The Diagnostic Accuracy of an Intelligent and Automated Fundus Disease Image Assessment System with Lesion Quantitative Function (SmartEye) in Diabetic Patients

Abstract

Background With the diabetes mellitus (DM) prevalence increasing annually, the human grading of retinal images to evaluate DR has posed a substantial burden worldwide. SmartEye is a recently developed fundus image processing and analysis system with lesion quantification function for DR screening. It is sensitive to the lesion area and can automatically identify the lesion position and size. We reported the diabetic retinopathy (DR) grading results of SmartEye versus ophthalmologists in analyzing images captured with non-mydriatic fundus cameras in community healthcare centers, as well as DR lesion quantitative analysis results on different disease stages. Methods This is a cross-sectional study. All the fundus images were collected from the Shanghai Diabetic Eye Study in Diabetics (SDES) program from Apr 2016 to Aug 2017. 19904 fundus images were acquired from 6013 diabetic patients. The grading results of ophthalmologists and SmartEye are compared. Lesion quantification of several images at different DR stages is also presented. Results The sensitivity for diagnosing no DR, mild NPDR (non-proliferative diabetic retinopathy), moderate NPDR, severe NPDR, PDR (proliferative diabetic retinopathy) are 86.19%, 83.18%, 88.64%, 89.59%, and 85.02%. The specificity are 63.07%, 70.96%, 64.16%, 70.38%, and 74.79%, respectively. The AUC are PDR, 0.80 (0.79, 0.81); severe NPDR, 0.80 (0.79, 0.80); moderate NPDR, 0.77 (0.76, 0.77); and mild NPDR, 0.78 (0.77, 0.79). Lesion quantification results showed that the total hemorrhage area, maximum hemorrhage area, total exudation area, and maximum exudation area increase with DR severity. Conclusions SmartEye has a high diagnostic accuracy in DR screening program using non-mydriatic fundus cameras. SmartEye quantitative analysis may be an innovative and promising method of DR diagnosis and grading.

Multi-label classification of fundus images based on graph convolutional network

“…FFA can clearly reflect the pathology of the blood vessels in the retina fundus, but it takes a long time and may cause a variety of adverse reactions [4,5]. Therefore, compared with FFA, fundus photography of the retinal is often used in the researches of fundus disease diagnosis algorithms, which makes it possible to carry out large-scale fundus disease screening rapidly and efficiently, and is conducive to the early detection and treatment of DR patients [6][7][8][9][10][11][12][13][14].…”

“…The model predicted the 5-level grades of international diabetic retinopathy and achieved an AUC of 0.986, a sensitivity of 0.971, a specificity of 0.923 on the EyePACS validation dataset [9]. In 2019, Xu et al [10] evaluated DR based on red lesions and bright lesions of fundus images. The model was tested with 19,904 fundus images.…”

Artificial Intelligence‐Based Diagnosis of Diabetes Mellitus: Combining Fundus Photography with Traditional Chinese Medicine Diagnostic Methodology

“…With the advancement in computer vision and artificial intelligence, techniques for measuring eye characteristics using fundus photography have been developed. These techniques can be used to detect eye diseases such as diabetic retinopathy or optic nerve hypoplasia [17,18]. In this study, we detect eye conditions by using fundus photography and the algorithm reported in our previous article [17].…”

“…These techniques can be used to detect eye diseases such as diabetic retinopathy or optic nerve hypoplasia [17,18]. In this study, we detect eye conditions by using fundus photography and the algorithm reported in our previous article [17]. We use the values obtained with the algorithm, which are reported in Table 1.…”

Regional analysis of diabetic retinopathy and co-existing social and demographic factors in the overall population of Poland

“…Early results showed high diagnostic sensitivity and specificity of such systems in DR screening programs in many countries. [ 33,34,35] Limitations of the study concern mostly data used. NHF's data include data provided to all insured people in Poland (in 2017 approx.…”