Nonsmall cell lung cancer (NSCLC) remains the leading cause of cancer-related deaths. With the development of screening, patient selection, and treatment strategies, patients’ survival outcomes and living quality significantly improved. However, some patients still have local recurrence or residual tumors after receiving definitive therapies. Salvage surgery has been regarded as an effective option for recurrent or residual NSCLC, but its effectiveness remains undetermined. Furthermore, conversion surgery is a special type of salvage surgery for tumors converted from ‘initially unresectable’ to ‘potentially resectable’ status due to a favorable response to systemic treatments. Although conversion surgery is a promising curative procedure for advanced NSCLC, its concept and clinical value remain unfamiliar to clinicians. In this narrative review, we provided an overview of the safety and efficacy of salvage surgery, especially salvage surgery after sublobar resection in early-stage NSCLC. More importantly, we highlighted the concept and value of conversion surgery after systemic treatment in advanced NSCLC to gain some insights into its role in the treatment of lung cancer.

This study aimed to develop and validate machine learning (ML) models to predict survival following oesophagectomy in oesophageal squamous cell carcinoma (ESCC) patients using intratumoral and peritumoral radiomic features. A retrospective analysis was conducted on ESCC patients with preoperative contrast-enhanced computed tomography who underwent oesophagectomy from June 2016 to January 2020. Patients were randomly assigned to training and test sets (8:2 ratio). Radiomic features were independently extracted from intratumoral and peritumoral regions. Cox regression, random survival forests (RSF), and gradient boosting decision tree (GBDT) were used for modelling. The performance of models was evaluated by discrimination and calibration. The study included 443 patients, 354 in the training set and 89 in the test set. Peritumoral radiomic features predominated in the final selection, with 14 of 17 selected features originating from peritumoral region. The optimal GBDT model (iAUC: 0.854; iBS: 0.160) using dual-region radiomic and clinical features outperformed other models, with a 1-year tAUC of 0.712 (95% CI 0.655–0.738) and 3-year tAUC of 0.733 (95% CI 0.655–0.805). It effectively stratified patients into high- and low-risk groups (P < 0.001). ML models using intratumoral and peritumoral radiomic features showed potential for predicting postoperative survival in ESCC patients, with the optimal GBDT model demonstrating effective risk stratification.