Microaneurysm detection in fundus images based on a novel end-to-end convolutional neural network

• Autorzy: Liao Yinhan , Xia Haiying , Song Shuxiang , Li Haisheng

Identyfikatory

DOI

10.1016/j.bbe.2021.04.005

• Języki publikacji: EN

Abstrakty

EN

Microaneurysms are the earliest symptom of diabetic retinopathy and play an important role in the screening of diabetic retinopathy. However, because of the complex background, automatic detection microaneurysm in fundus images is a challenging task. Firstly, motivated by the characteristics of microaneurysm, a novel deep convolutional encoder-decoder network for microaneurysm detection is designed to locate the MAs by the differences between the skip connection in the network. Then, a weighted dice loss, termed the smooth dice loss, is presented to put more focus on misclassified microaneurysms. Finally, an activation function with a long tail is used to produce an accurate probability map for MA detection. Plenty of experiments, conducted on the Retinopathy Online Challenge data-set and the e-ophtha-MA dataset, demonstrate that the proposed model achieves the comparable performance to the existing state-of-the-art methods on microaneurysm detection with only one-hundredth the running time compared with its counterparts. The proposed method is simple and effective, guarantees the performance while shortening the test time. It indicates the potential application in the auxiliary diagnosis of diabetic retinopathy screening.

Słowa kluczowe

EN

deep learning; computer aided diagnosis; diabetic retinopathy screening; microaneurysm detection; encoder-decoder

PL

uczenie głębokie; diagnoza wspomagana komputerowo; retinopatia cukrzycowa

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 2
• Strony: 589--604
• Opis fizyczny: Bibliogr. 49 poz., rys., tab., wykr.

Twórcy

autor

Liao Yinhan

• College of Electronics Engineering, Guangxi Normal University, Guilin, China

autor

Xia Haiying

• College of Electronics Engineering, Guangxi Normal University, Guilin 541004, China

autor

Song Shuxiang

• College of Electronics Engineering, Guangxi Normal University, Guilin, China

autor

Li Haisheng

• College of Electronics Engineering, Guangxi Normal University, Guilin, China

Bibliografia

• [1] Wang B, Congdon N, Bourne R, et al. Burden of vision loss associated with eye disease in China 1990–2020: findings from the Global Burden of Disease Study 2015. Br J Ophthalmol 2018;102(2):220–4. https://doi.org/10.1136/ bjophthalmol-2017-310333.
• [2] International Diabetes Federation, IDF Diabetes Atlas. 9th Edition, 2019. Brussels, Belgium, https://www.diabetesatlas. org/upload/resources/2019/IDF_Atlas_9th_Edition_2019.pdf.
• [3] Kausu TR, Gopi VP, Wahid KA, et al. Combination of clinical and multiresolution features for glaucoma detection and its classification using fundus images. Biocybern Biomed Eng 2018;38(2). https://doi.org/10.1016/j.bbe.2018.02.003.
• [4] Tian C, Fang T, Fan Y, et al. Multi-path convolutional neural network in fundus segmentation of blood vessels - ScienceDirect. Biocybern Biomed Eng 2020;40(2):583–95. https://doi.org/10.1016/j.bbe.2020.01.011.
• [5] Pachade S, Porwal P, Kokare M, et al. Retinal vasculature segmentation and measurement framework for color fundus and SLO images. Biocybern Biomed Eng 2020. https://doi.org/ 10.1016/j.bbe.2020.03.001.
• [6] Christodoulidis A, Hurtut T, Tahar HB, et al. A multi-scale tensor voting approach for small retinal vessel segmentation in high resolution fundus images. Comput Med Imaging Graph 2016:28–43. https://doi.org/10.1016/ j.compmedimag.2016.06.001.
• [7] Xu X., Tan T., Xu F. An Improved U-Net Architecture for Simultaneous Arteriole and Venule Segmentation in Fundus Image. Medical Image Understanding and Analysis. MIUA 2018. Communications in Computer and Information Science, vol 894. Springer, Cham. https://doi.org/10.1007/978- 3-319-95921-4_31.
• [8] Lee JC, Nguyen L, Hynan LS, et al. Comparison of 1-field, 2- fields, and 3-fields fundus photography for detection and grading of diabetic retinopathy. J Diabetes Complications 2019;33(12). https://doi.org/10.1016/j.jdiacomp.2019.107441 107441.
• [9] Liu YP, Li Z, Xu C, et al. Referable Diabetic Retinopathy Identification from Eye Fundus Images with Weighted Path for Convolutional Neural Network. Artif Intell Med 2019;99. https://doi.org/10.1016/j.artmed.2019.07.002.
• [10] Sahlsten J, Jaskari J, Kivinen J, et al. Deep Learning Fundus Image Analysis for Diabetic Retinopathy and Macular Edema Grading. Sci Rep 2019. https://doi.org/10.1038/s41598-019- 47181-w.
• [11] Akram MU, Akbar S, Hassan T, et al. Data on Fundus Images for Vessels Segmentation, Detection of Hypertensive Retinopathy, Diabetic Retinopathy and Papilledema. Data in Brief 2020;29. https://doi.org/10.1016/j.dib.2020.105282 105282.
• [12] Porwal P, Pachade S, Kamble R, et al. Indian diabetic retinopathy image dataset (IDRiD): A database for diabetic retinopathy screening research. Data 2018;3(3):25. https://doi. org/10.3390/data3030025.
• [13] Porwal P, Pachade S, Kokare M, et al. IDRiD: Diabetic Retinopathy-Segmentation and Grading Challenge. Med Image Anal 2019;59. https://doi.org/10.1016/ j.media.2019.101561 101561.
• [14] Bresnick GH, Mukamel DB, Dickinson JC, Cole DR. A screening approach to the surveillance of patients with diabetes for the presence of vision-threatening retinopathy. Opthalmology 2000;107(1):19–24. https://doi.org/10.1016/ S0161-6420(99)00010-X.
• [15] American Academy of Ophthalmology, International Clinical Diabetic Retinopathy Disease Severity Scale Detailed Table,2010. http://www.icoph.org/dynamic/attachments/ resources/diabetic-retinopathy-detail.pdf.
• [16] Babiuch Amy, Wykoff Charles Clifton, Hach Jenna et al. Longitudinal panretinal microaneurysm dynamics on ultrawidefield fluorescein angiography in eyes treated with intravitreal aflibercept for proliferative diabetic retinopathy in the recovery study. Br J Ophthalmol, 2020, undefined: undefined. http://dx.doi.org/10.1136/bjophthalmol-2020- 316952.
• [17] Baudoin CE, Lay BJ, Klein JC. Automatic detection of microaneurysms in diabetic fluorescein angiography. Revue d pidémiologie et de Santé Publique 1984;32(3–4):254–61. Available from: https://pubmed.ncbi.nlm.nih.gov/6522738/.
• [18] Spencer T, Olson JA, Mchardy KC, et al. An image-processing strategy for the segmentation and quantification of microaneurysms in fluorescein angiograms of the ocular fundus. Comput Biomed Res 1996;29(4):284–302. https://doi. org/10.1006/cbmr.1996.0021.
• [19] Kande G B, Savithri T S, Subbaiah P V, et al. Automatic Detection of Microaneurysms and Hemorrhages in Digital Fundus Images. Journal of Digital Imaging, 2010, 23(4): 430- 437. https://doi.org/10.1007%2Fs10278-009-9246-0.
• [20] Luo G, Chutatape O, Li H, et al. Abnormality detection in automated mass screening system of diabetic retinopathy[C]. Fourteenth IEEE Symposium on Computer-based Medical Systems. IEEE Computer Society, 2001: 132-137. https://doi. org/10.1109/CBMS.2001.941710.
• [21] Mizutani A, Muramatsu C, Hatanaka Y, et al. Automated microaneurysm detection method based on double-ring filter in retinal fundus images. Proceedings of SPIE, 2009, 7260:72601N-72601N-8. https://doi.org/10.1117/12.813468.
• [22] Xiwei Zhang. Image processing methods for computer-aided screening of diabetic retinopathy. Other. Ecole Nationale Supe´ rieure des Mines de Paris, 2014. English. NNT: 2014ENMP0024ff. tel-01083819ff. https://pastel.archivesouvertes.fr/tel-01083819.
• [23] Wu B, Zhu W, Shi F, et al. Automatic detection of microaneurysms in retinal fundus images. Comput Med Imaging Graph 2017;55:106–12. https://doi.org/10.1016/ j.compmedimag.2016.08.001.
• [24] Javidi M, Pourreza HR, Harati A, et al. Vessel segmentation and microaneurysm detection using discriminative dictionary learning and sparse representation. Comput Methods Programs Biomed 2017;139:93–108. https://doi.org/ 10.1016/j.cmpb.2016.10.015.
• [25] Zhou W, Wu C, Chen D, et al. Automatic Microaneurysm Detection Using the Sparse Principal Component AnalysisBased Unsupervised Classification Method. IEEE Access 2017;5:2563–72. https://doi.org/10.1109/ACCESS.2017.2671918.
• [26] Dashtbozorg B, Zhang J, Huang F, et al. Retinal Microaneurysms Detection Using Local Convergence Index Features. IEEE Trans Image Process 2018;27(7):3300–15. https://doi.org/10.1109/TIP.2018.2815345.
• [27] Derwin DJ, Selvi ST, Singh OJ. Discrimination of microaneurysm in color retinal images using texture descriptors. SIViP 2020;14:369–76. https://doi.org/10.1007/ s11760-019-01566-6.
• [28] Long S, Chen J, Hu A, et al. Microaneurysms detection in color fundus images using machine learning based on directional local contrast. Biomed Eng Online 2020;19(1):21. https://doi. org/10.1186/s12938-020-00766-3.
• [29] Melo T, Mendonça MA, Campilho A. Microaneurysm detection in color eye fundus images for diabetic retinopathy screening. Comput Biol Med 2020;126. https://doi.org/ 10.1016/j.compbiomed.2020.103995 103995.
• [30] Cao W, Czarnek N, Shan J, et al. Microaneurysm detection in fundus images using small image patches and machine learning methods[C]// IEEE Internation Conference on Bioinformatics and Biomedicine. IEEE, 2017. https://doi.org/ 10.1109/BIBM.2017.8217671.
• [31] Mateen M, Wen J, Nasrullah, et al. Fundus image classification using VGG-19 architecture with PCA and SVD. Symmetry 2018;11(1). https://doi.org/10.3390/sym11010001.
• [32] Du J, Zou B, Chen C, et al. Automatic microaneurysm detection in fundus image based on local cross-section transformation and multi-feature fusion. Comput Methods Programs Biomed 2020;196. https://doi.org/10.1016/j. Cmpb.2020.105687 105687.
• [33] Zhang L, Feng S, Duan G, et al. Detection of Microaneurysms in Fundus Images Based on an Attention Mechanism. Genes 2019;10(10):817-. https://doi.org/10.3390/genes10100817.
• [34] Chudzik P, Majumdar S, Calivà Francesco, et al. Microaneurysm detection using deep learning and interleaved freezing. Image Processing. 2018;10574. https:// doi.org/10.1117/12.2293520.
• [35] Eftekhari N, Pourreza HR, Masoudi M, et al. Microaneurysm detection in fundus images using a two-step convolutional neural network. Biomed Eng Online 2019;18(67):1–16. https:// doi.org/10.1186/s12938-019-0675-9.
• [36] Budak U, Şengür A, Guo Y, et al. A novel microaneurysms detection approach based on convolutional neural networks with reinforcement sample learning algorithm. Health Information Science and Systems 2017:5–14. https://doi.org/ 10.1007/s13755-017-0034-9.
• [37] Kumar S, Adarsh A, Kumar B, et al. An automated early diabetic retinopathy detection through improved blood vessel and optic disc segmentation. Opt Laser Technol 2020;121:105815-. https://doi.org/10.1016/j. Optlastec.2019.105815.
• [38] Savelli B, Bria A, Molinara M, et al. A multi-context CNN ensemble for small lesion detection. Artificial Intelligence in Medicine, 2020,103:101749-. https://doi.org/10.1016/j. Artmed.2019.101749.
• [39] Ronneberger O, Fischer P, Brox T, et al. U-Net: Convolutional Networks for Biomedical Image Segmentation[C]. medical image computing and computer assisted intervention, 2015: 234-241. https://doi.org/10.1007/978-3-319-24574-4_28.
• [40] Xie WL, Zhu D, Tong XX. Small target detection method based on visual attention. Comput Eng Appl 2013;49(12):125–8. https://doi.org/10.3778/j.issn.1002-8331.1110-0357.
• [41] Dice LR. Measures of the Amount of Ecologic Association Between Species. Ecology 1945;26(3):297–302. https://doi.org/ 10.2307/1932409.
• [42] Milletari F, Navab N, Ahmadi SA. V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV). p. 565–71. https://doi.org/10.1109/ 3DV.2016.79.
• [43] Lin T, Goyal P, Girshick R, et al. Focal Loss for Dense Object Detection[C]. International conference on computer vision, 2017: 2999-3007. https://doi.org/10.1109/ICCV.2017.324.
• [44] Wang X, Xiao T, Jiang Y, et al. Repulsion Loss: Detecting Pedestrians in a Crowd[C]. computer vision and pattern recognition, 2018: 7774-7783. https://doi.org/10.1109/ CVPR.2018.00811.
• [45] Chollet. F, et al., Keras, 2015, (https://github.com/fchollet/ keras).
• 46] Decencière E, Cazuguel G, Zhang X, et al. TeleOphta: Machine learning and image processing methods for teleophthalmology. IRBM 2013;34(2):196–203. https://doi.org/ 10.1016/j.irbm.2013.01.010.
• [47] Niemeijer M, Ginneken B, Cree MJ, et al. Retinopathy Online Challenge: Automatic Detection of Microaneurysms in Digital Color Fundus Photographs. IEEE Trans Med Imaging 2010;29(1):185–95. https://doi.org/10.1109/TMI.2009.2033909.
• [48] Thompson JD, Manning D, Hogg P, et al. Analyzing data from observer studies in medical imaging research: An introductory guide to free-response techniques. Radiography 2014;20(4):295–9. https://doi.org/10.1016/j.radi.2014.04.005.
• [49] Hillis SL, Chakraborty DP, Orton CG, et al. ROC or FROC? It depends on the research question. Med Phys 2017;44 (5):1603–6. https://doi.org/10.1002/mp.12151.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).