ESTRO 2023 - Abstract Book

S1870

Digital Posters

ESTRO 2023

process was used for preselection of the features with the highest predictive value. In the second step, the final models were composed by forward selection (likelihood ratio test) of features. Results The pulmonary complication NTCP model obtains AUC=0.86 (95%CI 0.72-0.97) at validation. It includes an increased risk for squamous cell carcinoma as compared to adenocarcinoma histology (p=0.006). The second predictor models the observed association between increased relative V15Gy on the left ventricle (p=0.008) and reduced complication risk. This observation needs further investigation. For cardiac complications AUC=0.66 (95%CI 0.45-0.83) is obtained at validation. Age (p=0.001) is confirmed as a key risk factor. An increased probability for cardiac events for more distal tumour sites (highest risk at the gastro-oesophageal junction, p=0.007) and for open surgery as compared to minimally invasive approaches (p=0.13) is also included. The fourth predictor is the normalized gray level non-uniformity of the dose in the lungs (p=0.015), a dosiomics feature designating an increased risk when large lung areas are homogeneously irradiated. Conclusion The selection of a dosiomics feature instead of a DVH feature in the cardiac complication model illustrates the added value of advanced 3D dose characteristics in NTCP modelling. Interaction between lung and heart doses and pulmonary and cardiac complications are apparent in both models. G. Nicolì 1 , G. Chiloiro 2 , D. Cusumano 3 , A. Romano 4 , L. Boldrini 5 , B. Barbaro 5 , B. Corvari 5 , E. Meldolesi 6 , V. Valentini 6 , M.A. Gambacorta 5 1 Fondazione Policlinico A. Gemelli IRCCS - Università Cattolica Sacro Cuore, Dipartimento Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, Rome, Italy; 2 Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Dipartimento Diagnostica per Immagini, Radioterapia Oncologica ed Ematologia, Rome, Italy; 3 Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Dipartimento Diagnostica per Immagini, Radioterapia oncologica ed Ematologia,, Rome, Italy; 4 Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Dipartimento Diagnostica per Immagini, Dipartimento Diagnostica per Immagini, Radioterapia oncologica ed Ematologia, Rome, Italy; 5 Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Dipartimento Diagnostica per Immagini, Radioterapia oncologica ed Ematologia, Rome, Italy; 6 Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Dipartimento Diagnostica per Immagini, Radioterapia oncologica ed Ematologia, Rome, Italy Purpose or Objective The standard treatment for locally advanced rectal cancer (LARC) is neoadjuvant chemoradiation therapy (nCRT) followed by total mesorectal excision (TME). Several studies have already shown that radiomics can predict pathological complete response (pCR) and survival outcomes. However, from a clinical point of view, there are prognostic factors such as tumour deposits, lymph node involvement, extramural vascular invasion (EMVI), all located in the mesorectum, which are accounted for in the choice of treatment. The aim of this study was to investigate the correlation of mesorectal radiomic features with pCR and 2-year disease-free survival (2y-DFS). Materials and Methods Patients (pts) with LARC and magnetic resonance imaging (MRI) before and after nCRT, treated in a single institution from May 2008 to November 2016 with a follow-up of at least 5 years, were retrospectively enrolled and analysed. Radiomic features were extracted from the GTV and mesorectum before and after nCRT and were blinded contoured by two radiation oncologists experienced in rectal cancer. All the radiomic features were extracted from MRI before and after CRT. Delta radiomic features were calculated as the ratio of features extracted at the two times. Pre-, post- and delta radiomic features of the mesorectum and GTV and clinical variables were selected for model development. The dataset was first randomly split into training set and validation set (66%/34%, Tripod 2a). The performance of the pCR and 2y-DFS predictive models was evaluated in terms of area under the receiver operating characteristic (ROC) curve (AUC) for both the training and validation set. Results A total of 203 LARC pts were collected (71 women, 132 men; median age 65 years (range 26-83 ). The median RT dose delivered at GTV was 55Gy (range 55-59.4 Gy). At a median follow-up 95 months, the pCR rate was 26.6% and the 2y-DFS was 84.3%. Overall, 565 variables were extracted (273 mesorectal features, 273 GTV features, and 19 clinical variables). The best performing pCR predictive model was based on GTV_ERI (Early Regression Index) and post_GTV_F_rlm.glnu with an AUC of 0.8 and 0.88 in the training and validation set, respectively. The best performing 2y-DFS predictive model was based on two features (Delta L-least GTV and Energy Pre-Mesorectum) with an AUC of 0.76 and 0.70 in the training and validation set, respectively. Conclusion The results of this study suggest a possible role of mesorectal radiomics features in predicting2y-DFS for LARC patients. Further analyses is needed to better understand the role of specific mesorectal features in predicting survival outcomes in LARC. PO-2088 Delta radiomic analysis of mesorectum to predict treatment response and prognosis in LARC