AI-guided PET/CT method to identify lung cancer subtype and EGFR mutation status
Official title: A Hierarchical Multi-modal AI Framework for Pathological and Genetic Subtyping of Lung Cancer Based on PET/CT Imaging
Run by Second Affiliated Hospital, Zhejiang University, School of Medicine · NCT07463300 · Data updated 2026-11-12
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 |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 5500 (estimated) |
| Sponsor | Second Affiliated Hospital, Zhejiang University, School of Medicine Academic / other |
| Locations | 9 sites (Guangzhou, Guangdong and 8 other locations) |
| Status | Recruiting |
| Started | August 1, 2024 |
| Main results expected | August 1, 2027 |
| Study ends | August 1, 2027 |
| Registry record updated | March 11, 2026 |
| Trial ID | NCT07463300 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a 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.
✕Probably 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.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
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.
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 gone: 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.
Who can join: the full rules
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 it's running
-
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
Show 3 more locations
-
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
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
ePRO in advanced lung cancer: emotional distress, brain metastasis, and symptom burden
This study tests how patients with advanced lung cancer—some with brain metastases—report emotional distress and symptoms over time using electronic questionnaires.
-
Urine VOC Test to Detect Lung Cancer in Never Smokers
A urine test that looks for volatile compounds is tested to see if it can help detect lung cancer in adults who have never smoked.
-
SI-B036 safety test in advanced and metastatic solid tumors
This early-phase study checks whether SI-B036 is safe and tolerable in adults with advanced or metastatic solid cancers who have had prior therapy.
-
Guaraná Supplement for Cancer-Related Fatigue in People Undergoing Treatment
This study tests whether taking guaraná capsules helps reduce cancer-related fatigue and improve quality of life in adults with breast, lung, colorectal, or gastric cancer who are actively receiving treatment.
-
ENPP1/cGAS and FAP in Solid Tumors in Vietnamese Patients
This Vietnam-based study will test ENPP1, cGAS, and FAP expression in archived tumor samples from Vietnamese adults with solid cancers using immunohistochemistry.
-
Olive oil before lung cancer surgery to see if it lowers chylothorax
This study tests whether drinking 40 mL of extra-virgin olive oil a few hours before lung cancer surgery can reduce chylothorax after tumor removal.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.