Nomogram Based on Clinical and Radiomics Data for Predicting Radiation-induced Temporal Lobe Injury in Patients with Non-metastatic Stage T4 Nasopharyngeal Carcinoma

• Published in: Clinical oncology (Royal College of Radiologists (Great Britain)) 2022-12, Vol.34 (12), p.e482-e492
• Main Authors: Bin, X., Zhu, C., Tang, Y., Li, R., Ding, Q., Xia, W., Tang, X., Yao, D., Tang, A.
• Format: Article
• Language: English
• Subjects: Humans; Magnetic Resonance Imaging - methods; MRI-based radiomics; Nasopharyngeal Carcinoma - radiotherapy; Nasopharyngeal Neoplasms - diagnostic imaging; Nasopharyngeal Neoplasms - drug therapy; Nasopharyngeal Neoplasms - radiotherapy; nomogram; Nomograms; Radiation Injuries - diagnostic imaging; Radiation Injuries - etiology; Retrospective Studies; T4/N0-3/M0 nasopharyngeal carcinoma; Temporal Lobe; temporal lobe injury
• ISSN: 0936-6555; 1433-2981
• DOI: 10.1016/j.clon.2022.07.007

To use pre-treatment magnetic resonance imaging-based radiomics data with clinical data to predict radiation-induced temporal lobe injury (RTLI) in nasopharyngeal carcinoma (NPC) patients with stage T4/N0–3/M0 within 5 years after radiotherapy. This study retrospectively examined 98 patients (198 temporal lobes) with stage T4/N0–3/M0 NPC. Participants were enrolled into a training cohort or a validation cohort in a ratio of 7:3. Radiomics features were extracted from pre-treatment magnetic resonance imaging that were T1-and T2-weighted. Spearman rank correlation, the t-test and the least absolute shrinkage and selection operator (LASSO) algorithm were used to select significant radiomics features; machine-learning models were used to generate radiomics signatures (Rad-Scores). Rad-Scores and clinical factors were integrated into a nomogram for prediction of RTLI. Nomogram discrimination was evaluated using receiver operating characteristic analysis and clinical benefits were evaluated using decision curve analysis. Participants were enrolled into a training cohort (n = 139) or a validation cohort (n = 59). In total, 3568 radiomics features were initially extracted from T1-and T2-weighted images. Age, Dmax, D1cc and 16 stable radiomics features (six from T1-weighted and 10 from T2-weighted images) were identified as independent predictive factors. A greater Rad-Score was associated with a greater risk of RTLI. The nomogram showed good discrimination, with a C-index of 0.85 (95% confidence interval 0.79–0.92) in the training cohort and 0.82 (95% confidence interval 0.71–0.92) in the validation cohort. We developed models for the prediction of RTLI in patients with stage T4/N0–3/M0 NPC using pre-treatment radiomics data and clinical data. Nomograms from these pre-treatment data improved the prediction of RTLI. These results may allow the selection of patients for earlier clinical interventions. •Interdisciplinary study that used pre-treatment MRI-based radiomics data for RTLI prediction in NPC patients.•Only included patients with stage T4/N0-3/M0 NPC, making the study more targeted.•Provide reliable risk stratification of RTLI by using non-invasive radiomics and clinical data.•Radiomics information was extracted from the routine MRI examinations without increasing healthcare costs.