AI-guided PET/CT method to identify lung cancer subtype and EGFR mutation status
A Hierarchical Multi-modal AI Framework for Pathological and Genetic Subtyping of Lung Cancer Based on PET/CT Imaging
This project uses PET/CT scans and clinical information to try to identify lung cancer subtypes and whether the EGFR gene is mutated in adults with newly diagnosed lung cancer.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 5500 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Second Affiliated Hospital, School of Medicine, Zhejiang University Academic / other |
| Locations | 9 sites (Guangzhou, Guangdong and 8 other locations) |
| Trial ID | NCT07463300 on ClinicalTrials.gov |
What this trial studies
Researchers combine 18F-FDG PET/CT imaging with clinical data (age, sex, smoking and family history, tumor biomarkers, etc.) to build a hierarchical multi-modal AI framework. The system is designed to operate in three levels: separate small cell from non-small cell lung cancer, subtype non-small cell cases into adenocarcinoma, squamous, or other, and predict EGFR driver-gene mutation status. The model is trained and tuned on retrospective training and validation sets, tested on a retrospective test set, and further evaluated in a prospective cohort. Data are collected and modeled across multiple hospital sites to support external validation and generalizability.
Who should consider this trial
Good fit: Adults (age ≥18) with newly diagnosed non-small cell lung cancer who have a pre-treatment 18F-FDG PET/CT scan, have received no prior anti-tumor treatment, and have no history of other malignancies.
Not a fit: Patients with pure ground-glass nodules lacking FDG uptake, those who have already begun cancer treatment, or those with prior other malignancies are unlikely to be eligible or to benefit.
Why it matters
Potential benefit: If successful, this approach could provide faster, noninvasive subtype and EGFR mutation information to help guide treatment decisions and potentially reduce the need for additional invasive testing.
How similar studies have performed: Previous single-center studies using PET/CT and AI have shown promising results for subtype classification and EGFR prediction, but a hierarchical multi-modal, multi-center approach is relatively novel.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Newly diagnosed NSCLC confirmed pathologically * Age ≥18 y * Underwent pre-treatment 18F-FDG PET/CT scan * No prior anti-tumor treatments * No history of other malignancies Exclusion Criteria: ▪ Pure ground-glass nodules with no FDG uptake
Where this trial is running
Guangzhou, Guangdong and 8 other locations
- Guangdong Second Provincial General Hospital — Guangzhou, Guangdong, China (Recruiting)
- Wuhan Tongji Hospital — Wuhan, Hubei, China (Recruiting)
- Zhongnan Hospital — Wuhan, Hubei, China (Recruiting)
- Northern Jiangsu People's Hospital — Yangzhou, Jiangsu, China (Recruiting)
- First Hospital of China Medical University — Shenyang, Liaoning, China (Recruiting)
- West China Hospital — Chengdu, Sichuan, China (Recruiting)
- The First Affiliated Hospital of Zhejiang Chinese Medical University — Hangzhou, Zhejiang, China (Recruiting)
- Department of Nuclear Medicine and PET/CT Center, The Second Affiliated Hospital, School of Medicine, Zhejiang University — Hangzhou, Zhejiang, China (Recruiting)
- Zhejiang Cancer Hospital — Hangzhou, Zhejiang, China (Recruiting)
Study contacts
- Principal investigator: Hong Zhang — Department of Nuclear Medicine and PET/CT Center, The Second Affiliated Hospital, School of Medicine, Zhejiang University
- Study coordinator: Hong Zhang
- Email: hzhang21@zju.edu.cn
- Phone: 0086-571-87767138
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.