AI model using CT scans to predict high-risk lung cancer linked to cystic airspaces
Builds an AI model to predict high-risk features in lung cancer before surgery.
Plain-language title generated from the registry record
Registry title: Multimodal AI Predicts High-risk Pathology in Lung Cancer Associated With Cystic Airspaces
Key facts
- Where
- Changsha, ChinaSee the site
AI summary: who the study is looking for
From the trial's eligibility criteria. Machine-read from the registry text on this page, so it can be wrong. The registry text below and the trial team decide who can take part.
The trial is looking for adults with non-small cell lung cancer that has an air-filled cyst inside the tumour on a chest CT scan, who had the tumour removed by surgery.
- Age
- 18 years or older
- Sex
- All sexes
- Disease stage
- Non-small cell lung cancer (NSCLC) confirmed by biopsy or by pathology after surgery, with a clear air-filled cystic part inside the tumour on the chest CT before surgery (lung cancer associated with cystic airspaces).
- Earlier treatment
- Had surgery to remove the lung tumour (lobectomy, segmentectomy or wedge resection). Cannot have had drug treatment for the cancer, radiotherapy, targeted therapy or immunotherapy before joining.
Main reasons for not taking part
- Past lung disease that can cause cysts in the lung, such as tuberculosis, lung fungal infection, lymphangioleiomyomatosis (LAM) or Birt-Hogg-Dubé (BHD) syndrome
- Severe emphysema that makes the tumour hard to see or measure on the CT
- Another primary cancer
- Missing or poor-quality chest CT images before surgery
- Missing or incomplete pathology results or clinical data
Read by machine on 12 November 2026.
Where in China
- The Second Xiangya Hospital of Central South UniversityChangsha, ChinaContact: Xue HeTaking people
Questions to ask the study team
- How often do I need to come in, and for how long each time?
- Are travel costs paid?
- Can I keep my own doctor?
- What happens if I want to stop?
Contact the study team: see the registry record → Contacts and Locations
Print a page for my doctorTrial details
- Who runs it
- Central South University
- Trial code
- NCT07820423
- Record updated
- 15 September 2026
- Original description
The goal of this observational study is to develop and validate an artificial intelligence (AI)-based multimodal radiomics model that integrates preoperative CT imaging features and clinical data to predict pathological high-risk features in patients with lung cancer associated with cystic airspaces (LCCA).Read full original descriptionShow less
Interpretable Multimodal Artificial Intelligence Predicts High-risk Pathology in Lung Cancer Associated With Cystic Airspaces
The goal of this observational study is to develop and validate an artificial intelligence (AI)-based multimodal radiomics model that integrates preoperative CT imaging features and clinical data to predict pathological high-risk features in patients with lung cancer associated with cystic airspaces (LCCA).
The main questions it aims to answer are:
Can an AI-based multimodal radiomics model accurately predict pathological high-risk features in LCCA before surgery? Does the integration of CT imaging features and clinical variables improve preoperative risk stratification compared with imaging or clinical information alone?
Inclusion: 1. Patients with non-small cell lung cancer (NSCLC) confirmed by biopsy or postoperative pathological examination; Patients who underwent surgical resection of a pulmonary tumor, including lobectomy, segmentectomy, or wedge resection; Patients with complete preoperative chest CT imaging data. 4. Patients whose preoperative chest CT showed a well-defined air-containing cystic component within the tumor, consistent with the radiological features of lung cancer associated with cystic airspaces (LCCA); Patients with available clinical and pathological data required for analysis.
Exclusion: 1. Patients with a history of pulmonary diseases that may cause cystic lung lesions, such as pulmonary tuberculosis, pulmonary fungal infection, lymphangioleiomyomatosis (LAM), or Birt-Hogg-Dubé (BHD) syndrome. Emphysema will not be considered an exclusion criterion; however, patients with severe emphysema will be excluded if it significantly affects the identification, boundary delineation, or imaging feature assessment of the target lesion; Patients who received systemic antitumor therapy before enrollment, including chemotherapy, radiotherapy, targeted therapy, or immunotherapy; Patients with other primary malignancies. 4. Patients with missing preoperative chest CT images or CT images of insufficient quality for analysis; Patients without a definite pathological diagnosis or with incomplete pathological results; Patients with missing clinical data.