Cascaded coarse-to-fine network with hybrid loss for eyeball segmentation in CT image

Anqi Zhang, Wentao Li, Jieliang Shi, Jingfan Fan*, Mingwei Gao, Jian Yang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publicationICMSSP 2021 - 2021 6th International Conference on Multimedia Systems and Signal Processing
PublisherAssociation for Computing Machinery
Pages35-40
Number of pages6
ISBN (Electronic)9781450390378
DOIs
Publication statusPublished - 22 May 2021
Event6th International Conference on Multimedia Systems and Signal Processing, ICMSSP 2021 - Virtual, Online, China
Duration: 22 May 202124 May 2021

Publication series

NameACM International Conference Proceeding Series

Conference

Conference6th International Conference on Multimedia Systems and Signal Processing, ICMSSP 2021
Country/TerritoryChina
CityVirtual, Online
Period22/05/2124/05/21

Keywords

  • Cascaded Network
  • Eyeball Segmentation
  • Hybrid Loss
  • Refinement Module

Fingerprint

Dive into the research topics of 'Cascaded coarse-to-fine network with hybrid loss for eyeball segmentation in CT image'. Together they form a unique fingerprint.

Cite this

Zhang, A., Li, W., Shi, J., Fan, J., Gao, M., & Yang, J. (2021). Cascaded coarse-to-fine network with hybrid loss for eyeball segmentation in CT image. In ICMSSP 2021 - 2021 6th International Conference on Multimedia Systems and Signal Processing (pp. 35-40). (ACM International Conference Proceeding Series). Association for Computing Machinery. https://doi.org/10.1145/3471261.3471268