基于单种群蛙跳优化CNN的眼底图像多病变检测

doi:10.3778/j.issn.1673-9418.2006067

摘要/Abstract

摘要：

为了有效解决眼底图像病变处存在交织重叠，大小血管密布并且受光照影响严重等问题，实现眼底图像多标签分类，提出了采用单种群蛙跳优化的卷积神经网络算法（SFCNN）对眼底多种病变进行检测。该算法保留混合蛙跳算法（SFLA）的高效寻优能力，简化成单种群蛙跳算法，并与传统卷积神经网络（CNN）有效结合。在初始化网络时，通过蛙跳算法优化网络初始权值选择；在网络迭代过程中监听卷积神经网络前向传播损失值并利用蛙跳算法的寻优能力修正异常权值；在网络符合结束条件后对最终权值进行一次蛙跳寻优，使网络权值得到进一步的优化，从而实现对复杂的眼底图像多病变检测分类。该算法对眼底图像病变检测的实验表明，相对于传统CNN算法，无论是在单病变检测还是同时整体检测，正确率均有所提高。

关键词: 混合蛙跳算法（SFLA）, 卷积神经网络（CNN）, 眼底图像, 多病变检测, 权值优化

Abstract:

In order to effectively solve the problem of interlaced overlap in the fundus image lesions, large and small blood vessels and severely affected by light, and to achieve multi-label classification of fundus images, in this paper, a single population frog-leaping optimization convolutional neural network algorithm (SFCNN) is proposed to detect various fundus lesions. The algorithm retains the efficient searching ability of the shuffled frog leaping algorithm (SFLA). It is simplified into a single population frog-leaping algorithm and effectively combined with the traditional convolutional neural networks (CNN). When initializing the network, the initial weight of the network is optimized by the frog-leaping algorithm. In the process of network iteration, the forward propagation loss of convolutional neural network is monitored and the abnormal weight is corrected by using the optimization ability of frog-leaping algorithm. After the network meets the end conditions, the final weight is optimized by frog-leaping, which further optimizes the network weight, so as to realize the detection and classification of complex fundus image with multiple lesions. The experiment of the detection of fundus image lesions shows that compared with CNN algorithm, the accuracy of the proposed algorithm is improved in both single lesion detection and overall detection.

Key words: shuffled frog leaping algorithm (SFLA), convolutional neural networks (CNN), fundus image, detection of multiple lesions, weight optimization

任龙杰, 孙颖, 丁卫平, 鞠恒荣, 曹金鑫. 基于单种群蛙跳优化CNN的眼底图像多病变检测[J]. 计算机科学与探索, 2021, 15(9): 1762-1772.

REN Longjie, SUN Ying, DING Weiping, JU Hengrong, CAO Jinxin. Multiple Lesions Detection of Fundus Images Based on CNN Algorithm Optimized by Single Population Frog-Leaping Algorithm[J]. Journal of Frontiers of Computer Science and Technology, 2021, 15(9): 1762-1772.

参考文献

[1] WALTER T, MASSIN P, ERGINAY A, et al. Automatic detection of microaneurysms in color fundus images[J]. Medical Image Analysis, 2007, 11(6): 555-566.
[2] ZHU C Z, XIANG Y, ZOU B J, et al. Retinal vessel segmentation in fundus images using CART and AdaBoost[J]. Journal of Computer-Aided Design & Computer Graphics, 2014, 26(3): 445-451.
朱承璋, 向遥, 邹北骥, 等. 基于分类回归树和AdaBoost的眼底图像视网膜血管分割[J]. 计算机辅助设计与图形学学报, 2014, 26(3): 445-451.
[3] ANWAR S M, MAJID M, QAYYUM A, et al. Medical image analysis using convolutional neural networks: a review[J]. Journal of Medical Systems, 2018, 42(11): 226.
[4] AGARWAL A, GULIA S, CHAUDHARY S, et al. Automatic glaucoma detection using adaptive threshold based technique in fundus image[C]//Proceedings of the 38th International Conference on Telecommunications and Signal Processing, Prague, Jul 9-11, 2015. Piscataway: IEEE, 2015: 416-420.
[5] GANGULY S, GANGULY S, SRIVASTAVA K, et al. An adaptive threshold based algorithm for detection of red lesions of diabetic retinopathy in a fundus image[C]//Proceedings of the 2014 International Conference on Medical Imaging, m-Health and Emerging Communication Systems, Greater Noida, Nov 7-8, 2014. Piscataway: IEEE, 2014: 91-94.
[6] BALASUBRAMANIAN T, KRISHNAN S, MOHANAKRISHNAN M, et al. HOG feature based SVM classification of glaucomatous fundus image with extraction of blood vessels[C]//Proceedings of the 2016 IEEE Annual India Conference, Bangalore, Dec 16-18, 2016. Piscataway: IEEE, 2016: 1-4.
[7] LIU J, YIN F S, WONG D W K, et al. Automatic glaucoma diagnosis from fundus image[C]//Proceedings of the 33rd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Boston, Aug 30-Sep 3, 2011. Piscataway: IEEE, 2011: 3383-3386.
[8] BOKHARI S T, SHARIF M, YASMIN M, et al. Fundus image segmentation and feature extraction for the detection of glaucoma: a new approach[J]. Current Medical Imaging Reviews, 2017, 14(1): 77-87.
[9] SRIDHAR S, RAO K J D S S, HEMANTH N, et al. An efficient blood vessel segmentation from color fundus image[J]. International Journal of Computer Applications, 2015, 119(2): 25-28.
[10] HOSSAIN N I, REZA S. Blood vessel detection from fundus image using Markov random field based image segmentation[C]//Proceedings of the 4th International Conference on Advances in Electrical Engineering, Dhaka, Sep 28-30, 2017. Piscataway: IEEE, 2017: 123-127.
[11] SAMAD R, NASARUDIN M S F, MUSTAFA M, et al. Boundary segmentation and detection of diabetic retinopathy (DR) in fundus image[J]. Journal of the American Society for Horticultural Science, 2015, 77(6): 25-28.
[12] ADAL K M, VAN ETTEN P G, MARTINEZ J P, et al. Detection of retinal changes from illumination normalized fundus images using convolutional neural networks[C]//Proceedings of the Medical Imaging 2017: Computer-Aided Diagnosis, Orlando, Feb 11-16, 2017. San Francisco: SPIE, 2017: 101341N.
[13] ORDó?EZ P F, CEPEDA C M, GARRIDO J, et al. Classification of images based on small local features: a case applied to microaneurysms in fundus retina images[J]. Journal of Medical Imaging, 2017, 4(4): 041309.
[14] DIAZ-PINTO A, MORALES S, NARANJO V, et al. CNNs for automatic glaucoma assessment using fundus images: an extensive validation[J]. BioMedical Engineering OnLine, 2019, 18(1): 29.
[15] XU K L, FENG D W, MI H B. Deep convolutional neural network-based early automated detection of diabetic retinopathy using fundus image[J]. Molecules, 2017, 22(12): 2054.
[16] PRENTA?I? P, LON?ARI? S. Detection of exudates in fundus photographs using convolutional neural networks[C]//Proceedings of the 2015 9th International Symposium on Image and Signal Processing and Analysis, Zagreb, Sep 7-9, 2015. Piscataway: IEEE, 2015: 188-192.
[17] ZHONG Z Q, YUAN J, TANG X Y. Left-vs-right eye discrimination based on convolutional neural network[J]. Journal of Computer Research and Development, 2018, 55(8): 1667-1673.
钟志权, 袁进, 唐晓颖. 基于卷积神经网络的左右眼识别[J]. 计算机研究与发展, 2018, 55(8): 1667-1673.
[18] MA D M, HE S S, YANG C F, et al. Semantic segmentation based on convolutional neural networks with feature fusion[J]. Computer Engineering and Applications, 2020, 56(10): 193-198.
马冬梅, 贺三三, 杨彩锋, 等. 特征融合型卷积神经网络的语义分割[J]. 计算机工程与应用, 2020, 56(10): 193-198.
[19] LECUN Y, BOSER B E, DENKER J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4): 541-551.
[20] GU J, WANG Z, KUEN J, et al. Recent advances in convolutional neural networks[J]. Pattern Recognition, 2018, 77: 354-377.
[21] LECUN Y, BENGIO Y. Convolutional networks for images, speech, and time series[M]//The Handbook of Brain Theory and Neural Networks. Cambridge: MIT Press, 1998.
[22] QU J Y, SUN X, GAO X. Remote sensing image target recognition based on CNN[J]. Foreign Electronic Measurement Technology, 2016, 35(8): 45-50.
曲景影, 孙显, 高鑫. 基于CNN模型的高分辨率遥感图像目标识别[J]. 国外电子测量技术, 2016, 35(8): 45-50.
[23] LI C M, YANG S X, YANG Y, et al. Hyperspectral remote sensing image classification based on maximum overlap pooling convolutional neural network[J]. Sensors, 2018, 18(10): 3587.
[24] HAN Y, CAI J H, ZHOU G G, et al. Advances in shuffled frog leaping algorithm[J]. Computer Science, 2010, 37(7): 16-19.
韩毅, 蔡建湖, 周根贵, 等. 随机蛙跳算法的研究进展[J]. 计算机科学, 2010, 37(7): 16-19.
[25] CUI W H, LIU X B, WANG W, et al. Survey on shuffled frog leaping algorithm[J]. Control and Decision, 2012, 27(4): 481-486.
崔文华, 刘晓冰, 王伟, 等. 混合蛙跳算法研究综述[J]. 控制与决策, 2012, 27(4): 481-486.
[26] XU F, ZHANG G Z. Clustering algorithm based on modified shuffled frog leaping algorithm and K-means[J]. Computer Engineering and Applications, 2013, 49(1): 176-180.
许方, 张桂珠. 一种改进的混合蛙跳和K均值结合的聚类算法[J]. 计算机工程与应用, 2013, 49(1): 176-180.
[27] HOOVER A D, KOUZNETSOVA V, GOLDBAUM M. Locating blood vessels in retinal images by piecewise threshold probing of a matched filter response[J]. IEEE Transactions on Medical Imaging, 2000, 19(3): 203-210.
[28] SAUNDERS C, STITSON M O, WESTON J, et al. Support vector machine[J]. Computer Science, 2002, 1(4): 1-28.
[29] LI Z, TIAN X M. Study of soft sensor modeling method based on KPCA-SVM[C]//Proceedings of the 6th World Congress on Intelligent Control and Automation, Dalian, Jun 21-23, 2006. Piscataway: IEEE, 2006: 4876-4880.