ESTRO 2024 - Abstract Book

S5041

Physics - Radiomics, functional and biological imaging and outcome prediction

ESTRO 2024

References:

[1] Green A, Vasquez Osorio E, Aznar MC, McWilliam A, van Herk M. Image Based Data Mining Using Per-voxel Cox Regression. Front Oncol. 2020;10:1178. Published 2020 Jul 21. doi:10.3389/fonc.2020.01178

[2] Massi MC, Gasperoni F, Ieva F, et al. A Deep Learning Approach Validates Genetic Risk Factors for Late Toxicity After Prostate Cancer Radiotherapy in a REQUITE Multi-National Cohort. Front Oncol. 2020;10:541281. Published 2020 Oct 15. doi:10.3389/fonc.2020.541281

[3] Franco NR, Massi MC, Ieva F, et al. Development of a method for generating SNP interaction-aware polygenic risk scores for radiotherapy toxicity. Radiother Oncol. 2021;159:241-248. doi:10.1016/j.radonc.2021.03.024

[4] Iacovacci J, Palorini F, Cicchetti A, Fiorino C, Rancati T. Dependence of the AUC of NTCP models on the observational dose-range highlights cautions in comparison of discriminative performance. Phys Med. 2023;113:102654. doi:10.1016/j.ejmp.2023.102654

Acknowledgements to REQUITE EU 7th FP GA 601826, RADprecise ERAPERMED2018-244 and JTC ERA PerMed 2020, PerPlanRT Project - Italian Ministry of Health ERP-2020-23671125

1420

Digital Poster

Prediction of necrosis based on deep learning for recurrent nasopharyngeal carcinoma radiotherapy

Yimei Liu 1 , Shanfu Lu 2 , Yuhan An 1 , Meining Chen 1 , Runda Huang 1 , Jingjing Miao 1 , Yiran Wang 2 , Zhenyu Qi 1 , Yao Lu 3 , Xiaowu Deng 1 , Yinglin Peng 1 1 Sun Yat-sen University Cancer Center, State Key Laboratory of Oncology in Southern China, Collaborative Innovation Center for Cancer Medicine, Guangdong Key Laboratory of Nasopharyngeal Carcinoma Diagnosis and Therapy, Department of Radiation Oncology, Guangzhou, China. 2 Proception Vision Medical Technology Inc,, Department of Radiation Oncology, Zhejiang, China. 3 Sun Yat-sen University, School of Data and Computer Science, Guangzhou, China

Purpose/Objective:

Purpose: Radiotherapy is one of the main treatments for recurrent nasopharyngeal carcinoma (rNPC). Re-irradiation for recurrent nasopharyngeal carcinoma may lead to necrosis in the nasopharyngeal target area, which increase the probability of massive nasopharyngeal hemorrhage and further affect the survival of patients. Therefore, it is essential to predict the probability of re-irradiation induced nasopharyngeal necrosis for helping adaptation of appropriate intervention or adjustment of radiotherapy plan. In this study, multi-sequence magnetic resonance imaging (MRI) and planned dose of radiotherapy (Plan Dose) were used to predict nasopharyngeal necrosis after re irradiation therapy in patients with recurrent nasopharyngeal carcinoma (NPC) based on deep learning method, so as to provide reference for clinical decision-making.