Hard Exudates Detection Method Based on Generative Adversarial Networks in Color Fundus Images
Long Shengchun1*, Chen Jiali1, Huang Xiaoxiao1, Chen Zhiqing2,
1.(College of Computer Science and Technology, Zhejiang university of technology, Hangzhou 310023, China) 2.(Eye Center, Affiliated Hospital of Zhejiang University School of Medicine, Hangzhou 310009, China)
Abstract：Diabetic retinopathy (DR) is a serious complication of diabetes and one of the most common causes of visual impairment. Hard exudates (HE) are early symptoms of DR, and its detection plays a key role in screening DR using fundus images. In this study, an automatic computational method based on Generative Adversarial Networks (GANs) for HE detection was proposed and evaluated on a publicly available database (e-ophtha EX). Compared with the general Convolutional Neural Network (CNN),GANs was composed of the generator G and the discriminator D, the mutual game and competition between them made the GANs detect HE in color fundus images more accurately. Firstly, the center of optic disc (OD) was located by considering its vessels features and brightness information, and masked to avoid interference with HE detection. Secondly, the generator G and the discriminator D were trained on e-ophtha EX dataset alternately, with the optimal model determined, which had the best segmentation effect on the validation dataset. The proposed algorithm was validated on e-ophtha EX database on pixel level, achieving the overall average sensitivity, PPV and F-score of 88.6%, 84.3% and 86.4%. It was then tested on another independent database (DIARETDB1) with the overall average sensitivity, specificity and accuracy of 100%, 96.2% and 97.8%, respectively. In summary, the evaluation results on both retinal image databases demonstrated the effectiveness of using GANs for automatic HE detection.
龙胜春, 陈嘉莉, 黄肖肖, 陈芝清,. 基于生成对抗网络的彩色眼底图像硬性渗出检测方法[J]. 中国生物医学工程学报, 2019, 38(2): 157-165.
Long Shengchun, Chen Jiali, Huang Xiaoxiao, Chen Zhiqing,. Hard Exudates Detection Method Based on Generative Adversarial Networks in Color Fundus Images. Chinese Journal of Biomedical Engineering, 2019, 38(2): 157-165.
[1] Zheng Yingfeng, He M, Congdon N. The worldwide epidemic of diabetic retinopathy [J]. Indian Journal of Ophthalmology, 2012, 60(5):428-431. [2] Akram MU, Tariq A, Khan SA, et al. Automated detection of exudates and macula for grading of diabetic macular edema [J]. Computer Methods & Programs in Biomedicine, 2014, 114(2):141-152. [3] Niemeijer M, Van GB, Russell SR, et al. Automated detection and differentiation of drusen, exudates, and cotton-wool spots in digital color fundus photographs for diabetic retinopathy diagnosis [J]. Investigative Ophthalmology & Visual Science, 2007, 48(5):2260-2267. [4] Tariq A, Anjum MA, Akram MU, et al. Automated detection of exudates in colored retinal images for diagnosis of diabetic retinopathy [J]. Appl Opt, 2012, 51(20): 4858-4866. [5] Osareh A, Mirmehdi M, Thomas BT, et al. Comparative exudate classification using support vector machines and neural networks [C] //Medical Image Computing and Computer-Assisted Intervention. Tokyo: Springer, 2002,2489:413-420. [6] Reza AW, Eswaran C, Dimyati K. Diagnosis of diabetic retinopathy: automatic extraction of optic disc and exudates from retinal images using marker-controlled watershed transformation [J]. Journal of Medical Systems, 2011, 35(6):1491-501. [7] 肖志涛, 赵北方, 张芳,等. 基于k均值聚类和自适应模板匹配的眼底出血点检测方法 [J]. 中国生物医学工程学报, 2015, 34(3):264-271. [8] Prentasic P, Loncaric S. Detection of exudates in fundus photographs using convolutional neural networks [C] //International Symposium on Image and Signal Processing and Analysis. Zagreb: IEEE, 2015:188-192. [9] Melinscak M, Prentasic P, Loncaric S. Retinal vessel segmentation using deep neural networks [C]//The 10th International Conference on Computer Vision Theory and Applications. Berlin: VISAPP, 2015:577-582. [10] Son J, Sang JP, Jung KH. Retinal vessel segmentation in fundoscopic images with generative adversarial networks [J]. Computing Research Repository, 2017, arXiv:1706.09318. [11] Goodfellow IJ, Pouget-Abadie J, Mirza M, et al. Generative adversarial networks [J]. Advances in Neural Information Processing Systems, 2014, 3:2672-2680. [12] Ronneberger O, Fischer P, Brox T. U-Net: Convolutional networks for biomedical image segmentation [C] //International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich: Springer, 2015:234-241. [13] Sánchez CI, Hornero R, López MI, et al. A novel automatic image processing algorithm for detection of hard exudates based on retinal image analysis [J]. Medical Engineering & Physics, 2008, 30(3):350-357. [14] Kauppi T, Kalesnykiene V, Kamarainen JK, et al. Diaretdb1 diabetic retinopathy database and evaluation protocol [C] //Proceeding of the British Machine Vision Conference. Coventry:DPLP, 2007:1-10. [15] Zhang Xiwei, Thibault G, Decencière, et al. Exudate detection in color retinal images for mass screening of diabetic retinopathy [J]. Medical Image Analysis, 2014,18(7):1026-1043. [16] 肖志涛, 王雯, 耿磊,等. 基于背景估计和SVM分类器的眼底图像硬性渗出物检测方法 [J]. 中国生物医学工程学报, 2015, 34(6):720-728. [17] Kingma D, Ba J. Adam: A Method for stochastic optimization [J]. Computer Science, 2014, 12(6980):1-6. [18] Hinton GE, Srivastava N, Krizhevsky A, et al. Improving neural networks by preventing co-adaptation of feature detectors [J]. Computer Science, 2012, 3(4): 212-223. [19] Imani E, Pourreza HR. A novel method for retinal exudate segmentation using signal separation algorithm [J]. Journal of Computer Methods and Programs in Biomedicine, 2016, 133:195-205. [20] Liu Q, Zou B, Chen J, et al. A location-to-segmentation strategy for automatic exudate segmentation in colour retinal fundus images [J]. Computerized Medical Imaging & Graphics, 2017, 55(pp): 78-86. [21] Medhi JP, Dandapat S. An effective fovea detection and automatic assessment of diabetic maculopathy in color fundus images [J]. Computers in Biology & Medicine, 2016, 74(1):30-44.
