Extended application of a CT-based artificial intelligence prognostication model in patients with primary lung cancer undergoing stereotactic ablative radiotherapy

Authors
Hyungjin Kim, Joo Ho Lee, Hak Jae Kim, Chang Min Park, Hong-Gyun Wu, Jin Mo Goo
Journal
Radiotherapy and Oncology
Related Product

Research

Date Published
2021.11
Summary

This study aimed to validate a CT-based deep learning prognostication model, initially developed for surgical patients, in those with primary lung cancer undergoing stereotactic ablative radiotherapy (SABR). Utilizing SABR-planning CT images imported into the Aview software (Coreline Soft, Seoul, Korea), the retrospective study included 135 patients with clinical stage T1-2N0M0 lung cancer treated between 2013 and 2018. Key outcomes were local recurrence-free survival (LRFS), disease-free survival (DFS), and overall survival (OS). Model performance, assessed via time-dependent ROC curve analysis, yielded AUCs of 0.72 for LRFS, 0.70 for DFS, and 0.66 for OS. Multivariable Cox regression demonstrated significant associations between model output and LRFS (HR 1.043), DFS (HR 1.03), and OS (HR 1.025). The findings support the external validity and transportability of the CT-based deep learning model for predicting outcomes in SABR-treated lung cancer patients.

Contact

Please leave your inquiry if you have any questions regarding our products, recruitment, investment, or any other matters.

Contact us