TY - GEN
T1 - Shape-aware weakly/semi-supervised optic disc and cup segmentation with regional/marginal consistency
AU - Meng, Yanda
AU - Chen, Xu
AU - Zhang, Hongrun
AU - Zhao, Yitian
AU - Gao, Dongxu
AU - Hamill, Barbra
AU - Patri, Godhuli
AU - Peto, Tunde
AU - Madhusudhan, Savita
AU - Zheng, Yalin
N1 - DBLP License: DBLP's bibliographic metadata records provided through http://dblp.org/ are distributed under a Creative Commons CC0 1.0 Universal Public Domain Dedication. Although the bibliographic metadata records are provided consistent with CC0 1.0 Dedication, the content described by the metadata records is not. Content may be subject to copyright, rights of privacy, rights of publicity and other restrictions.
PY - 2022/9/16
Y1 - 2022/9/16
N2 - Glaucoma is a chronic eye disease that permanently impairs vision. Vertical cup to disc ratio (vCDR) is essential for glaucoma screening. Thus, accurately segmenting the optic disc (OD) and optic cup (OC) from colour fundus images is essential. Previous fully-supervised methods achieved accurate segmentation results; then, they calculated the vCDR with offline post-processing step. However, a large set of labeled segmentation images are required for the training, which is costly and time-consuming. To solve this, we propose a weakly/semi-supervised framework with the benefits of geometric associations and specific domain knowledge between pixel-wise segmentation probability map (PM), geometry-aware modified signed distance function representations (mSDF), and local boundary region of interest characteristics (B-ROI). Firstly, we propose a dual consistency regularisation based semi-supervised paradigm, where the regional and marginal consistency benefits the proposed model from the objects’ inherent region and boundary coherence of a large amount of unlabeled data. Secondly, for the first time, we exploit the domain-specific knowledge between the boundary and region in terms of the perimeter and area of an oval shape of OD & OC, where a differentiable vCDR estimating module is proposed for the end-to-end training. Thus, our model does not need any offline post-process to generate vCDR. Furthermore, without requiring any additional laborious annotations, the supervision on vCDR can serve as a weakly-supervision for OD & OC region and boundary segmentation. Experiments on six large-scale datasets demonstrate that our method outperforms state-of-the-art semi-supervised approaches for segmentation of the optic disc and optic cup, and estimation of vCDR for glaucoma assessment in colour fundus images, respectively. The implementation code is made available. (https://github.com/smallmax00/Share_aware_Weakly-Semi_ODOC_seg)
AB - Glaucoma is a chronic eye disease that permanently impairs vision. Vertical cup to disc ratio (vCDR) is essential for glaucoma screening. Thus, accurately segmenting the optic disc (OD) and optic cup (OC) from colour fundus images is essential. Previous fully-supervised methods achieved accurate segmentation results; then, they calculated the vCDR with offline post-processing step. However, a large set of labeled segmentation images are required for the training, which is costly and time-consuming. To solve this, we propose a weakly/semi-supervised framework with the benefits of geometric associations and specific domain knowledge between pixel-wise segmentation probability map (PM), geometry-aware modified signed distance function representations (mSDF), and local boundary region of interest characteristics (B-ROI). Firstly, we propose a dual consistency regularisation based semi-supervised paradigm, where the regional and marginal consistency benefits the proposed model from the objects’ inherent region and boundary coherence of a large amount of unlabeled data. Secondly, for the first time, we exploit the domain-specific knowledge between the boundary and region in terms of the perimeter and area of an oval shape of OD & OC, where a differentiable vCDR estimating module is proposed for the end-to-end training. Thus, our model does not need any offline post-process to generate vCDR. Furthermore, without requiring any additional laborious annotations, the supervision on vCDR can serve as a weakly-supervision for OD & OC region and boundary segmentation. Experiments on six large-scale datasets demonstrate that our method outperforms state-of-the-art semi-supervised approaches for segmentation of the optic disc and optic cup, and estimation of vCDR for glaucoma assessment in colour fundus images, respectively. The implementation code is made available. (https://github.com/smallmax00/Share_aware_Weakly-Semi_ODOC_seg)
KW - Optic disc and cup segmentation
KW - Weakly/semi-supervised learning
UR - https://dblp.org/db/conf/miccai/miccai2022-4.html#MengCZZGHPPMZ22
UR - https://dblp.org/db/conf/miccai/2022-4
UR - https://conferences.miccai.org/2022/en/CONFERENCE-TIMELINE.html
U2 - 10.1007/978-3-031-16440-8_50
DO - 10.1007/978-3-031-16440-8_50
M3 - Conference contribution
SN - 9783031164392
T3 - Lecture Notes in Computer Science
SP - 524
EP - 534
BT - Medical Image Computing and Computer Assisted Intervention – MICCAI 2022
A2 - Wang, Linwei
A2 - Dou, Qi
A2 - Thomas Fletcher, P.
A2 - Speidel, Stefanie
A2 - Li, Shuo
PB - Springer Nature
T2 - 25th International Conference on Medical Image Computing and Computer Assisted Intervention
Y2 - 18 September 2022 through 22 September 2022
ER -