0 avis
Mechanistic simulation of tumor response outperforms radiomics predicting recurrence in prostate cancer radiotherapy
Archive ouverte
Edité par CCSD ; IEEE Computer Society -
International audience. In prostate cancer radiotherapy, biochemical recurrence has been traditionally predicted using radiomics approaches with however limited performance. The purpose of this work was to use a mechanistic in silico model of tumor growth and response to irradiation to obtain better predictions. A cohort of 76 patients with localized prostate adenocarcinoma having undergone external beam radiotherapy was used. Analogous digital tissues were built from pre-treatment MRI. The prescribed irradiation protocols were simulated using the mechanistic model. Logistic regression was then performed to predict recurrence i) directly from MRI features following a conventional radiomics approach, ii) from intermediate parameters and iii) from the number of tumor cells at t =8 weeks output given by the mechanistic model. Significant improvement in prediction (p-value leq 0.0001) was achieved using the simulation-based marker (AUC =0.85) compared to predictions based on the MRI features without and with oversampling (AUC =0.77 and 0.80, respectively). © 2021 IEEE.
Consulter en ligne
Suggestions
Du même auteur
