Geographic variation and ethnicity in diabetic retinopathy detection via deep learning

The prevalence of diabetes is on the rise steadily around the globe. Diabetic retinopathy DR is a result of damage to the blood vessels in the retina due to diabetes and its fast treatment is crucial for preventing possible blindness. The diagnosis of DR is done mostly using a comprehensive eye exam, where the eye is dilated for better inspection. Analysis by an ophthalmologist is prone to human error and thus automatic and highly accurate detection of DR is preferred for an earlier and better diagnosis. It is important, however, that automatic detection be accurate for all data collected from patients of different geographic and ethnic backgrounds. In this paper, the automatic detection of DR with a deep learning algorithm is analyzed when geographic and ethnic information of the patients is also integrated into the architecture. It is shown that robust and generalizable DR detection performance is linearly related to the correlation of geographic and ethnic patient information between the training and the testing datasets. The deep learning model created eliminates geographic variation in the detection and works for patients of all ethnicities.

Keywords:

Deep learning, diabetic retinopathy, ethnicity fundus images, geographic variation,

___

[1] Wilkinson CP, Ferris FL, Klein RE, Lee PP, Agardh CD et al. Proposed international clinical diabetic retinopathy and diabetic macular edema disease severity scales. Ophthalmology 2003; 110 (9): 1677-1682. doi:10.1016/S0161- 6420(03)00475-5
[2] Yu F, Sun J, Li A, Cheng J, Wan C et al. Image quality classification for DR screening using deep learning. In: 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC); Seogwipo, South Korea; 2017. pp. 664–667. doi: 10.1109/EMBC.2017.8036912
[3] Kanungo YS, Srinivasan B, Choudhary S. Detecting diabetic retinopathy using deep learning. In: 2nd IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT); Bangalore, India; 2017. pp. 801–804. doi: 10.1109/RTEICT.2017.8256708
[4] Kaymak S, Serener A. Automated age-related macular degeneration and diabetic macular edema detection on OCT images using deep learning. In: 14th IEEE International Conference on Intelligent Computer Communication and Processing (ICCP); Cluj-Napoca, Romania; 2018. pp. 265–269. doi: 10.1109/ICCP.2018.8516635
[5] He K, Zhang X, Ren S, Sun J. Deep residual Learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Las Vegas, NV, USA; 2016. pp. 770–778. doi: 10.1109/CVPR.2016.90
[6] Szegedy C, Liu W, Jia Y, Sermanet P, Reed S et al. Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Boston, MA, USA; 2015. pp. 1–9. doi: 10.1109/CVPR.2015.7298594
[7] Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Las Vegas, NV, USA; 2016. pp. 2818–2826. doi: 10.1109/CVPR.2016.308
[8] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations; San Diego, CA, USA; 2015.
[9] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems; Lake Tahoe, NV, USA; 2012. pp. 1097-1105.
[10] Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Honolulu, HI, USA; 2017. pp. 2261–2269. doi: 10.1109/CVPR.2017.243
[11] Abràmoff MD, Niemeijer M, Russell SR. Automated detection of diabetic retinopathy: barriers to translation into clinical practice. Expert Review of Medical Devices 2010; 7 (2): 287–296. doi: 10.1586/erd.09.76
[12] Giancardo L, Meriaudeau F, Karnowski TP, Li Y, Garg S et al. Exudate-based diabetic macular edema detection in fundus images using publicly available datasets. Medical Image Analysis 2012; 16 (1): 216–226. doi: 10.1016/j.media.2011.07.004
[13] Ting DSW, Cheung CYL, Lim G, Tan GSW, Quang ND et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA 2017; 318 (22): 2211-2223. doi: 10.1001/jama.2017.18152
[14] Gargeya R, Leng T. Automated identification of diabetic retinopathy using deep learning. Ophthalmology 2017; 124 (7): 962–969. doi: 10.1016/j.ophtha.2017.02.008
[15] Bourne RRA. Ethnicity and ocular imaging. Eye 2011; 25 (3): 297–300. doi: 10.1038/eye.2010.187
[16] Decencière E, Zhang X, Cazuguel G, Lay B, Cochener B et al. Feedback on a publicly distributed image database: the MESSIDOR database. Image Analysis & Stereology 2014; 33 (3): 231-234. doi: 10.5566/ias.1155
[17] Decencière E, Cazuguel G, Zhang X, Thibault G, Klein JC et al. TeleOphta: machine learning and image processing methods for teleophthalmology. IRBM 2013; 34 (2): 196–203. doi: 10.1016/j.irbm.2013.01.010
[18] Budai A, Bock R, Maier A, Hornegger J, Michelson G. Robust vessel segmentation in fundus images. International Journal of Biomedical Imaging 2013; 2013: 1–11. doi: 10.1155/2013/154860
[19] Porwal P, Pachade S, Kamble R, Kokare M, Deshmukh G et al. Indian diabetic retinopathy image dataset (IDRiD): a database for diabetic retinopathy screening research. Data 2018; 3 (3): 25. doi: 10.3390/data3030025
[20] Cree MJ, Gamble E, Cornforth D. Color normalisation to reduce inter-patient and intra-patient variability in microaneurysm detection in color retinal images. In: ARPS Workshop on Digital Image Computing (WDIC); Brisbane, Australia; 2005. pp. 163–168.
[21] Seoud L, Hurtut T, Chelbi J, Cheriet F, Langlois JMP. Red lesion detection using dynamic shape features for diabetic retinopathy screening. IEEE Transactions on Medical Imaging 2016; 35 (4): 1116–1126. doi: 10.1109/TMI.2015.2509785
[22] Pires R, Jelinek HF, Wainer J, Valle E, Rocha A. Advancing bag-of-visual-words representations for lesion classification in retinal images. PLoS ONE 2014; 9 (6): e96814. doi: 10.1371/journal.pone.0096814
[23] Orlando JI, Prokofyeva E, del Fresno M, Blaschko MB. An ensemble deep learning based approach for red lesion detection in fundus images. Computer Methods and Programs in Biomedicine 2018; 153: 115–127. doi: 10.1016/j.cmpb.2017.10.017
[24] van Grinsven MJJP, van Ginneken B, Hoyng CB, Theelen T, Sánchez CI. Fast convolutional neural network training using selective data sampling: application to hemorrhage detection in color fundus images. IEEE Transactions on Medical Imaging 2016; 35 (5): 1273–1284. doi: 10.1109/TMI.2016.2526689
[25] Niemeijer M, Staal J, van Ginneken B, Loog M, Abràmoff MD. Comparative study of retinal vessel segmentation methods on a new publicly available database. In: Medical Imaging 2004: Image Processing; San Diego, CA, USA; 2004. pp. 648-656. doi: 10.1117/12.535349
[26] Kauppi T, Kalesnykiene V, Kamarainen JK, Lensu L, Sorri I et al. The DIARETDB1 diabetic retinopathy database and evaluation protocol. In: Proceedings of the British Machine Vision Conference; Warwick, UK; 2007. pp. 15.1- 15.10. doi: 10.5244/C.21.15
[27] Cuadros J, Bresnick G. EyePACS: an adaptable telemedicine system for diabetic retinopathy screening. Journal of Diabetes Science and Technology 2009; 3 (3): 509–516. doi: 10.1177/193229680900300315
[28] Quellec G, Charrière K, Boudi Y, Cochener B, Lamard M. Deep image mining for diabetic retinopathy screening. Medical Image Analysis 2017; 39: 178–193. doi: 10.1016/j.media.2017.04.012
[29] Pratt H, Coenen F, Broadbent DM, Harding SP, Zheng Y. Convolutional neural networks for diabetic retinopathy. Procedia Computer Science 2016; 90: 200–205. doi: 10.1016/j.procs.2016.07.014
[30] Doshi D, Shenoy A, Sidhpura D, Gharpure P. Diabetic retinopathy detection using deep convolutional neural networks. In: IEEE International Conference on Computing, Analytics and Security Trends (CAST); Pune, India; 2016. pp. 261–266. doi: 10.1109/CAST.2016.7914977
[31] Fleming A, Philip S, Goatman K, Prescott G, Sharp P et al. The evidence for automated grading in diabetic retinopathy screening. Current Diabetes Reviews 2011; 7 (4): 246–252. doi: 10.2174/157339911796397802
[32] Abràmoff MD, Folk JC, Han DP, Walker JD, Williams DF et al. Automated analysis of retinal images for detection of referable diabetic retinopathy. JAMA Ophthalmology 2013; 131 (3): 351-357. doi: 10.1001/jamaophthalmol.2013.1743
[33] Gulshan V, Peng L, Coram M, Stumpe MC, Wu D et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 2016; 316 (22): 2402–2410. doi: 10.1001/jama.2016.17216
[34] Ghosh R, Ghosh K, Maitra S. Automatic detection and classification of diabetic retinopathy stages using CNN. In: 4th IEEE International Conference on Signal Processing and Integrated Networks (SPIN); Noida, India; 2017. pp. 550–554. doi: 10.1109/SPIN.2017.8050011
[35] Seoud L, Hurtut T, Chelbi J, Cheriet F, Langlois JMP. Red lesion detection using dynamic shape features for diabetic retinopathy screening. IEEE Transactions on Medical Imaging 2016; 35 (4): 1116–1126. doi: 10.1109/TMI.2015.2509785

Turkish Journal of Electrical Engineering and Computer Science-Cover

ISSN: 1300-0632
Yayın Aralığı: Yılda 6 Sayı
Yayıncı: TÜBİTAK

Arşiv