Deep learning to estimate response of concurrent chemoradiotherapy in non-small-cell lung carcinoma

Abstract

Background Concurrent chemoradiotherapy (CCRT) is a crucial treatment for non-small cell lung carcinoma (NSCLC). However, the use of deep learning (DL) models for predicting the response to CCRT in NSCLC remains unexplored. Therefore, we constructed a DL model for estimating the response to CCRT in NSCLC and explored the associated biological signaling pathways. Methods Overall, 229 patients with NSCLC were recruited from six hospitals. Based on contrast-enhanced computed tomography (CT) images, a three-dimensional ResNet50 algorithm was used to develop a model and validate the performance in predicting response and prognosis. An associated analysis was conducted on CT image visualization, RNA sequencing, and single-cell sequencing. Results The DL model exhibited favorable predictive performance, with an area under the curve of 0·86 (95% confidence interval [CI]: 0·79–0·92) in the training cohort and 0·84 (95% CI: 0·75–0·94) in the validation cohort. The DL model (low score vs. high score) was an independent predictive factor; it was significantly associated with progression-free survival and overall survival in both the training (hazard ratio [HR] = 0·54 [0·36−0·80], P = 0·002; 0·44 [0·28−0·68], P < 0·001) and validation cohorts (HR = 0·46 [0·24−0·88], P = 0·008; 0·30 [0·14−0·60], P < 0·001). Also, it was positively related to the pathways involved in cell adhesion molecules, the P53 signaling pathway, and natural killer cell-mediated cytotoxicity. Single-cell analysis revealed that differentially expressed genes were enriched in different immune cells. Conclusion The DL model demonstrated a strong predictive ability for determining the response in patients with NSCLC undergoing CCRT; our findings contribute to understanding the potential biological mechanisms.