Deep learning-based Diabetic Retinopathy assessment on embedded system

Diabetic Retinopathy (DR) is a disease which affect the vision ability. The observation by an ophthalmologist usually conducted by analyzing the retinal images of the patient which are marked by some DR features. However some misdiagnosis are usually found due to human error. Here, a deep learning-based low-cost embedded system is established to assist the doctor for grading the severity of the DR from the retinal images. A compact deep learning algorithm named Deep-DR-Net which fits on a small embedded board is afterwards proposed for such purposes. In the heart of Deep-DR-Net, a cascaded encoder-classifier network is arranged using residual style for ensuring the small model size. The usage of different types of convolutional layers subsequently guarantees the features richness of the network for differentiating the grade of the DR. Experimental results show the capability of the proposed system for detecting the existence as well as grading the severity of the DR symptomps.

[1]  U. Rajendra Acharya,et al.  Evolutionary algorithm based classifier parameter tuning for automatic diabetic retinopathy grading: A hybrid feature extraction approach , 2013, Knowl. Based Syst..

[2]  Annupan Rodtook,et al.  Automatic exudates detection in retinal images using efficient integrated approaches , 2014, Signal and Information Processing Association Annual Summit and Conference (APSIPA), 2014 Asia-Pacific.

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Richard L. Abbott.  Preferred practice pattern changes: author reply , 2004 .

[6]  J Conrath,et al.  Foveal avascular zone in diabetic retinopathy: quantitative vs qualitative assessment , 2005, Eye.

[7]  Lawrence A. Yannuzzi,et al.  Fluorescein and ICG Angiography: Textbook and Atlas , 1998 .

[8]  P. Zimmet,et al.  Definition, diagnosis and classification of diabetes mellitus and its complications. Part 1: diagnosis and classification of diabetes mellitus. Provisional report of a WHO Consultation , 1998, Diabetic medicine : a journal of the British Diabetic Association.

[9]  Eugenio Culurciello,et al.  ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation , 2016, ArXiv.

[10]  P. L. Hildebrand,et al.  Preferred practice patterns. , 1996, Ophthalmology.

[11]  Sergey Ioffe,et al.  Rethinking the Inception Architecture for Computer Vision , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[13]  Mouloud Adel,et al.  Semi‐automated detection of the foveal avascular zone in fluorescein angiograms in diabetes mellitus , 2006, Clinical & experimental ophthalmology.

[14]  Hermawan Nugroho,et al.  Analysis of foveal avascular zone in colour fundus images for grading of diabetic retinopathy severity , 2010, 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology.

[15]  M Palta,et al.  Abnormalities of the foveal avascular zone in diabetic retinopathy. , 1984, Archives of ophthalmology.

[16]  B V Howard,et al.  Relationships between insulin secretion, insulin action, and fasting plasma glucose concentration in nondiabetic and noninsulin-dependent diabetic subjects. , 1984, The Journal of clinical investigation.

[17]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[18]  J. Shaw,et al.  Global estimates of diabetes prevalence for 2013 and projections for 2035. , 2014, Diabetes Research and Clinical Practice.