TY - GEN
T1 - Cascaded coarse-to-fine network with hybrid loss for eyeball segmentation in CT image
AU - Zhang, Anqi
AU - Li, Wentao
AU - Shi, Jieliang
AU - Fan, Jingfan
AU - Gao, Mingwei
AU - Yang, Jian
N1 - Publisher Copyright:
© 2021 ACM.
PY - 2021/5/22
Y1 - 2021/5/22
N2 - Eyeball segmentation in computed tomography (CT) images is the basis of computer-assisted diagnosis and surgery navigation system for eye diseases. Fully automatic eyeball segmentation is challenging due to the blurry boundaries, low contrast, and small proportion the eyeball occupied. We propose a framework based on cascaded coarse-to-fine network, combined with hybrid loss function for eyeball segmentation in CT images. The application of refinement module optimizes the coarse segmentation result. The hybrid loss function composed of CE, IoU, and SSIM simultaneously supervises the region and boundaries of the segmentation. Experiments on 4590 2D head CT images show that our method can effectively maintain the eyeball structure with clear boundaries and reduce the false-positive prediction in noneyeball regions.
AB - Eyeball segmentation in computed tomography (CT) images is the basis of computer-assisted diagnosis and surgery navigation system for eye diseases. Fully automatic eyeball segmentation is challenging due to the blurry boundaries, low contrast, and small proportion the eyeball occupied. We propose a framework based on cascaded coarse-to-fine network, combined with hybrid loss function for eyeball segmentation in CT images. The application of refinement module optimizes the coarse segmentation result. The hybrid loss function composed of CE, IoU, and SSIM simultaneously supervises the region and boundaries of the segmentation. Experiments on 4590 2D head CT images show that our method can effectively maintain the eyeball structure with clear boundaries and reduce the false-positive prediction in noneyeball regions.
KW - Cascaded Network
KW - Eyeball Segmentation
KW - Hybrid Loss
KW - Refinement Module
UR - http://www.scopus.com/inward/record.url?scp=85114667787&partnerID=8YFLogxK
U2 - 10.1145/3471261.3471268
DO - 10.1145/3471261.3471268
M3 - Conference contribution
AN - SCOPUS:85114667787
T3 - ACM International Conference Proceeding Series
SP - 35
EP - 40
BT - ICMSSP 2021 - 2021 6th International Conference on Multimedia Systems and Signal Processing
PB - Association for Computing Machinery
T2 - 6th International Conference on Multimedia Systems and Signal Processing, ICMSSP 2021
Y2 - 22 May 2021 through 24 May 2021
ER -