%0 Conference Paper %F Oral %T Prediction performance of radiomic features when obtained using an object detection framework %+ Service NEUROSPIN (NEUROSPIN) %A Chegraoui, Hamza %A Rebei, Amine %A Philippe, Cathy %A Frouin, Vincent %Z This work is partially funded by the Collaborative Research Agreement; Ref: CJ2020-0306/37598 between GustaveRoussy Villejuif and CEA Saclay. %Z ISBI 2021 moves to a fully virtual conference %< avec comité de lecture %J isbi 2021 %B IEEE ISBI 2021 - International Symposium on Biomedical Imaging %C Nice, France %8 2021-04-13 %D 2021 %Z Mathematics [math] %Z Computer Science [cs] %Z Life Sciences [q-bio]Conference papers %X Radiomic features analysis is a non invasive method for disease profiling. In the case of brain tumour studies, the quality of these features depends on the quality of tumour segmentation. However, these segmentations are not available for most cohorts. One way to address this issue is using object detection frameworks to automatically extract the area where the tumour is located in. The purpose of this study is to compare the quality of bounding-boxes based radiomics with manual segmentation, with regards to their performance in patient stratification and survival prediction. %G English %2 https://cea.hal.science/cea-03162316/document %2 https://cea.hal.science/cea-03162316/file/_HChegraoui__BIOMEDE_ISBI20.pdf %L cea-03162316 %U https://cea.hal.science/cea-03162316 %~ CEA %~ INSMI %~ CEA-UPSAY %~ UNIV-PARIS-SACLAY %~ JOLIOT %~ CEA-DRF %~ NEUROSPIN %~ UNIVERSITE-PARIS-SACLAY %~ GS-ENGINEERING %~ GS-LIFE-SCIENCES-HEALTH