About this trial
The goal of this observational study is to determine the most accurate tumor size measurement method for T-staging and prognostic assessment in lung cancer with cystic airspaces (LCCA). The main questions it aims to answer are:
* What is the optimal T-staging approach for accurately classifying lung cancer with cystic airspaces (LCCA) and predicting patient outcomes? * How do imaging features of cystic lesions correlate with their pathological characteristics? * What is the relationship between imaging features of cystic airspace-associated lesions and patient prognosis? * Can optimizing the T-staging method improve clinical decision-making in patients with LCCA?
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Histologically confirmed non-small cell lung cancer (NSCLC), as verified by biopsy or postoperative pathological examination;
Patients who have undergone surgical lung resection;
Patients with complete preoperative chest CT imaging data;
Preoperative chest CT showing a well-defined gas-containing (air-filled) cystic component within the tumor.
Disqualifiers
History of pulmonary diseases that could produce cystic lung lesions (e.g., tuberculosis, pulmonary fungal infections, bullae, emphysema, Lymphangioleiomyomatosis [LAM], or Birt-Hogg-Dubé [BHD] syndrome);
Systemic anti-tumor therapies, including chemotherapy, radiotherapy, or targeted therapies (such as monoclonal antibodies, small-molecule tyrosine kinase inhibitors, among others), were administered prior to enrollment;
Patients with concurrent other malignancies;
Patients with missing or poor-quality preoperative chest CT imaging data.
Trial population
Patients with LCCA who underwent surgical treatment in the Second Xiangya Hospital of Central South University
Trial design
Cohort
Prospective
Treatments tested in this trial
Not listed
Trial groups
Trial outcomes
Primary outcomes
DFS
Disease-Free Survival
OS
Overall Survival
Secondary outcomes
Rate of T-stage reclassification
T-stage reclassification
AI-based extraction of radiologic characteristics of cystic airspace-associated lesions
Machine learning was employed to extract and analyze the radiologic characteristics of cystic airspace-associated lesions.
AI to extract and analyze pathological features
Machine learning was employed to extract and analyze pathological features
Oncogenic driver genetic alterations
Results of driver gene mutation testing
Sponsors and contacts
Click on the lead sponsor to view all of their trials.
Central South University
Lead sponsor
Second Xiangya Hospital of Central South University
Sponsor institution