Hyperspectral Ophthalmoscope Images for the Diagnosis of Diabetic Retinopathy Stage

A methodology that applies hyperspectral imaging (HSI) on ophthalmoscope images to identify diabetic retinopathy (DR) stage is demonstrated. First, an algorithm for HSI image analysis is applied to the average reflectance spectra of simulated arteries and veins in ophthalmoscope images. Second, the average simulated spectra are categorized by using a principal component analysis (PCA) score plot. Third, Beer-Lambert law is applied to calculate vessel oxygen saturation in the ophthalmoscope images, and oxygenation maps are obtained. The average reflectance spectra and PCA results indicate that average reflectance changes with the deterioration of DR. The G-channel gradually decreases because of vascular disease, whereas the R-channel gradually increases with oxygen saturation in the vessels. As DR deteriorates, the oxygen utilization of retinal tissues gradually decreases, and thus oxygen saturation in the veins gradually increases. The sensitivity of diagnosis is based on the severity of retinopathy due to diabetes. Normal, background DR (BDR), pre-proliferative DR (PPDR), and proliferative DR (PDR) are arranged in order of 90.00%, 81.13%, 87.75%, and 93.75%, respectively; the accuracy is 90%, 86%, 86%, 90%, respectively. The F1-scores are 90% (Normal), 83.49% (BDR), 86.86% (PPDR), and 91.83% (PDR), and the accuracy rates are 95%, 91.5%, 93.5%, and 96%, respectively.

[1]  Matthew D Davis,et al.  Diabetic Retinopathy: A clinical overview , 1992, Diabetes Care.

[2]  Mark S Humayun,et al.  NONINVASIVE ASSESSMENT OF RETINAL VASCULAR OXYGEN CONTENT AMONG NORMAL AND DIABETIC HUMAN SUBJECTS: A Study Using Hyperspectral Computed Tomographic Imaging Spectroscopy , 2014, Retina.

[3]  Hsiang-Chen Wang,et al.  Optimal lighting of RGB LEDs for oral cavity detection. , 2012, Optics express.

[4]  Shehzad Khalid,et al.  Identification and classification of microaneurysms for early detection of diabetic retinopathy , 2013, Pattern Recognit..

[5]  J. Shaw,et al.  IDF diabetes atlas: global estimates of the prevalence of diabetes for 2011 and 2030. , 2011, Diabetes research and clinical practice.

[6]  Hsiang-Chen Wang,et al.  Optical perception for detection of cutaneous T-cell lymphoma by multi-spectral imaging , 2014 .

[7]  Shehzad Khalid,et al.  Detection and classification of retinal lesions for grading of diabetic retinopathy , 2014, Comput. Biol. Medicine.

[8]  Meng-Tsan Tsai,et al.  Visual perception enhancement for detection of cancerous oral tissue by multi-spectral imaging , 2013 .

[9]  Mateusz Scibor,et al.  Intravascular oxygen saturation in retinal vessels in normal subjects and open-angle glaucoma subjects. , 2006, Acta ophthalmologica Scandinavica.

[10]  G. Romeo,et al.  Response of capillary cell death to aminoguanidine predicts the development of retinopathy: comparison of diabetes and galactosemia. , 2000, Investigative ophthalmology & visual science.

[11]  M. Lu,et al.  Early identification of esophageal squamous neoplasm by hyperspectral endoscopic imaging , 2018, Scientific Reports.

[12]  Yan Liang,et al.  Deep convolutional neural networks for diabetic retinopathy detection by image classification , 2018, Comput. Electr. Eng..

[13]  Rangaraj M. Rangayyan,et al.  Detection of blood vessels in the retina with multiscale Gabor filters , 2008, J. Electronic Imaging.

[14]  Fang-Hsuan Cheng,et al.  Enhanced visualization of oral cavity for early inflamed tissue detection. , 2010, Optics express.

[15]  L. Aiello,et al.  Diabetic Retinopathy , 1998, Diabetes Care.

[16]  J. Beach,et al.  Oximetry of retinal vessels by dual-wavelength imaging: calibration and influence of pigmentation. , 1999, Journal of applied physiology.

[17]  Y. Yasuno,et al.  Three-dimensional vascular imaging of proliferative diabetic retinopathy by Doppler optical coherence tomography. , 2015, American journal of ophthalmology.

[18]  Dietrich Schweitzer,et al.  Diabetic patients with retinopathy show increased retinal venous oxygen saturation , 2009, Graefe's Archive for Clinical and Experimental Ophthalmology.

[19]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[20]  P. C. Siddalingaswamy,et al.  Automatic detection of multiple oriented blood vessels in retinal images , 2010 .

[21]  S. Burns,et al.  Retinal Blood Velocity and Flow in Early Diabetes and Diabetic Retinopathy Using Adaptive Optics Scanning Laser Ophthalmoscopy , 2019, Journal of clinical medicine.

[22]  R. Unger.  Reinventing type 2 diabetes: pathogenesis, treatment, and prevention. , 2008, JAMA.

[23]  Alon Harris,et al.  Retinal oximetry in primary open-angle glaucoma. , 2011, Investigative ophthalmology & visual science.

[24]  P E Stanga,et al.  High-resolution hyperspectral imaging of the retina with a modified fundus camera. , 2010, Journal francais d'ophtalmologie.

[25]  Yu-Ping Hsiao,et al.  Identified early stage mycosis fungoides from psoriasis and atopic dermatitis using non-invasive color contrast enhancement by LEDs lighting , 2015 .

[26]  Praveen Kumar Reddy Maddikunta,et al.  Early Detection of Diabetic Retinopathy Using PCA-Firefly Based Deep Learning Model , 2020, Electronics.

[27]  R. Kowluru,et al.  Effect of long-term administration of alpha-lipoic acid on retinal capillary cell death and the development of retinopathy in diabetic rats. , 2004, Diabetes.

[28]  T. Wong,et al.  Update on animal models of diabetic retinopathy: from molecular approaches to mice and higher mammals , 2012, Disease Models & Mechanisms.

[29]  Chie-Tong Kuo,et al.  Diagnosis of Human Bladder Cancer Cells at Different Stages Using Multispectral Imaging Microscopy , 2014, IEEE Journal of Selected Topics in Quantum Electronics.

[30]  Shuan-Yu Huang,et al.  Identifying the incidence level of periodontal disease through hyperspectral imaging , 2018, Optical and Quantum Electronics.

[31]  Jesse J. Jung,et al.  Long-Term Visual Outcomes for a Treat and Extend Anti-Vascular Endothelial Growth Factor Regimen in Eyes with Neovascular Age-Related Macular Degeneration , 2015, Journal of clinical medicine.

[32]  Jamshid Dehmeshki,et al.  Genetic algorithm based feature selection combined with dual classification for the automated detection of proliferative diabetic retinopathy , 2015, Comput. Medical Imaging Graph..

[33]  G. Querques,et al.  Multimodal Imaging Assessment of Vascular and Neurodegenerative Retinal Alterations in Type 1 Diabetic Patients without Fundoscopic Signs of Diabetic Retinopathy , 2019, Journal of clinical medicine.

[34]  Se Woon Cho,et al.  Aiding the Diagnosis of Diabetic and Hypertensive Retinopathy Using Artificial Intelligence-Based Semantic Segmentation , 2019, Journal of clinical medicine.

[35]  R. Simó,et al.  Intravitreous anti-VEGF for diabetic retinopathy: hopes and fears for a new therapeutic strategy , 2008, Diabetologia.

[36]  Isabelle Bloch,et al.  A Morphological Approach for Vessel Segmentation in Eye Fundus Images, with Quantitative Evaluation , 2011 .

[37]  T. Sano,et al.  [Diabetic retinopathy]. , 2001, Nihon rinsho. Japanese journal of clinical medicine.

[38]  Paul Geladi,et al.  Principal Component Analysis , 1987, Comprehensive Chemometrics.

[39]  D. Guyer,et al.  Pegaptanib, a targeted anti-VEGF aptamer for ocular vascular disease , 2006, Nature Reviews Drug Discovery.

[40]  Einar Stefánsson,et al.  Retinal oxygen saturation is altered in diabetic retinopathy , 2011, British Journal of Ophthalmology.

[41]  D. Weinberger,et al.  Indocyanine green angiographic findings in nonproliferative diabetic retinopathy. , 1998, American journal of ophthalmology.

[42]  David J Browning,et al.  Comparison of the clinical diagnosis of diabetic macular edema with diagnosis by optical coherence tomography. , 2004, Ophthalmology.