Ruben T H M Larue1,2, Remy Klaassen3, Arthur Jochems1, Ralph T H Leijenaar1, Maarten C C M Hulshof4, Mark I van Berge Henegouwen5, Wendy M J Schreurs6, Meindert N Sosef7, Wouter van Elmpt2, Hanneke W M van Laarhoven3, Philippe Lambin1. 1. a The D-Lab: Decision Support for Precision Medicine, GROW - School for Oncology and Developmental Biology, Maastricht University Medical Centre , Maastricht , The Netherlands. 2. b Department of Radiation Oncology (MAASTRO), GROW - School for Oncology and Developmental Biology , Maastricht University Medical Centre , Maastricht , The Netherlands. 3. c Department of Medical Oncology , Academic Medical Centre , Amsterdam , The Netherlands. 4. d Department of Radiotherapy , Academic Medical Centre , Amsterdam , The Netherlands. 5. e Department of Surgery , Academic Medical Centre , Amsterdam , The Netherlands. 6. f Department of Nuclear Medicine , Zuyderland Medical Centre , Heerlen , The Netherlands. 7. g Department of Surgery , Zuyderland Medical Centre , Heerlen , The Netherlands.
Abstract
BACKGROUND: Radiomic features retrieved from standard CT-images have shown prognostic power in several tumor sites. In this study, we investigated the prognostic value of pretreatment CT radiomic features to predict overall survival of esophageal cancer patients after chemoradiotherapy. MATERIAL AND METHODS: Two datasets of independent centers were analyzed, consisting of esophageal cancer patients treated with concurrent chemotherapy (Carboplatin/Paclitaxel) and 41.4Gy radiotherapy, followed by surgery if feasible. In total, 1049 radiomic features were calculated from the primary tumor volume. Recursive feature elimination was performed to select the 40 most relevant predictors. Using these 40 features and six clinical variables as input, two random forest (RF) models predicting 3-year overall survival were developed. RESULTS: In total 165 patients from center 1 and 74 patients from center 2 were used. The radiomics-based RF model yielded an area under the curve (AUC) of 0.69 (95%CI 0.61-0.77), with the top-5 most important features for 3-year survival describing tumor heterogeneity after wavelet filtering. In the validation dataset, the RF model yielded an AUC of 0.61 (95%CI 0.47-0.75). Kaplan Meier plots were significantly different between risk groups in the training dataset (p = .027) and borderline significant in the validation dataset (p = .053). The clinical RF model yielded AUCs of 0.63 (95%CI 0.54-0.71) and 0.62 (95%CI 0.49-0.76) in the training and validation dataset, respectively. Risk groups did not reach a significant correlation with pathological response in the primary tumor. CONCLUSIONS: A RF model predicting 3-year overall survival based on pretreatment CT radiomic features was developed and validated in two independent datasets of esophageal cancer patients. The radiomics model had better prognostic power compared to the model using standard clinical variables.
BACKGROUND: Radiomic features retrieved from standard CT-images have shown prognostic power in several tumor sites. In this study, we investigated the prognostic value of pretreatment CT radiomic features to predict overall survival of esophageal cancerpatients after chemoradiotherapy. MATERIAL AND METHODS: Two datasets of independent centers were analyzed, consisting of esophageal cancerpatients treated with concurrent chemotherapy (Carboplatin/Paclitaxel) and 41.4Gy radiotherapy, followed by surgery if feasible. In total, 1049 radiomic features were calculated from the primary tumor volume. Recursive feature elimination was performed to select the 40 most relevant predictors. Using these 40 features and six clinical variables as input, two random forest (RF) models predicting 3-year overall survival were developed. RESULTS: In total 165 patients from center 1 and 74 patients from center 2 were used. The radiomics-based RF model yielded an area under the curve (AUC) of 0.69 (95%CI 0.61-0.77), with the top-5 most important features for 3-year survival describing tumor heterogeneity after wavelet filtering. In the validation dataset, the RF model yielded an AUC of 0.61 (95%CI 0.47-0.75). Kaplan Meier plots were significantly different between risk groups in the training dataset (p = .027) and borderline significant in the validation dataset (p = .053). The clinical RF model yielded AUCs of 0.63 (95%CI 0.54-0.71) and 0.62 (95%CI 0.49-0.76) in the training and validation dataset, respectively. Risk groups did not reach a significant correlation with pathological response in the primary tumor. CONCLUSIONS: A RF model predicting 3-year overall survival based on pretreatment CT radiomic features was developed and validated in two independent datasets of esophageal cancerpatients. The radiomics model had better prognostic power compared to the model using standard clinical variables.
Authors: Gerard M Healy; Emmanuel Salinas-Miranda; Rahi Jain; Xin Dong; Dominik Deniffel; Ayelet Borgida; Ali Hosni; David T Ryan; Nwabundo Njeze; Anne McGuire; Kevin C Conlon; Jonathan D Dodd; Edmund Ronan Ryan; Robert C Grant; Steven Gallinger; Masoom A Haider Journal: Eur Radiol Date: 2021-11-10 Impact factor: 7.034