Novel Non-Invasive Radiomic Signature on CT Scans Predicts Response to Platinum-Based Chemotherapy and Is Prognostic of Overall Survival in Small Cell Lung Cancer

BACKGROUND: Small cell lung cancer (SCLC) is an aggressive malignancy characterized by initial chemosensitivity followed by resistance and rapid progression. Presently, there are no predictive biomarkers that can accurately guide the use of systemic therapy in SCLC patients. This study explores the role of radiomic features from both within and around the tumor lesion on pretreatment CT scans to a) prognosticate overall survival (OS) and b) predict response to chemotherapy. METHODS: One hundred fifty-three SCLC patients who had received chemotherapy were included. Lung tumors were contoured by an expert reader. The patients were divided randomly into approximately equally sized training (S(tr) = 77) and test sets (S(te) = 76). Textural descriptors were extracted from the nodule (intratumoral) and parenchymal regions surrounding the nodule (peritumoral). The clinical endpoints of this study were OS, progression-free survival (PFS), and best objective response to chemotherapy. Patients with complete or partial response were defined as “responders,” and those with stable or progression of disease were defined as “non-responders.” The radiomic risk score (RRS) was generated by using the least absolute shrinkage and selection operator (LASSO) with the Cox regression model. Patients were classified into the high-risk or low-risk groups based on the median of RRS. Association of the radiomic signature with OS was evaluated on S(tr) and then tested on S(te). The features identified by LASSO were then used to train a linear discriminant analysis (LDA) classifier (M(Rad)) to predict response to chemotherapy. A prognostic nomogram (N(Rad+Clin)) was also developed on S(tr) by combining clinical and prognostic radiomic features and validated on S(te). The Kaplan–Meier survival analysis and log-rank statistical tests were performed to assess the discriminative ability of the features. The discrimination performance of the N(Rad+Clin) was assessed by Harrell’s C-index. To estimate the clinical utility of the nomogram, decision curve analysis (DCA) was performed by calculating the net benefits for a range of threshold probabilities in predicting which high-risk patients should receive more aggressive treatment as compared with the low-risk patients. RESULTS: A univariable Cox regression analysis indicated that RRS was significantly associated with OS in S(tr) (HR: 1.53; 95% CI, [1.1–2.2; p = 0.021]; C-index = 0.72) and S(te) (HR: 1.4, [1.1–1.82], p = 0.0127; C-index = 0.69). The RRS was also significantly associated with PFS in S(tr) (HR: 1.89, [1.4–4.61], p = 0.047; C-index = 0.7) and S(te) (HR: 1.641, [1.1–2.77], p = 0.04; C-index = 0.67). M(Rad) was able to predict response to chemotherapy with an area under the receiver operating characteristic curve (AUC) of 0.76 ± 0.03 within S(tr) and 0.72 within S(te). Predictors, including the RRS, gender, age, stage, and smoking status, were used in the prognostic nomogram. The discrimination ability of the N(Rad+Clin) model on S(tr) and S(te) was C-index [95% CI]: 0.68 [0.66–0.71] and 0.67 [0.63–0.69], respectively. DCA indicated that the N(Rad+Clin) model was clinically useful. CONCLUSIONS: Radiomic features extracted within and around the lung tumor on CT images were both prognostic of OS and predictive of response to chemotherapy in SCLC patients.