Combination of quantitative features from H&E biopsies and CT scans predicts response to chemotherapy and overall survival in small cell lung cancer (SCLC).

8572 Background: Small Cell Lung Cancer (SCLC) is an aggressive malignancy with a rapid growth, and Chemotherapy remains mainstay of treatment. Identifying therapeutic targets in SCLC presents a challenge, partially due to a lack of accurate and consistently predictive biomarkers. In this study we sought to evaluate the utility of a combination of computer-extracted radiographic and pathology features from pretreatment baseline CT and H&E biopsy images to predict sensitivity to platinum-based chemotherapy and overall survival (OS) in SCLC. Methods: Seventy-eight patients with extensive and limited-stage SCLC who received platinum-doublet chemotherapy were selected. Objective response to chemotherapy (RECIST criteria) and overall survival (OS) as clinical endpoints were available for 51 and 78 patients respectively. The patients were divided randomly into two sets (Training (Sd), Validation (Sv)) with a constraint (equal number of responders and nonresponders in Sd)—Sd comprised twenty-one patients with SCLC. Sv included thirty patients. CT scans and digitized Hematoxylin Eosin-stained (H&E) biopsy images were acquired for each patient. A set of CT derived (46%) and tissue derived (53%) image features were captured. These included shape and textural patterns of the tumoral and peritumoral regions from CT scans and of tumor regions on H&E images. A random forest feature selection and linear regression model were used to identify the most predictive CT and H&E derived image features associated with chemotherapy response from Sd. A Cox proportional hazard regression model was used with these features to compute a risk score for each patients in Sd. Patients in Sv were stratified into high and low-risk groups based on the median risk score. Kaplan-Meier survival analysis was used to assess the prognostic ability of the risk score on Sv. Results: The risk score comprised nine CT (intra and peri-tumoral texture) and six H&E derived (cancer cell texture and shape) features. A linear regression model in conjunction with these 15 features was significantly associated with chemo-sensitivity in Sv (AUC = 0.76, PRC = 0.81). A multivariable model with these 15 features was significantly associated with OS in Sv (HR = 2.5, 95% CI: 1.3-4.9, P = 0.0043). Kaplan-Meier survival analysis revealed a significantly reduced OS in the high-risk group compared to the low-risk group. Conclusions: A combined CT and H&E tissue derived image signature model predicted response to chemotherapy and improved OS in SCLC patients. Image features from baseline CT scans and H&E tissue slide images may help in better risk stratification of SCLC patients. Additional independent validation of these quantitative image-based biomarkers is warranted.