DiaNet: A Deep Learning Based Architecture to Diagnose Diabetes Using Retinal Images Only

Diabetes is one of the leading fatal diseases globally, putting a huge burden on the global healthcare system. Early diagnosis of diabetes is hence, of utmost importance and could save many lives. However, current techniques to determine whether a person has diabetes or has the risk of developing diabetes are primarily reliant upon clinical biomarkers. In this article, we propose a novel deep learning architecture to predict if a person has diabetes or not from a photograph of his/her retina. Using a relatively small-sized dataset, we develop a multi-stage convolutional neural network (CNN)-based model DiaNet that can reach an accuracy level of over 84% on this task, and in doing so, successfully identifies the regions on the retina images that contribute to its decision-making process, as corroborated by the medical experts in the field. This is the first study that highlights the distinguishing capability of the retinal images for diabetes patients in the Qatari population to the best of our knowledge. Comparing the performance of DiaNet against the existing clinical data-based machine learning models, we conclude that the retinal images contain sufficient information to distinguish the Qatari diabetes cohort from the control group. In addition, our study reveals that retinal images may contain prognosis markers for diabetes and other comorbidities like hypertension and ischemic heart disease. The results led us to believe that the inclusion of retinal images into the clinical setup for the diagnosis of diabetes is warranted in the near future.

[1]  Li Fei-Fei,et al.  ImageNet: A large-scale hierarchical image database , 2009, CVPR.

[2]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  R. Malik,et al.  Visual complications in diabetes mellitus: beyond retinopathy , 2017, Diabetic medicine : a journal of the British Diabetic Association.

[4]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[5]  Rishab Gargeya,et al.  Automated Identification of Diabetic Retinopathy Using Deep Learning. , 2017, Ophthalmology.

[6]  Borys Tymchenko,et al.  Deep Learning Approach to Diabetic Retinopathy Detection , 2020, ICPRAM.

[7]  A. Bener,et al.  Predictions Burden of Diabetes and Economics Cost: Contributing Risk Factors of Changing Disease Prevalence and its Pandemic Impact to Qatar. , 2016, Experimental and clinical endocrinology & diabetes : official journal, German Society of Endocrinology [and] German Diabetes Association.

[8]  Ann L. Albright,et al.  Prevalence of diabetic retinopathy in the United States, 2005-2008. , 2010, JAMA.

[9]  Ying Zhu,et al.  Diabetic Retinopathy Detection Using Prognosis of Microaneurysm and Early Diagnosis System for Non-Proliferative Diabetic Retinopathy Based on Deep Learning Algorithms , 2020, IEEE Access.

[10]  Nader Sheibani,et al.  Diabetes and Retinal Vascular Dysfunction , 2014, Journal of ophthalmic & vision research.

[11]  Raghvendra Mall,et al.  Harnessing Qatar Biobank to understand type 2 diabetes and obesity in adult Qataris from the First Qatar Biobank Project , 2018, Journal of Translational Medicine.

[12]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[13]  Tahmina Nasrin Poly,et al.  Deep learning algorithms for detection of diabetic retinopathy in retinal fundus photographs: A systematic review and meta-analysis , 2020, Comput. Methods Programs Biomed..

[14]  T. Wong,et al.  Ten Emerging Trends in the Epidemiology of Diabetic Retinopathy , 2016, Ophthalmic epidemiology.

[15]  S. Al-Kaabi,et al.  Impact of noncommunicable diseases in the State of Qatar , 2015, ClinicoEconomics and outcomes research : CEOR.

[16]  Weihong Deng,et al.  Very deep convolutional neural network based image classification using small training sample size , 2015, 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR).

[17]  P. Elliott,et al.  The Qatar Biobank: background and methods , 2015, BMC Public Health.

[18]  Subhashini Venugopalan,et al.  Predicting Risk of Developing Diabetic Retinopathy using Deep Learning , 2021, The Lancet. Digital health.

[19]  Gowri Srinivasa,et al.  Automated Grading of Diabetic Retinopathy in Retinal Fundus Images using Deep Learning , 2019, 2019 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).

[20]  W. Sa-ngiamvibool,et al.  Classification and Identification of Diabetic Retinopathy Severity Stages in Thai Patients Using Deep Learning Based Convolution Neural Networks , 2019 .

[21]  Sabri Boughorbel,et al.  Automated Classification of Diabetic Retinopathy Severity: A Deep Learning Approach , 2018 .

[22]  B. Klein,et al.  Global Prevalence and Major Risk Factors of Diabetic Retinopathy , 2012, Diabetes Care.

[23]  R. Klein,et al.  Global Prevalence and Major Risk Factors of Diabetic Retinopathy , 2012, Diabetes Care.

[24]  Jorge A Cuadros,et al.  EyePACS: An Adaptable Telemedicine System for Diabetic Retinopathy Screening , 2009, Journal of diabetes science and technology.

[25]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

[26]  Hamza Baali,et al.  Identification of Potential Risk Factors of Diabetes for the Qatari Population , 2020, 2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT).

[27]  Nathan Congdon,et al.  The Prevalence of Diabetic Retinopathy in the United States , 2002 .

[28]  Zumin Shi,et al.  Association of low serum magnesium with diabetes and hypertension: findings from Qatar Biobank Study. , 2019, Diabetes research and clinical practice.

[29]  M. Wintergerst,et al.  Diabetic retinopathy screening using smartphone-based fundus imaging in India. , 2020, Ophthalmology.

[30]  Wei Zhang,et al.  Automated identification and grading system of diabetic retinopathy using deep neural networks , 2019, Knowl. Based Syst..

[31]  Jennifer K. Sun,et al.  Diabetic Retinopathy: A Position Statement by the American Diabetes Association , 2017, Diabetes Care.

[32]  Ashikur Rahman,et al.  Automated Detection of Diabetic Retinopathy using Deep Residual Learning , 2020 .

[33]  Yara T. E. Lechanteur,et al.  Evaluation of a deep learning system for the joint automated detection of diabetic retinopathy and age‐related macular degeneration , 2019, Acta ophthalmologica.

[34]  P. O S I T I O N S T A T E M E N T,et al.  Diagnosis and Classification of Diabetes Mellitus , 2011, Diabetes Care.

[35]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[36]  Gavin C. Cawley,et al.  On Over-fitting in Model Selection and Subsequent Selection Bias in Performance Evaluation , 2010, J. Mach. Learn. Res..

[37]  Leslie N. Smith,et al.  A disciplined approach to neural network hyper-parameters: Part 1 - learning rate, batch size, momentum, and weight decay , 2018, ArXiv.

[38]  J. Naren,et al.  A Detailed Study on Diagnosis and Prediction of Diabetic Retinopathy Using Current Machine Learning and Deep Learning Techniques , 2019 .

[39]  N. Afifi,et al.  Qatar Biobank Cohort Study: Study Design and First Results. , 2019, American journal of epidemiology.

[40]  Subhashini Venugopalan,et al.  Development and Validation of a Deep Learning Algorithm for Detection of Diabetic Retinopathy in Retinal Fundus Photographs. , 2016, JAMA.