Optic disc detection based on visual saliency in fundus image

Pengfei Lyu; Ying Wang; Siqi Wang; Xiaosheng Yu; Chengdong Wu

doi:10.11834/jig.200444

Research and Application | Views : 0 下载量: 182 CSCD: 1

PDF
Export
Share
Collection
Album

Optic disc detection based on visual saliency in fundus image
Vol. 26, Issue 9, Pages: 2293-2304(2021)
Received：06 August 2020，

Revised：2020-10-12，

Accepted：19 October 2020，

Published：16 September 2021
DOI： 10.11834/jig.200444
稿件说明：

移动端阅览

DOI：

Pengfei Lyu, Ying Wang, Siqi Wang, Xiaosheng Yu, Chengdong Wu. Optic disc detection based on visual saliency in fundus image[J]. Journal of Image and Graphics, 2021, 26(9): 2293-2304. DOI： 10.11834/jig.200444.

摘要

目的

青光眼是导致失明的主要疾病之一，视盘区域的形状、大小等参数是青光眼临床诊断的重要指标。然而眼底图像通常亮度低、对比度弱，且眼底结构复杂，各组织以及病灶干扰严重。为解决上述问题，实现视盘的精确检测，提出一种视觉显著性的眼底图像视盘检测方法。

方法

首先，依据视盘区域显著的特点，采用一种基于视觉显著性的方法对视盘区域进行定位；其次，采用全卷积神经网络（fully convolutional neural network，FCN）预训练模型提取深度特征，同时计算视盘区域的平均灰度，进而提取颜色特征；最后，将深度特征、视盘区域的颜色特征和背景先验信息融合到单层元胞自动机（single-layer cellular automata，SCA）中迭代演化，实现眼底图像视盘区域的精确检测。

结果

在视网膜图像公开数据集DRISHTI-GS、MESSIDOR和DRIONS-DB上对本文算法进行实验验证，平均相似度系数分别为0.965 8、0.961 6和0.971 1；杰卡德系数分别为0.934 1、0.922 4和0.937 6；召回率系数分别为0.964 8、0.958 9和0.967 4；准确度系数分别为0.996 6、0.995 3和0.996 8，在3个数据集上均可精确地检测视盘区域。实验结果表明，本文算法精确度高，鲁棒性强，运算速度快。

结论

本文算法能够有效克服眼底图像亮度低、对比度弱及血管、病灶等组织干扰的影响，在多个视网膜图像公开数据集上进行验证均取得了较好的检测结果，具有较强的泛化性，可以实现视盘区域的精确检测。

Abstract

Objective

Glaucoma is a type of disease characterized by atrophy and depression of the nipple

visual field defect

and visual loss. It is one of the main diseases that cause blindness and visual impairment. The clinical diagnosis of glaucoma includes the optic disc

optic cup

intraocular pressure

and the angle between the cornea and iris. Early detection and treatment are crucial for avoiding visual impairment and blindness. In a fundus image

the optic disc is a bright yellow-white spot that resembles a circle

and it is the birthplace of the fundus blood vessels. The shape

size

and depth of the optic disc area and other parameters are important indicators in the clinical diagnosis of glaucoma. Detection of the optic disc can also help determine the location of other lesions

such as fundus hemorrhage and micro aneurysm. Thus

precise detection of the optic disc area is also vital. However

the fundus image is often not bright

and its contrast is poor. In addition

the fundus structure is complex

and the overlapping of tissues and lesions is serious. These problems pose great challenges to the accurate detection and segmentation of the optic disc. The traditional single visual saliency method is considerably affected by color and brightness; hence

tissues

such as blood vessels

and bright lesions easily interfere in optic disc detection. Fully convolutional neural networks (FCNs) classify images at the pixel level

thus solving the problem of image segmentation at the semantic level. In the process of FCN optic disc testing

the detection results are minimally affected by tissues (e.g.

vascular lesions)

the borders are rough

and the accuracy is low. To overcome these difficulties and achieve accurate detection of the fundus image optic disc

this study combines the advantages of the visual saliency method and FCN

and a visual saliency disc detection method based on the fusion of deep and shallow features is proposed.

Method

First

on the basis of the prominent characteristics of the optic disc area

a method based on visual saliency detection is used to locate the optic disc area. The saliency detection method based on morphological open reconstruction is utilized to extract the candidate solutions of the optic disc so that the enhanced optic disc becomes conspicuous and appears as a bright circular structure. The center of gravity of the optic disc is obtained and marked

and an image with a pixel size of 400×400 with the center of gravity as the center is extracted to segment the optic disc. Second

the Matconvnet computer vision neural network toolbox is used to extract deep features from the pre-trained model. The pre-trained model uses the pascal-fcn8s-dag.mat file provided on the official website of the Matconvnet toolbox

which uses the PASCAL VOC (pattern analysis

statistical modeling and computational learning visual object classes) 2011 dataset for training. Moreover

the average grayscale of the disc area is calculated for the 400×400 pixel size images to obtain color features. Lastly

by fusing the color feature

depth feature

and background prior information into a single-layer cellular automaton

the similarity is judged based on the distance between different cells in the feature space. Iterative evolution is performed to achieve accurate detection of the optic disc area in the fundus image.

Result

The proposed algorithm is experimentally verified on public datasets of fundus images

namely

DRISHTI-GS

MESSIDOR

and DRIONS-DB. The three datasets are mainly used for optic nerve head detection

including optic cup and optic disc. The optic disc area can be accurately detected in all datasets. The proposed algorithm detects the optic disc area in these datasets

and the evaluation indicators include Dice

Jaccard

recall

and accuracy. In the DRISHTI-GS dataset

Dice is 0.965 8

Jaccard is 0.934 1

recall is 0.964 8

and accuracy is 0.996 6. In the MESSIDOR dataset

Dice

Jaccard

recall

and accuracy have values of 0.961 6

0.922 4

0.958 9

and 0.995 3

respectively. In the DRIONS-DB dataset

Dice is 0.971 1

Jaccard is 0.937 6

recall is 0.967 4

and accuracy is 0.996 8. In addition

the proposed algorithm is compared with three algorithms

namely

improved circular Hough transform with Hough peak value selection and red channel superpixel segmentation for optic disc segmentation

accurate optic disc and cup segmentation from fundus images by using a multi-feature-based approach for glaucoma assessment

and dense fully convolutional with U-shape segmentation of the optic disc and cup in color fundus for glaucoma diagnosis. The proposed algorithm has higher accuracy

robustness

and calculation speed than the compared algorithms.

Conclusion

We propose a single-layer cellular automaton optic disc detection algorithm that integrates deep and shallow features. Experimental results show that the proposed algorithm can effectively overcome the effects of low brightness and low contrast of fundus images and the interference of blood vessels

lesions

and other tissues. The algorithm is verified on multiple public datasets of fundus images and achieves good detection results. It has strong generalization and realizes accurate detection of the optic disc area.

关键词

Keywords

references

Achanta R, Shaji A, Smith K, Lucchi A, Fua P and Süsstrunk S. 2012. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(11): 2274-2282[DOI: 10.1109/TPAMI.2012.120]

Acharya U R, Bhat S, Koh J E W, Bhandary S V and Adeli H. 2017. A novel algorithm to detect glaucoma risk using texton and local configuration pattern features extracted from fundus images. Computers in Biology and Medicine, 88: 72-83[DOI: 10.1016/j.compbiomed.2017.06.022]

Al-Bander B, Williams B M, Al-Nuaimy W, Al-Taee M A, Pratt H and Zheng Y L. 2018. Dense fully convolutional segmentation of the optic disc and cup in colour fundus for glaucoma diagnosis. Symmetry, 10(4): #87[DOI: 10.3390/sym10040087]

Decencière E, Zhang X W, Cazuguel G, Lay B, Cochener B, Trone C, Gain P, Ordonez R, Massin P, Erginay A, Charton B and Klein J C. 2014. Feedback on a publicly distributed image database: the messidor database. Image Analysis&Stereology, 33(3): 231-234[DOI: 10.5566/ias.1155]

Edupuganti V G, Chawla A and Kale A. 2018. Automatic optic disk and cup segmentation of fundus images using deep learning//Proceedings of the 25th IEEE International Conference on Image Processing (ICIP). Athens, Greece: IEEE: 2227-2231[ DOI: 10.1109/ICIP.2018.8451753 http://dx.doi.org/10.1109/ICIP.2018.8451753 ]

Fu H Z, Cheng J, Xu Y W, Wong D W K, Liu J and Cao X C. 2018. Joint optic disc and cup segmentation based on multi-label deep network and polar transformation. IEEE Transactions on Medical Imaging, 37(7): 1597-1605[DOI: 10.1109/TMI.2018.2791488]

Gao Y, Yu X S, Wu C D, Zhou W, Wang X N and Zhuang Y M. 2019. Accurate optic disc and cup segmentation from retinal images using a multi-feature based approach for glaucoma assessment. Symmetry, 11(10): #1267[DOI: 10.3390/sym11101267]

Hariharan B, Arbeláez P, Girshick R and Malik J. 2017. Object Instance segmentation and fine-grained localization using hypercolumns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 39(4): 627-639[DOI: 10.1109/TPAMI.2016.2578328]

Issac A, Parthasarthi M and Dutta M K. 2015. An adaptive threshold based algorithm for optic disc and cup segmentation in fundus images//Proceedings of the 2nd International Conference on Signal Processing and Integrated Networks (SPIN). Noida, India: IEEE: 143-147[ DOI: 10.1109/SPIN.2015.7095384 http://dx.doi.org/10.1109/SPIN.2015.7095384 ]

Jasty U, Harris A, Siesky B, Rowe L W, Vercellin A C V, Mathew S and Pasquale L R. 2020. Optic disc haemorrhage and primary open-angle glaucoma: a clinical review. British Journal of Ophthalmology, 104(11): 1488-1491[DOI: 10.1136/bjophthalmol-2019-314583]

Kao E F, Lin P C, Chou M C, Jaw T S and Liu G C. 2014. Automated detection of fovea in fundus images based on vessel-free zone and adaptive Gaussian template. Computer Methods and Programs in Biomedicine, 117(2): 92-103[DOI: 10.1016/j.cmpb.2014.08.003]

Long J, Shelhamer E and Darrell T. 2015. Fully convolutional networks for semantic segmentation//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, USA: IEEE: 3431-3440[ DOI: 10.1109/CVPR.2015.7298965 http://dx.doi.org/10.1109/CVPR.2015.7298965 ]

Mohammad S, Morris D T and Thacker N. 2013. Texture analysis for the segmentation of optic disc in retinal images//Proceedings of 2013 IEEE International Conference on Systems, Man, and Cybernetics. Manchester, UK: IEEE: 4265-4270[ DOI: 10.1109/SMC.2013.727 http://dx.doi.org/10.1109/SMC.2013.727 ]

Qin Y, Lu H C, Xu Y Q and Wang H. 2015. Saliency detection via cellular automata//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, USA: IEEE: 110-119[ DOI: 10.1109/CVPR.2015.7298606 http://dx.doi.org/10.1109/CVPR.2015.7298606 ]

Ramani R G and Shanthamalar J J. 2020. Improved image processing techniques for optic disc segmentation in retinal fundus images. Biomedical Signal Processing and Control, 58: #101832[DOI: 10.1016/j.bspc.2019.101832]

Sevastopolsky A. 2017. Optic disc and cup segmentation methods for glaucoma detection with modification of U-net convolutional neural network. Pattern Recognition and Image Analysis, 27(3): 618-624[DOI: 10.1134/S1054661817030269]

Sivaswamy J, Krishnadas S R, Joshi G D, Jain M and Tabish A U S. 2014. Drishti-GS: retinal image dataset for optic nerve head (ONH) segmentation//Proceedings of the 11th IEEE International Symposium on Biomedical Imaging (ISBI). Beijing, China: IEEE: 53-56[ DOI: 10.1109/ISBI.2014.6867807 http://dx.doi.org/10.1109/ISBI.2014.6867807 ]

Taha A A and Hanbury A. 2015. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Medical Imaging, 15(1): #29[DOI: 10.1186/s12880-015-0068-x]

Tekeli O, Savku E and Abdullayev A. 2016. Optic disc area in different types of Glaucoma. International Journal of Ophthalmology, 9(8): 1134-1137[DOI: 10.18240/ijo.2016.08.08]

Thakur N and Juneja M. 2019. Optic disc and optic cup segmentation from retinal images using hybrid approach. Expert Systems with Applications, 127: 308-322[DOI: 10.1016/j.eswa.2019.03.009]

Wang Y, Yu X S, Chi J N, Lei X L and Wu C D. 2020. Segmentation of optic cup and disc based on two-layer level set describer in retinal fundus images. Journal of Image and Graphics, 25(6): 1260-1270

王莹, 于晓升, 迟剑宁, 雷晓亮, 吴成东. 2020. 双层水平集描述眼底图像视杯视盘分割. 中国图象图形学报, 25(6): 1260-1270[DOI: 10.11834/jig.190396]

Welfer D, Scharcanski J and Marinho D R. 2013. A morphologic two-stage approach for automated optic disk detection in color eye fundus images. Pattern Recognition Letters, 34(5): 476-485[DOI: 10.1016/j.patrec.2012.12.011]

Yu T, Ma Y D and Li W. 2015. Automatic localization and segmentation of optic disc in fundus image using morphology and level set//The 9th International Symposium on Medical Information and Communication Technology (ISMICT). Kamakura, Japan: IEEE: 195-199[ DOI: 10.1109/ISMICT.2015.7107527 http://dx.doi.org/10.1109/ISMICT.2015.7107527 ]

Yu S, Xiao D, Frost S and Kanagasingam Y. 2019. Robust optic disc and cup segmentation with deep learning for glaucoma detection. Computerized Medical Imaging and Graphics, 74: 61-71[DOI: 10.1016/j.compmedimag.2019.02.005]

Zhou W, Wu C D, Gao Y and Yu X S. 2017. Automatic optic disc boundary extraction based on saliency object detection and modified local intensity clustering model in retinal images. IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences, E100, A(9): 2069-2072[ DOI: 10.1587/transfun.E100.A.2069 http://dx.doi.org/10.1587/transfun.E100.A.2069 ]

Alert me when the article has been cited

提交

Saliency detection based on multi-level features and spatial attention

Cross-modal feature fusion and detail-enhanced RGB-D salient object detection

Two-stage vision transformer for fusing global and local features in distracted driving behavior recognition

MoLiNet： a local and global information interactive fusion network for improving multi-classification of pathological image artifacts

Image denoising via Swin Transformer V2 and feature fusion U-Net