A Self-Supervised Foundation Model Based on Three-Dimensional Chest CT Scans for Lung Cancer Diagnosis and Prognosis Prediction
Abstract
The self-supervised Unified CT-Based Lung Cancer Imaging Foundation model, trained on 33 901 chest scans, surpassed state-of-the-art algorithms in predicting lung cancer histologic subtype, stage, survival, and recurrence while reducing annotation demands.
Fields of Study & Subjects
Lung Cancer Diagnosis and Treatment
Radiomics and Machine Learning in Medical Imaging
AI in cancer detection
Publication details
- Journal / source
- Radiology Imaging Cancer
- Publisher
- Radiological Society of North America (RSNA)
- Volume
- 8
- Issue
- 2
- Pages
- e250360–e250360
- Publication date
- 20 February 2026
- Language
- EN