Deep learning model for pathological invasiveness prediction using smartphone-based surgical resection images in clinical stage IA lung adenocarcinoma (SuRImage): a prospective, multicentric, diagnostic study

Key Points

• The central aim focuses on predicting pathological invasiveness in clinical stage IA lung adenocarcinoma using a deep learning model developed from smartphone images.
• Utilized smartphone-based surgical resection images for analysis
• Developed a deep learning model
• Conducted a prospective, multicentric study to validate the model
• The model shows potential for accurately predicting invasiveness in lung adenocarcinoma
• Demonstrated feasibility of using smartphone images for clinical assessments