasets, but large prospective multicenter clinical validation remains limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: 1. Patients with non-small cell lung cancer scheduled to undergo PET-CT and pathological examinations; 2. Voluntarily participate and sign an informed consent form; Exclusion Criteria: 1. History of other malignant tumours; 2. Image artefacts; 3. Without pathological diagnostic information; 4. Without paired CT and FDG-PET scan images.
Where this trial is running
Zunyi, Guizhou and 4 other locations
- Affiliated Hospital of Zunyi Medical University — Zunyi, Guizhou, China (Recruiting)
- The First Affiliated Hospital of Nanchang University — Jiangxi, Nanchang, China (Recruiting)
- Shanghai East Hospital — Shanghai, Shanghai Municipality, China (Recruiting)
- Shanghai Pulmonary Hospital — Shanghai, Shanghai Municipality, China (Recruiting)
- Ningbo No.2 Hospital — Ningbo, Zhejiang, China (Recruiting)
Study contacts
- Study coordinator: Xinchen Shen
- Email: shenxinchen9@163.com
- Phone: 17366690957
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.