深度学习在糖尿病视网膜病变分类领域的研究进展

doi:10.3778/j.issn.1002-8331.2307-0330

摘要/Abstract

摘要： 糖尿病视网膜病变是导致糖尿病患者视力受损的主要原因之一，早期的分类诊断对于病情的治疗与控制具有重要意义。深度学习方法能够自动提取视网膜病变的特征并进行分类，因此成为糖尿病视网膜病变分类的重要工具。介绍常用的糖尿病视网膜病变数据集及评价指标，总结了深度学习在糖尿病视网膜病变二分类中的应用；综述了不同的经典深度学习模型在糖尿病视网膜病变严重程度分类中的应用，重点阐述卷积神经网络的分类诊断方法，并对不同方法进行综合对比分析；最后讨论该领域面临的挑战，并对未来发展方向进行了展望。

关键词: 糖尿病视网膜病变, 深度学习, 二分类, 严重程度分类, 卷积神经网络（CNN）

Abstract: Diabetic retinopathy is one of the primary causes of visual impairment in diabetic patients, and early classification and diagnosis are of significant importance for disease management and control. Deep learning methods have the capability to automatically extract features of retinal lesions and perform classification, making them essential tools for diabetic retinopathy classification. This paper begins by introducing commonly used datasets and evaluation metrics for diabetic retinopathy, summarizing the applications of deep learning in binary classification of diabetic retinopathy. It then provides an overview of various classical deep learning models used for severity classification of diabetic retinopathy, focuses on the classification and diagnosis methods of convolutional neural networks, and makes a comprehensive comparative analysis of different approaches. Finally, the paper discusses the challenges in this field and provides an outlook on future directions for research and development.

Key words: diabetic retinopathy, deep learning, binary classification, severity classification, convolutional neural network(CNN)

孙石磊, 李明, 刘静, 马金刚, 陈天真. 深度学习在糖尿病视网膜病变分类领域的研究进展[J]. 计算机工程与应用, 2024, 60(8): 16-30.

SUN Shilei, LI Ming, LIU Jing, MA Jingang, CHEN Tianzhen. Research Progress on Deep Learning in Field of Diabetic Retinopathy Classification[J]. Computer Engineering and Applications, 2024, 60(8): 16-30.

参考文献

[1] YANG Z, TAN T E, SHAO Y, et al. Classification of diabetic retinopathy: past, present and future[J]. Frontiers in Endocrinology, 2022, 13: 1079217.
[2] SHANKAR K, ZHANG Y, LIU Y, et al. Hyperparameter tuning deep learning for diabetic retinopathy fundus image classification[J]. IEEE Access, 2020, 8: 118164-118173.
[3] SHARAFELDEEN A, ELSHARKAWY M, KHALIFA F, et al. Precise higher-order reflectivity and morphology models for early diagnosis of diabetic retinopathy using OCT images[J]. Scientific Reports, 2021, 11(1): 4730.
[4] 韩长明, 彭福来, 陈财, 等.基于脑电信号的癫痫发作预测研究进展[J].生物医学工程学杂志, 2021, 38(6): 1193-1202.
HAN C M, PENG F L, CHEN C, et al. Research progress of epileptic seizure predictions based on electroencephalogram signals[J]. Journal of Biomedical Engineering, 2021, 38(6): 1193-1202.
[5] 陆言巧, 沈兰, 何奔.人工智能在心血管疾病的辅助诊疗中的应用[J].上海交通大学学报(医学版), 2020, 40(2): 259-262.
LU Y W, SHEN L, HE B. Application of artificial inte-lligence in assisted diagnosis and treatment of cardio-vascular disease[J]. Diseases. Journal of Shanghai Jiao Tong University (Medical Science), 2020, 40(2): 259-262.
[6] VUJOSEVIC S, ALDINGTON S J, SILVA P, et al. Screening for diabetic retinopathy: new perspectives and challenges[J]. The Lancet Diabetes & Endocrinology, 2020, 8(4): 337-347.
[7] AJIT A, ACHARYA K, SAMANTA A. A review of convolutional neural networks[C]//Proceedings of the 2020 International Conference on Emerging Trends In Information Technology and Engineering, 2020: 1-5.
[8] ADEM K. Exudate detection for diabetic retinopathy with circular Hough transformation and convolutional neural networks[J]. Expert Systems with Applications, 2018, 114: 289-295.
[9] 杨培伟, 周余红, 邢岗, 等.卷积神经网络在生物医学图像上的应用进展[J].计算机工程与应用, 2021, 57(7): 44-58.
YANG P W, ZHOU Y H, XING G, et al. Applications of convolutional neural network in biomedical image[J]. Computer Engineering and Applications, 2021, 57(7): 44-58.
[10] 范家伟, 张如如, 陆萌, 等.深度学习方法在糖尿病视网膜病变诊断中的应用[J].自动化学报, 2021, 47(5): 985-1004.
FAN J W, ZHANG R R, LU M, et al. Applications of deep learning techniques for diabetic retinal diagnosis[J]. Acta Automatica Sinica, 2021, 47(5): 985-1004.
[11] VIJ R, ARORA S. A systematic review on diabetic retinopathy detection using deep learning techniques[J]. Archives of Computational Methods in Engineering, 2023, 30(3): 2211-2256.
[12] NADEEM M W, GOH H G, HUSSAIN M, et al. Deep learning for diabetic retinopathy analysis: a review, research challenges, and future directions[J]. Sensors, 2022, 22: 6780.
[13] ASIRI N, HUSSAIN M, AL ADEL F, et al. Deep learning based computer-aided diagnosis systems for diabetic retinopathy: a survey[J]. Artificial Intelligence in Medicine, 2019, 99: 101701.
[14] 聂永琦, 曹慧, 杨锋, 等.深度学习在糖尿病视网膜病灶检测中的应用综述[J].计算机工程与应用, 2021, 57(20): 25-41.
NIE Y Q, CAO H, YANG F, et al. Review of application of deep learning in detection of diabetic retinal lesions[J]. Computer Engineering and Applications, 2021, 57(20): 25-41.
[15] Kaggle[EB/OL].（2021-01-25）[2023-06-30].http: //www.kagglecom/c/diabetic-retinopathy-detection/discussion/15617.
[16] DECENCIERE E, CAZUGUEL G, ZHANG X, et al. TeleOphta: machine learning and image processing methods for teleophthalmology[J]. IRBM, 2013, 34(2): 196-203.
[17] KAUPPI T, KALESNYKIENE V, KAMARAINEN J K, et al. The DIARETDB1 diabetic retinopathy database and evaluation protocol[C]//Proceedings of the British Machine Vision Conference, 2007.
[18] 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.
[19] DECENCIèRE E, ZHANG X, CAZUGUEL G, et al. Feedback on a publicly distributed image database: the MESSIDOR database[J]. Image Analysis & Stereology, 2014, 33(3): 231-234.
[20] PORWAL P, PACHADE S, KAMBLE R, et al. Indian diabetic retinopathy image dataset (IDRiD)[J]. IEEE DataPort, 2018, 2.
[21] HOLLOW F. Diabetes eye health: a guide for health professionals[Z]. The Fred Hollows Foundation in Partnership with the International Diabetes Federation (IDF), 2015.
[22] KANTH S, JAISWAL A, KAKKAR M. Identification of different stages of Diabetic Retinopathy using artificial neural network[C]//Proceedings of the 2013 Sixth International Conference on Contemporary Computing (IC3), 2013: 479-484.
[23] HARUN N H, YUSOF Y, HASSAN F, et al. Classification of fundus images for diabetic retinopathy using artificial neural network[C]//Proceedings of the 2019 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology, 2019: 498-501.
[24] XU K, FENG D, MI H. Deep convolutional neural network-based early automated detection of diabetic retinopathy using fundus image[J]. Molecules, 2017, 22(12): 2054.
[25] LAM C, YI D, GUO M, et al. Automated detection of diabetic retinopathy using deep learning[C]//AMIA Summits on Translational Science Proceedings, 2018: 147-155.
[26] PIRES R, AVILA S, WAINER J, et al. A data-driven approach to referable diabetic retinopathy detection[J]. Artificial Intelligence in Medicine, 2019, 96: 93-106.
[27] SKOUTA A, ELMOUFIDI A, JAI-ANDALOUSSI S, et al. Automated binary classification of diabetic retinopathy by convolutional neural networks[C]//Advances in Intelligent Systems and Computing, 2021: 177-187.
[28] ADRIMAN R, MUCHTAR K, MAULINA N. Performance evaluation of binary classification of diabetic retinopathy through deep learning techniques using texture feature[J]. Procedia Computer Science, 2021, 179: 88-94.
[29] ASIA A O, ZHU C Z, ALTHUBITI S A, et al. Detection of diabetic retinopathy in retinal fundus images using CNN classification models[J]. Electronics, 2022, 11(17): 2740.
[30] DAS S, SAHA S K. Diabetic retinopathy detection and classification using CNN tuned by genetic algorithm[J]. Multimedia Tools and Applications, 2022, 81(6): 8007-8020.
[31] WILKINSON C P, FERRIS III F L, KLEIN R E, et al. Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales[J]. Ophthalmology, 2003, 110(9): 1677-1682.
[32] SEBASTIAN A, ELHARROUSS O, AL-MAADEED S, et al. A survey on deep-learning-based diabetic retinopathy classification[J]. Diagnostics, 2023, 13(3): 345.
[33] LIPTON Z C, BERKOWITZ J, ELKAN C. A critical review of recurrent neural networks for sequence learning[J]. arXiv: 1506.00019, 2015.
[34] 王晋宇, 杨海涛, 李高源, 等.生成对抗网络及其图像处理应用研究进展[J].计算机工程与应用, 2021, 57(8): 26-35.
WANG J Y, YANG H T, LI G Y, et al. Research progress of generative adversarial network and its application in image processing[J]. Computer Engineering and Applications, 2021, 57(8): 26-35.
[35] HINTON G E, SALAKHUTDINOV R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313: 504-507.
[36] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems, 2017.
[37] PRATT H, COENEN F, BROADBENT D M, et al. Convolutional neural networks for diabetic retinopathy[J]. Procedia Computer Science, 2016, 90: 200-205.
[38] ISLAM S M S, HASAN M M, ABDULLAH S. Deep learning based early detection and grading of diabetic retinopathy using retinal fundus images[J]. arXiv:1812.10595, 2018.
[39] MANSOUR R F. Deep-learning-based automatic computer-aided diagnosis system for diabetic retinopathy[J]. Biomedical Engineering Letters, 2018, 8: 41-57.
[40] HACISOFTAOGLU R E, KARAKAYA M, SALLAM A B. Deep learning frameworks for diabetic retinopathy detection with smartphone-based retinal imaging systems[J]. Pattern Recognition Letters, 2020, 135: 409-417.
[41] 庞浩, 王枞.用于糖尿病视网膜病变检测的深度学习模型[J].软件学报, 2017, 28(11): 3018-3029.
PANG H, WANG C. Deep learning model for diabetic r-etinopathy detection[J]. Journal of Software, 2017, 28(11): 3018-3029.
[42] DE LA TORRE J, VALLS A, PUIG D. A deep learning interpretable classifier for diabetic retinopathy disease grading[J]. Neurocomputing, 2020, 396: 465-476.
[43] ARAúJO T, ARESTA G, MENDON?A L, et al. DR| GRADUATE: uncertainty-aware deep learning-based diabetic retinopathy grading in eye fundus images[J]. Medical Image Analysis, 2020, 63: 101715.
[44] BHIMAVARAPU U, BATTINENI G. Deep learning for the detection and classification of diabetic retinopathy with an improved activation function[J].Healthcare, 2022, 11(1): 97.
[45] FARAG M M, FOUAD M, ABDEL-HAMID A T. Automatic severity classification of diabetic retinopathy based on DenseNet and convolutional block attention module[J]. IEEE Access, 2022, 10: 38299-38308.
[46] 白杰, 张赛, 李艳萍.基于PL-EfficientNet的糖尿病视网膜病变检测研究[J].电子设计工程, 2022, 30(21): 175-179.
BAI J, ZHANG S, LI Y P. Diabetic retinopathy detection research based on PL-EfficientNet[J]. Electronic Design Engineering, 2022, 30(21): 175-179.
[47] KOBAT S G, BAYGIN N, YUSUFOGLU E, et al. Automated diabetic retinopathy detection using horizontal and vertical patch division-based pre-trained DenseNET with digital fundus images[J]. Diagnostics, 2022, 12(8): 1975.
[48] INGLE V, AMBAD P. Diabetic retinopathy classifier with convolution neural network[J]. Materials Today: Proceedings, 2023, 72: 1765-1773.
[49] MEHBOOB A, AKRAM M U, ALGHAMDI N S, et al. A deep learning based approach for grading of diabetic retinopathy using large fundus image dataset[J]. Diagnostics, 2022, 12(12): 3084.
[50] CAO J, CHEN J, ZHANG X, et al. Diabetic retinopathy classification based on dense connectivity and asymmetric convolutional neural network[J]. Neural Computing and Applications, 2022(1): 1-14.
[51] GAYATHRI S, GOPI V P, PALANISAMY P. A lightweight CNN for Diabetic Retinopathy classification from fundus images[J]. Biomedical Signal Processing and Control, 2020, 62: 102115.
[52] NAHIDUZZAMAN M, ISLAM M R, GONI M O F, et al. Diabetic retinopathy identification using parallel convolutional neural network based feature extractor and ELM classifier[J]. Expert Systems with Applications, 2023, 217: 1-11.
[53] XU Z, DONG J. Multi-stage classification of diabetic retinopathy based on mixed attention network[C]//Proceedings of the 3rd International Conference on Electronic Communication and Artificial Intelligence, 2022: 495-502.
[54] LI Y, SONG Z, KANG S, et al. Semi-supervised auto-encoder graph network for diabetic retinopathy grading[J]. IEEE Access, 2021, 9: 140759-140767.
[55] NNEJI G U, CAI J, DENG J, et al. Identification of diabetic retinopathy using weighted fusion deep learning based on dual-channel fundus scans[J]. Diagnostics, 2022, 12(2): 540.
[56] ALJEHANE N O. An intelligent moth flame optimization with inception network for diabetic retinopathy detection and grading[C]//Proceedings of the 2nd International Conference on Computing and Information Technology, 2022: 370-373.
[57] BODAPATI J D, NARALASETTI V, SHAREEF S N, et al. Blended multi-modal deep convnet features for diabetic retinopathy severity prediction[J]. Electronics, 2020, 9(6): 914.
[58] DHIRAVIDACHELVI E, SENTHIL PANDI S, PRABAVATHI R, et al. Artificial humming bird optimization-based hybrid CNN-RNN for accurate exudate classification from fundus images[J]. Journal of Digital Imaging, 2023, 36(1): 59-72.
[59] MRIDHA K, SHORNA M M, AREFIN N, et al. DBNet: detect diabetic retinopathy to stop blindness before it’s too late[C]//Proceedings of the 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions), 2022: 1-6.
[60] ZHOU Y, WANG B, HE X, et al. DR-GAN: conditional generative adversarial network for fine-grained lesion synthesis on diabetic retinopathy images[J]. IEEE Journal of Biomedical and Health Informatics, 2020, 26(1): 56-66.
[61] ZHENG C, XIE X, ZHOU K, et al. Assessment of generative adversarial networks model for synthetic optical coherence tomography images of retinal disorders[J]. Translational Vision Science & Technology, 2020, 9(2): 29.
[62] YOO T K, CHOI J Y, KIM H K, et al. Adopting low-shot deep learning for the detection of conjunctival melanoma using ocular surface images[J]. Computer Methods and Programs in Biomedicine, 2021, 205: 106086.
[63] ARUNKUMAR R, KARTHIGAIKUMAR P. Multi-retinal disease classification by reduced deep learning features[J]. Neural Computing and Applications, 2017, 28: 329-334.
[64] HUGHES J, HARAN M. Dimension reduction and alleviation of confounding for spatial generalized linear mixed models[J]. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 2013, 75(1): 139-159.
[65] SYAHPUTRA M F, RAHMAH M, JAYA I, et al. Diabetic retinopathy identification using deep believe network[J]. Journal of Physics: Conference Series, 2019, 1235: 012103.
[66] TEHRANI A A, NICKFARJAM A M, EBRAHIMPOUR-KOMLEH H, et al. Multi-input 2-dimensional deep belief network: diabetic retinopathy grading as case study[J]. Multimedia Tools and Applications, 2021, 80: 6171-6186.
[67] JIANG H, YANG K, GAO M, et al. An interpretable ensemble deep learning model for diabetic retinopathy disease classification[C]//Proceedings of the 41st Annual International Conference of the IEEE Engineering In Medicine and Biology Society, 2019: 2045-2048.
[68] KHALED O, EL-SAHHAR M, EL-DINE M A, et al. Cascaded architecture for classifying the preliminary stages of diabetic retinopathy[C]//Proceedings of the 9th International Conference on Software and Information Engineering, 2020: 108-112.
[69] AL-KARAWI A, AV?AR E. A deep learning framework with edge computing for severity level detection of diabetic retinopathy[J]. Multimedia Tools and Applications, 2023, 82: 37687-37708.
[70] MENAOUER B, DERMANE Z, EL HOUDA KEBIR N, et al. Diabetic retinopathy classification using hybrid deep learning approach[J]. SN Computer Science, 2022, 3(5): 357.
[71] MONDAL S S, MANDAL N, SINGH K K, et al. EDLDR: an ensemble deep learning technique for detection and classification of diabetic retinopathy[J]. Diagnostics, 2023, 13(1): 124.
[72] YANG H, CHEN J, XU M. Fundus disease image classification based on improved transformer[C]//Proceedings of the 2021 International Conference on Neuromorphic Computing, 2021: 207-214.
[73] RAJKUMAR R S, JAGATHISHKUMAR T, RAGUL D, et al. Transfer learning approach for diabetic retinopathy detection using residual network[C]//Proceedings of the 6th International Conference on Inventive Computation Technologies, 2021: 1189-1193.
[74] LE D, ALAM M, YAO C K, et al. Transfer learning for automated OCTA detection of diabetic retinopathy[J]. arXiv: 1910.01796, 2019.
[75] SUGENO A, ISHIKAWA Y, OHSHIMA T, et al. Simple methods for the lesion detection and severity grading of diabetic retinopathy by image processing and transfer learning[J]. Computers in Biology and Medicine, 2021, 137: 104795.
[76] GANGWAR A K, RAVI V. Diabetic retinopathy detection using transfer learning and deep learning[C]//Evolution in Computational Intelligence: Frontiers in Intelligent Computing: Theory and Applications (FICTA 2020), 2021: 679-689.
[77] TANG M C S, TEOH S S, IBRAHIM H, et al. A deep learning approach for the detection of neovascularization in fundus images using transfer learning[J]. IEEE Access, 2022, 10: 20247-20258.
[78] BODAPATI J D, SHAIK N S, NARALASETTI V. Composite deep neural network with gated-attention mechanism for diabetic retinopathy severity classification[J]. Journal of Ambient Intelligence and Humanized Computing, 2021, 12(10): 9825-9839.
[79] TARIQ H, RASHID M, JAVED A, et al. Performance analysis of deep-neural-network-based automatic diagnosis of diabetic retinopathy[J]. Sensors, 2021, 22(1): 205.
[80] GOUR N, KHANNA P. Multi-class multi-label ophthalmological disease detection using transfer learning based convolutional neural network[J]. Biomedical Signal Processing and Control, 2021, 66: 102329.
[81] GU Z, LI Y, WANG Z, et al. Classification of diabetic retinopathy severity in fundus images using the vision transformer and residual attention[J]. Computational Intelligence and Neuroscience, 2023,9414: 1-12.
[82] SUN R, LI Y, ZHANG T, et al. Lesion-aware transformers for diabetic retinopathy grading[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 10938-10947.
[83] YAO Z, YUAN Y, SHI Z, et al. FunSwin: a deep learning method to analysis diabetic retinopathy grade and macular edema risk based on fundus images[J]. Frontiers in Physiology, 2022, 13: 961386.
[84] WU K, PENG B, ZHAI D. Multi-granularity dilated transformer for lung nodule classification via local focus scheme[J]. Applied Sciences, 2022, 13(1): 377.
[85] MURTHY S, PRASAD P M K. Adversarial transformer network for classification of lung cancer disease from CT scan images[J]. Biomedical Signal Processing and Control, 2023, 86: 105327.
[86] JIANG H, XU J, SHI R, et al. A multi-label deep learning model with interpretable grad-CAM for diabetic retinopathy classification[C]//Proceedings of the 42nd Annual International Conference of the IEEE Engineering in Medicine & Biology Society, 2020: 1560-1563.
[87] PAPADOPOULOS A, TOPOUZIS F, DELOPOULOS A. An interpretable multiple-instance approach for the detection of referable diabetic retinopathy in fundus images[J]. Scientific Reports, 2021, 11(1): 14326.