International Journal of Radiation Research

en A prognostic model based on computed tomography radiomics to evaluate response of immunotherapy in non-small cell lung cancer using clinical data Radiation Biology Radiation Biology تحقيق بديع Original Research <div style="text-align: justify;">Background: This study aimed to develop and validate a computed tomography (CT) radiomics–based model for predicting immunotherapy response and prognosis in patients with advanced non-small cell lung cancer (NSCLC). Materials and Methods: A total of 117 patients with advanced NSCLC treated with PD-1/PD-L1 immune checkpoint inhibitors were retrospectively enrolled from two centers. Baseline CT scans obtained before immunotherapy and follow-up CT scans acquired 6–8 weeks after treatment initiation were analyzed. Tumor lesions were manually segmented, and radiomics features were extracted. Two support vector machine–based models were constructed: a pre-treatment CT (pre-CT) model and a delta-CT model derived from changes in radiomics features before and after immunotherapy. Model performance for predicting immunotherapy response, defined according to RECIST 1.1 criteria, was evaluated using receiver operating characteristic (ROC) analysis. Kaplan–Meier survival analysis was performed to assess the prognostic value of radiomics scores. Results: In the training cohort, the pre-CT and delta-CT models achieved area under the ROC curve (AUC) values of 0.825 and 0.844, respectively. In the validation cohort, the delta-CT model demonstrated superior predictive performance (AUC: 0.795) compared with the pre-CT model (AUC: 0.686). Subgroup analysis showed that the delta-CT model performed well in adenocarcinoma patients, whereas the pre-CT model showed better discrimination in squamous cell carcinoma patients. Higher delta-CT radiomics scores were significantly associated with poorer OS and PFS. Conclusion: CT radiomics models, particularly those based on longitudinal changes after immunotherapy, can effectively predict immunotherapy response and prognosis in advanced NSCLC, providing a non-invasive tool to support clinical decision-making.</div> Non-small-cell lung cancer, immunotherapy, CT radiomics, therapeutic effect, prognosis. 577 584 http://ijrr.com/browse.php?a_code=A-10-1-1542&slc_lang=en&sid=1 D. Wang 7900319475328460034076 7900319475328460034076 No Department of Thoracic Surgery, Shanghai Pudong Hospital, Fudan University Pudong Medical Center, Shanghai, 200000, China X. Wang 7900319475328460034077 7900319475328460034077 No Department of Thoracic Surgery, Shanghai Pudong Hospital, Fudan University Pudong Medical Center, Shanghai, 200000, China Z. Wang 7900319475328460034078 7900319475328460034078 No Medical Imaging Center, Hefei First People's Hospital, The Third Affliated Hospital of Anhui Medical University, Hefei, Anhui, 230000, China Y. Xu xyd927927@163.com 7900319475328460034079 7900319475328460034079 Yes Department of Thoracic Surgery, Shanghai Pudong Hospital, Fudan University Pudong Medical Center, Shanghai, 200000, China