ESTRO 2023 - Abstract Book

S1897

Digital Posters

ESTRO 2023

to investigate the potential of diffusion MRI-based radiomic models as a non-invasive tool for Gleason Score prediction in PCa patients treated with radiotherapy. Materials and Methods 65 PCa patients, who underwent diffusion-weighted MRI (DWI) and enrolled for radiotherapy between 2014 and 2018 at the European Institute of Oncology (IEO, Italy), were included in the study. From mono-exponential fits of DWI, apparent diffusion coefficient (ADC) maps were estimated for 50 eligible patients. 107 radiomics features (14 shape, 18 first-order, 75 texture) were extracted from ADC maps of the whole prostate glands. A comparison was made of 5 feature selection routines (correlation, mutual information, Relief, RFECV, Mann-Whitney U-test), with the most predictive features from each being fed to three different classification models (logistic regression (LR), support vector machine (SVM), random forest (RF)) investigating the ability to predict total GS (6 (52%) vs. 7 (48%)) starting from ADC. Classification models were encapsulated in a 5-fold cross-validation routine. In addition, receiver operating characteristic (ROC) curves were built, and the average precision (AP) was calculated to access the accuracy of classification models. The predictive powers of the models built with radiomics features were finally compared, in terms of F1-score, with the ability of conventional clinical scores (i.e., NCCN risk class, T-stage, ECE, PIRADS) to stratify patients according to total GS. Results From AP and ROC analyses, the best diagnostic performance was found using RFECV as feature selection and LR as classifier, reaching an AP of 0.78 and an area under the ROC curve (AUC) of 0.81 (Fig1) . Among the 36 features with the highest predictive performance for GS, the textural ones were found to be the most frequent (12 shape, 6 first order, 18 texture). In the F1-score analyses, the radiomics-based model was found to be more powerful in predicting GS (F1=0.71, Fig.1) than the conventional clinical scores (F1=0.42, 0.19, 0.19, 0.12 for ECE, NCCN risk-class, PIRADS, and T-stage, respectively).

Conclusion Radiomic models based on DWI are a promising non-invasive tool for PCa characterization implying advantages for personalized therapy approaches.

PO-2113 Evaluating and updating predictive models: a high-tech open platform to boost clinical translation

A. Huat 1 , N.R. Franco 2 , J. Chang-Claude 3 , A. Cicchetti 4 , S. Gutiérrez-Enríquez 5 , P. Seibold 6 , C. Talbot 7 , A. Vega 8 , D. Gibon 1 , P. Zunino 2 , T. Rancati 4 1 AQUILAB by Coexya, R&D Department, Loos, France; 2 Politecnico di Milano, Department of Mathematics, Milan, Italy; 3 German Cancer Research (DKFZ), Division of Cancer Epidemiology, Heidelberg, Germany; 4 Fondazione IRCCS Istituto Nazionale dei Tumori, Prostate Cancer Program, Milan, Italy; 5 Vall d’Hebron Institute of Oncology (VHIO), Hereditary Cancer Genetics Group, Barcelona, Spain; 6 German Cancer Research Center (DKFZ), Division of Cancer Epidemiology, Heidelberg, Germany; 7 (on behalf of the REQUITE Consortium) University of Leicester, Genetics Department, Leicester, United Kingdom; 8 Fundación Pública Galega Medicina Xenómica, Instituto de Investigación Sanitaria, Santiago de Compostela, Spain