Optic disc detection based on fully convolutional network and weighted matrix recovery model

Eye diseases often affect human health. Accurate detection of the optic disc contour is one of the important steps in diagnosing and treating eye diseases. However, the structure of fundus images is complex, and the optic disc region is often disturbed by blood vessels. Considering that the optic di...

Full description

Saved in:
Bibliographic Details
Published in:Medical & biological engineering & computing 2023-12, Vol.61 (12), p.3319-3333
Main Authors: Wang, Siqi, Yu, Xiaosheng, Jia, Wenzhuo, Chi, Jianning, Lv, Pengfei, Wang, Junxiang, Wu, Chengdong
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Biomedical and Life Sciences
Biomedical Engineering and Bioengineering
Biomedicine
Blood vessels
Clustering
Computer Applications
Datasets
Eye
Eye diseases
Human Physiology
Imaging
Iterative methods
Mathematical analysis
Neural networks
Original Article
Radiology
Recovery
Segmentation
Sparse matrices
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Eye diseases often affect human health. Accurate detection of the optic disc contour is one of the important steps in diagnosing and treating eye diseases. However, the structure of fundus images is complex, and the optic disc region is often disturbed by blood vessels. Considering that the optic disc is usually a saliency region in fundus images, we propose a weakly-supervised optic disc detection method based on the fully convolution neural network (FCN) combined with the weighted low-rank matrix recovery model (WLRR). Firstly, we extract the low-level features of the fundus image and cluster the pixels using the Simple Linear Iterative Clustering (SLIC) algorithm to generate the feature matrix. Secondly, the top-down semantic prior information provided by FCN and bottom-up background prior information of the optic disc region are used to jointly construct the prior information weighting matrix, which more accurately guides the decomposition of the feature matrix into a sparse matrix representing the optic disc and a low-rank matrix representing the background. Experimental results on the DRISHTI-GS dataset and IDRiD dataset show that our method can segment the optic disc region accurately, and its performance is better than existing weakly-supervised optic disc segmentation methods. Graphical abstract Graphical abstract of optic disc segmentation
ISSN:0140-0118
1741-0444
DOI:10.1007/s11517-023-02891-2