Optic disc detection based on fully convolutional network and weighted matrix recovery model
Medical & Biological Engineering & Computing · 2023
DOI: 10.1007/s11517-023-02891-2 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical & Biological Engineering & Computing, 2023. Verfasst von Siqi Wang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Robot Science and Engineering, Northeastern University, 110170, Shen Yang, Liao Ning, China. Hauptthemen laut MEDLINE: Optic Disk, Glaucoma. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 50 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Key Research and Development Program of Liaoning Province, Natural Science Foundation of Liaoning Province.
Abstract (Originalsprache)
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 of optic disc segmentation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Robot Science and Engineering, Northeastern University, 110170, Shen Yang, Liao Ning, China.
- Faculty of Robot Science and Engineering, Northeastern University, 110170, Shen Yang, Liao Ning, China. yuxiaosheng@ise.neu.edu.cn.
- Art School, HE University, 110163, Shen Yang, Liao Ning, China.
- Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education, Northeastern University, 110170, Shen Yang, Liao Ning, China.
Förderung
- National Natural Science Foundation of China
- Key Research and Development Program of Liaoning Province
- Natural Science Foundation of Liaoning Province
- National Key Laboratory Foundation of China
Zitieren
APA
Wang, S., Yu, X., Jia, W., Chi, J., Lv, P., Wang, J., & Wu, C. (2023). Optic disc detection based on fully convolutional network and weighted matrix recovery model. Medical & Biological Engineering & Computing. https://doi.org/10.1007/s11517-023-02891-2
Vancouver
Wang S, Yu X, Jia W, Chi J, Lv P, Wang J, et al. Optic disc detection based on fully convolutional network and weighted matrix recovery model. Medical & Biological Engineering & Computing. 2023. doi:10.1007/s11517-023-02891-2
BibTeX
@article{Wang2023,
author = {Wang, Siqi and Yu, Xiaosheng and Jia, Wenzhuo and Chi, Jianning and Lv, Pengfei and Wang, Junxiang and Wu, Chengdong},
title = {Optic disc detection based on fully convolutional network and weighted matrix recovery model},
journal = {Medical & Biological Engineering & Computing},
year = {2023},
doi = {10.1007/s11517-023-02891-2}
}
EUVIMED