TY - JOUR
T1 - A recursive ensemble organ segmentation (REOS) framework
T2 - Application in brain radiotherapy
AU - Chen, Haibin
AU - Lu, Weiguo
AU - Chen, Mingli
AU - Zhou, Linghong
AU - Timmerman, Robert
AU - Tu, Dan
AU - Nedzi, Lucien
AU - Wardak, Zabi
AU - Jiang, Steve
AU - Zhen, Xin
AU - Gu, Xuejun
N1 - Publisher Copyright:
© 2019 Institute of Physics and Engineering in Medicine.
PY - 2019/1/11
Y1 - 2019/1/11
N2 - The aim of this work is to develop a novel recursive ensemble OARs segmentation (REOS) framework for accurate organs-at-risk (OARs) automatic segmentation. The REOS recursively segment individual OARs by ensembling images features extracted from an organ localization module and a contour detection module. Both modules are based on a 3D U-Net architecture. The organ localization module is trained for rough segmentation to localize a region of interest (ROI) that encompasses the to-be-delineated OAR, while the contour detection module is trained to segment the OAR within the identified ROI. In this study, the developed REOS framework is applied for brain radiotherapy on segmenting six OARs including the eyes, the brainstem (BS), the optical nerves and the chiasm. Eighty T1-weighted magnetic resonance images (MRI) from 80 brain cancer patients' cases with OARs' gold standard contours were collected for training and testing REOS. On 20 testing cases, the REOS achieve a high segmentation accuracy with Dice similarity coefficient (DSC) mean and standard deviation of 93.9% ± 1.4%, 94.5% ± 2.0%, 90.6% ± 2.7%, on the left and right eyes and the BS, respectively. On small and segmentation-challenging organs, the left and right optical nerves and the chiasm, the REOS achieves DSC of 78.0% ± 10.5%, 82.2% ± 5.9% and 71.1% ± 9.1%. The satisfactory performances demonstrated the effectiveness of the REOS in OARs segmentation.
AB - The aim of this work is to develop a novel recursive ensemble OARs segmentation (REOS) framework for accurate organs-at-risk (OARs) automatic segmentation. The REOS recursively segment individual OARs by ensembling images features extracted from an organ localization module and a contour detection module. Both modules are based on a 3D U-Net architecture. The organ localization module is trained for rough segmentation to localize a region of interest (ROI) that encompasses the to-be-delineated OAR, while the contour detection module is trained to segment the OAR within the identified ROI. In this study, the developed REOS framework is applied for brain radiotherapy on segmenting six OARs including the eyes, the brainstem (BS), the optical nerves and the chiasm. Eighty T1-weighted magnetic resonance images (MRI) from 80 brain cancer patients' cases with OARs' gold standard contours were collected for training and testing REOS. On 20 testing cases, the REOS achieve a high segmentation accuracy with Dice similarity coefficient (DSC) mean and standard deviation of 93.9% ± 1.4%, 94.5% ± 2.0%, 90.6% ± 2.7%, on the left and right eyes and the BS, respectively. On small and segmentation-challenging organs, the left and right optical nerves and the chiasm, the REOS achieves DSC of 78.0% ± 10.5%, 82.2% ± 5.9% and 71.1% ± 9.1%. The satisfactory performances demonstrated the effectiveness of the REOS in OARs segmentation.
KW - brain radiotherapy
KW - deep learning
KW - segmentation
UR - http://www.scopus.com/inward/record.url?scp=85059829737&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85059829737&partnerID=8YFLogxK
U2 - 10.1088/1361-6560/aaf83c
DO - 10.1088/1361-6560/aaf83c
M3 - Article
C2 - 30540975
AN - SCOPUS:85059829737
SN - 0031-9155
VL - 64
JO - Physics in medicine and biology
JF - Physics in medicine and biology
IS - 2
M1 - 025015
ER -