Research on Optic Disc and Macula Fovea Simultaneous Location and Detection Method on FPGA

doi:10.3778/j.issn.1002-8331.2010-0233

Abstract

Abstract: In the automatic analysis of retinal images, the location of optic disc and macula fovea is a prerequisite for computer aided diagnosis or screening of diabetic retinopathy. In this paper, a novel algorithm for locating the optic disc and macula fovea in retinal images based on YOLOv4-tiny is proposed and transplanted to field programmable gate array （FPGA） platform. Compared with the traditional method, the present work can not only locate the position of the disc and macula in retinal images simultaneously, quickly and precisely, but also be the first attempt to realize 38 layers medium-sized neural network through using high level synthesis（HLS） language and time division multiplexing technology. The COCO data set and 381 retinal images from the recognized Kaggle-Diabetic Retinopathy Detection competition are used in the training experiment. From the experimental results, the mean average precision（mAP） of optic disc and macular fovea localization after transplanting to FPGA platform is 96.11%, and it only takes 150.445?ms to detect an image on the FPGA system, which presents a good clinical application prospect in related fields.

Key words: diabetic retinopathy, optic disc, macula fovea, YOLOv4-tiny, field programmable gate array（FPGA）

摘要： 在眼底图像自动分析中，视盘与黄斑的定位是实现利用计算机辅助诊断或筛查糖尿病视网膜病变的先决条件。提出一种实现眼底图像中视盘与黄斑同时定位检测的新方法，使用YOLOv4-tiny算法定位检测，将该算法移植到现场可编程逻辑门阵列（field programmable gate array，FPGA）。与传统方法相比，该方法不仅可以快速准确地同时定位眼底图像中视盘和黄斑的位置，而且也是利用高层综合（high level synthesis，HLS）语言和时分复用技术实现38层中型神经网络的首次尝试。实验采用公认的COCO数据集和Kaggle-Diabetic Retinopathy Detection竞赛中的381幅眼底图像对算法进行训练，将训练后的算法移植到FPGA平台后视盘和黄斑定位的平均正确率（mean average precision，mAP）为96.11%，检测一张图片只需要150.445?ms，在相关领域具有良好的临床应用前景。

关键词: 糖尿病视网膜病变（DR）, 黄斑, 视盘, YOLOv4-tiny, 现场可编程逻辑门阵列（FPGA）

ZHANG Wei, ZHOU Hua, LIU Yuhong, ZHANG Rongfen. Research on Optic Disc and Macula Fovea Simultaneous Location and Detection Method on FPGA[J]. Computer Engineering and Applications, 2022, 58(11): 193-199.

张卫, 周骅, 刘宇红, 张荣芬. 视盘与黄斑同时定位检测的FPGA方法研究[J]. 计算机工程与应用, 2022, 58(11): 193-199.

References

[1] SILBERMAN N，AHRLICH K，FERGUS R，et al.Case for automated detection of diabetic retinopathy[C]//AAAI Spring Symposium：Artificial Intelligence for Development，2010.
[2] DEEPAK K S，SIVASWAMY J.Automatic assessment of macular edema from color retinal images[J].IEEE Transactions on Medical Imaging，2012，31（3）：766-776.
[3] NIEMEIJER M，ABRàMOFF M D，VAN GINNEKEN B.Fast detection of the optic disc and fovea in color fundus photographs[J].Medical Image Analysis，2009，13（6）：859-870.
[4] SINTHANAYOTHIN C，BOYCE J F，COOK H L，et al.Automated localisation of the optic disc，fovea，and retinal blood vessels from digital colour fundus images[J].British Journal of Ophthalmology，1999，83（8）：902-910.
[5] LI H，CHUTATAPE O.Automatic location of optic disk in retinal images[C]//Proceedings of IEEE International Conference on Image Processing，Thessaloniki，Greece，2001：837-840.
[6] HOOVER A，GOLDBAUM M.Locating the optic nerve in a retinal image using the fuzzy convergence of the blood vessels[J].IEEE Transactions on Medical Imaging，2003，22（8）：951-958.
[7] YOUSSIF A A H A R，GHALWASH A Z，GHONEIM A A S A R.Optic disc detection from normalized digital fundus images by means of a vessels’ direction matched filter[J].IEEE Transactions on Medical Imaging，2008，27（1）：11-18.
[8] WELFER D，SCHARCANSKI J，KITAMURA C M，et al.Segmentation of the optic disk in color eye fundus images using an adaptive morphological approach[J].Computers in Biology and Medicine，2010，40（2）：124-137.
[9] 李居朋，陈后金，张新媛.基于交叉网络的眼底视神经乳头自动定位[J].电子与信息学报，2009，31（5）：1170-1174.
LI J P，CHEN H J，ZHANG X Y.Automatic localization of optic nerve head in the fundus images based on cross-network[J].Journal of Electronics & Information Technology，2009，31（5）：1170-1174.
[10] 张东波，易瑶，赵圆圆.基于投影的视网膜眼底图像视盘检测方法[J].中国生物医学工程学报，2013，32（4）：477-483.
ZHANG D B，YI Y，ZHAO Y Y.Projection based optic disk detection method in retinal fundus image[J].Chinese Journal of Biomedical Engineering，2013，32（4）：477-483.
[11] LI H，CHUTATAPE O.Automated feature extraction in color retinal images by a model based approach[J].IEEE Transactions on Biomedical Engineering，2004，51（2）：246-254.
[12] NIEMEIJER M，ABRàMOFF M D，VAN GINNEKEN B.Segmentation of the optic disc，macula and vascular arch in fundus photographs[J].IEEE Transactions on Medical Imaging，2007，26（1）：116-127.
[13] CHIN K S，TRUCCO E，TAN L，et al.Automatic fovea location in retinal images using anatomical priors and vessel density[J].Pattern Recognition Letters，2013，34（10）：1152-1158.
[14] 郑绍华，陈健，潘林，等.眼底图像中黄斑中心与视盘自动检测新方法[J].电子与信息学报，2014（11）：2586-2592.
ZHENG S H，CHEN J，PAN L，et al.A novel method of macula fovea and optic disk automatic detection for retinal images[J].Journal of Electronics & Information Technology，2014（11）：2586-2592.
[15] 钱玉多.基于FPGA的神经网络硬件实现研究[D].武汉：华中科技大学，2012.
QIAN Y D.The research of hardware implementation of neural networks based on FPGA[D].Wuhan：Huazhong University of Science and Technology，2012.
[16] 北京大学软件与微电子学院.基于FPGA的卷积神经网络IP核：CN201910038533.1[P].2019-05-21.
School of Software and Microelectronics，Peking University.The IP core of convolution neural network based on FPGA：CN201910038533.1[P].2019-05-21.
[17] REDMON J.You only look once：unified，real-time object detection[C]//IEEE Conferenceon Computer Vision and Pattern Recognition，2016.
[18] 黄智勇，吴海华，虞智，等.基于Tiny-yolo的网络压缩与硬件加速方法[J].华南理工大学学报（自然科学版），2019，47（6）：51-56.
HUANG Z Y，WU H H，YU Z，et al.Method of network compression and hardware acceleration based on Tiny-yolo[J].Journal of South China University of Technology（Natural Science Edition），2019，47（6）：51-56.