TY - GEN
T1 - A Unified 3D Framework for Organs-at-Risk Localization and Segmentation for Radiation Therapy Planning
AU - Navarro, Fernando
AU - Sasahara, Guido
AU - Shit, Suprosanna
AU - Sekuboyina, Anjany
AU - Ezhov, Ivan
AU - Peeken, Jan C.
AU - Combs, Stephanie E.
AU - Menze, Bjoern H.
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Automatic localization and segmentation of organs-at-risk (OAR) in CT are essential pre-processing steps in medical image analysis tasks, such as radiation therapy planning. For instance, the segmentation of OAR surrounding tumors enables the maximization of radiation to the tumor area without compromising the healthy tissues. However, the current medical workflow requires manual delineation of OAR, which is prone to errors and is annotator-dependent. In this work, we aim to introduce a unified 3D pipeline for OAR localization-segmentation rather than novel localization or segmentation architectures. To the best of our knowledge, our proposed framework fully enables the exploitation of 3D context information inherent in medical imaging. In the first step, a 3D multi-variate regression network predicts organs' centroids and bounding boxes. Secondly, 3D organ-specific segmentation networks are leveraged to generate a multi-organ segmentation map. Our method achieved an overall Dice score of 0.9260 ± 0.18% on the VISCERAL dataset containing CT scans with varying fields of view and multiple organs.
AB - Automatic localization and segmentation of organs-at-risk (OAR) in CT are essential pre-processing steps in medical image analysis tasks, such as radiation therapy planning. For instance, the segmentation of OAR surrounding tumors enables the maximization of radiation to the tumor area without compromising the healthy tissues. However, the current medical workflow requires manual delineation of OAR, which is prone to errors and is annotator-dependent. In this work, we aim to introduce a unified 3D pipeline for OAR localization-segmentation rather than novel localization or segmentation architectures. To the best of our knowledge, our proposed framework fully enables the exploitation of 3D context information inherent in medical imaging. In the first step, a 3D multi-variate regression network predicts organs' centroids and bounding boxes. Secondly, 3D organ-specific segmentation networks are leveraged to generate a multi-organ segmentation map. Our method achieved an overall Dice score of 0.9260 ± 0.18% on the VISCERAL dataset containing CT scans with varying fields of view and multiple organs.
KW - CT
KW - Multi-organ segmentation
KW - Multi-variate regression
KW - Organ localization
UR - http://www.scopus.com/inward/record.url?scp=85138128079&partnerID=8YFLogxK
U2 - 10.1109/EMBC48229.2022.9871680
DO - 10.1109/EMBC48229.2022.9871680
M3 - Conference contribution
C2 - 36086554
AN - SCOPUS:85138128079
T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
SP - 1544
EP - 1547
BT - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 44th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2022
Y2 - 11 July 2022 through 15 July 2022
ER -