A Hierarchical Multi-modal AI Framework for Pathological and Genetic Subtyping of Lung Cancer Based on PET/CT Imaging

Plain-language summary

This study examines a multimodal artificial intelligence framework that uses PET/CT images to help identify the pathological and genetic subtypes of lung cancer. Patients aged 18 and older with newly diagnosed, pathologically confirmed non-small cell lung cancer (NSCLC) who had a pre-treatment 18F-FDG PET/CT scan and no history of other cancers can take part. It is a study with no assigned phase and is currently recruiting participants.

The summary above is a plain-language rendering of the official record. The original English title is shown for reference.

Trial details

Phase

N/A

Status

Recruiting

Sponsor

Second Affiliated Hospital, School of Medicine, Zhejiang University

Intervention

PET imaging analysis, data mining, and AI model developing

Start date

8/1/2024

Estimated completion

8/1/2027

Countries

China

Related genes

Locations

• Guangzhou, China
• Wuhan, China
• Wuhan, China
• Yangzhou, China
• Shenyang, China
• Chengdu, China
• Hangzhou, China
• Hangzhou, China
• Hangzhou, China

Eligibility criteria

Criteria are reproduced from the ClinicalTrials.gov record in the original English. Only the trial team can determine eligibility.

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