Automated analysis of retinal imaging using machine learning techniques for computer vision

Purpose: To propose and to evaluate a quantitative measuring method of meibomian gland (MG) vagueness. Methods: A total of 47 patients (32 female and 15 male, 39.21 AE 11.07 years) with meibomian gland dysfunction (MGD) were recruited to the MGD group, and 47 healthy volunteers were recruited to the control group matched in age and gender. The clinical examinations included ocular surface evaluation, MG function indexes and MG morphological indexes (including MG vagueness value). Reliability and efficacy of MG vagueness value, correlation between vagueness value and relevant variables, and diagnostic efficacy of combining vagueness value with efficacious indexes were all evaluated. Results: The MG vagueness value of the MGD group (19.78 AE 13.17) was significantly lower than that of the control group (31.90 AE 13.15). The vagueness value possessed good between-reader reliability (intraclass correlation coefficient = 0.928 > 0.9), and was correlated with age (r = À0.356), most clinical indexes and the acinar shortest diameter (r = À0.278). The area under the curve (AUC) in the receiver operating characteristic (ROC) curve of vagueness value was 0.766 [95% confidence interval (CI): 0.668-0.864] with sufficient diagnostic efficacy, and the cutoff value was <21. The AUC improved to 0.956 (95% CI: 0.938-0.999), after efficacious indexes (vagueness value, meiboscore and tear breakup time) were combined. Conclusion: Meibomian gland (MG) vagueness is quantifiable. The MG vagueness value proposed in this study has good reliability, a close relationship with MGD clinical features and sufficient diagnostic efficacy. Combining this new index with other indexes commonly used offers an exciting prospect in MGD diagnosis.

show abstract

“…Many studies have explored the use of AI to screen retina diseases, such as diabetic retinopathy (De Fauw et al. ; Schmidt‐Erfurth et al. ).…”

Section: Discussionmentioning

confidence: 99%

The quantitative measuring method of meibomian gland vagueness and diagnostic efficacy of meibomian gland index combination

Yin

Gong

2019

Acta Ophthalmologica

View full text Add to dashboard Cite

show abstract

“…8 Advanced means of medical image analysis are now beginning to offer tools that are not only able to automatically and reliably segment even discrete morphologic features and to recognize associations between markers, identifying pathophysiological patterns, but also to offer distinct predictions of the future disease course. 9 In this article, we present a method to identify the individual risk of conversion of intermediate AMD to the advanced stages, that is, neovascular AMD or geographic atrophy (GA). We describe how modern means of artificial intelligence such as machine learning techniques can be used to predict the individual risk of disease progression in a common and severe disease such as AMD based mainly on morphologic imaging biomarkers but also on integrating genetic and demographic parameters.…”

mentioning

confidence: 99%

Prediction of Individual Disease Conversion in Early AMD Using Artificial Intelligence

Schmidt‐Erfurth

Waldstein

Klimscha

et al. 2018

Invest. Ophthalmol. Vis. Sci.

161

140

View full text Add to dashboard Cite

show abstract

“…Retinal fundus imaging with an NMC and automated grading take only 10 minutes, can be performed at the point of care and may obviate a separate visit to an ophthalmologist [55]. Automated analysis of OCT images through use of DL is being explored in a collaborative project between Moorfields Eye Hospital and Google DeepMind [56], and in other retinal centers of excellence [57].…”

Section: Automated Disease Detectionmentioning

confidence: 99%

Fundamental principles of an effective diabetic retinopathy screening program

et al. 2020

View full text Add to dashboard Cite

Background Diabetic retinopathy (DR) is the leading cause of blindness among working-age adults worldwide. Early detection and treatment are necessary to forestall vision loss from DR. Methods A working group of ophthalmic and diabetes experts was established to develop a consensus on the key principles of an effective DR screening program. Recommendations are based on analysis of a structured literature review. Results The recommendations for implementing an effective DR screening program are: (1) Examination methods must be suitable for the screening region, and DR classification/grading systems must be systematic and uniformly applied. Twofield retinal imaging is sufficient for DR screening and is preferable to seven-field imaging, and referable DR should be well defined and reliably identifiable by qualified screening staff; (2) in many countries/regions, screening can and should take place outside the ophthalmology clinic; (3) screening staff should be accredited and show evidence of ongoing training; (4) screening programs should adhere to relevant national quality assurance standards; (5) studies that use uniform definitions of risk to determine optimum risk-based screening intervals are required; (6) technology infrastructure should be in place to ensure that high-quality images can be stored securely to protect patient information; (7) although screening for diabetic macular edema (DME) in conjunction with DR evaluations may have merit, there is currently insufficient evidence to support implementation of programs solely for DME screening. Conclusion Use of these recommendations may yield more effective DR screening programs that reduce the risk of vision loss worldwide.

show abstract

Automated analysis of retinal imaging using machine learning techniques for computer vision

Cited by 27 publications

References 12 publications

The quantitative measuring method of meibomian gland vagueness and diagnostic efficacy of meibomian gland index combination

The quantitative measuring method of meibomian gland vagueness and diagnostic efficacy of meibomian gland index combination

Prediction of Individual Disease Conversion in Early AMD Using Artificial Intelligence

Fundamental principles of an effective diabetic retinopathy screening program

Contact Info

Product

Resources

About