Artificial Intelligence in Diabetic Eye Disease Screening

Cy, Cheung; Tang, Fang; Dsw, Ting; Gsw, Tan; Ty, Wong

doi:10.22608/apo.201976

Cited by 32 publications

(24 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The introduction of AI models for retinal image interpretation in the screening of DR is rapid evolving. 65,66 Historically, AI systems have relied on 'hard-coded' image-processing and specific lesion detection algorithms. More recent computing advances have been capable of delivering outstanding results through Deep Learning (DL) processes that enable AI systems to self-learn and improve with increasing number of images evaluated.…”

Section: Approaches To Retinal Image Analysis and Prediction Of Dr Prmentioning

confidence: 99%

Screening for diabetic retinopathy: new perspectives and challenges

Vujosevic

Aldington

Silva

et al. 2020

The Lancet Diabetes & Endocrinology

358

238

View full text Add to dashboard Cite

Although all stages of diabetic retinopathy (DR) have been declining since 1980 in populations with improved diabetes control, the crude prevalence of visual impairment and blindness caused by DR has increased in recent years. This is mainly due to the global increase of type 2 diabetes. Screening for DR is essential to detect referable cases that need timely full ophthalmic examination and treatment in order to avoid permanent visual loss. In recent years personalized screening intervals taking into account several risk factors has been proposed with a good costeffectiveness ratios. However, limited resources are available for nationwide screening programs. New technologies such as scanning confocal ophthalmology with ultrawide field imaging and mobile hand-held devices, tele-ophthalmology for remote grading and artificial intelligence for automated detection and classification of DR are changing screening strategies and improving its cost-effectiveness. The emergent evidence that retinal imaging is useful for identifying subjects at risk of cardiovascular disease or cognitive impairment is also a challenge that could change the concept of DR screening into a more broad examination, not limited to prevent sight-threatening disease. Box. Searching strategy and selection criteria We identified references for this review through searches of PubMed and Google Scholar for articles published in English up to November 7 th , 2019. The key words used included "diabetic retinopathy", "screening of diabetic retinopathy", "retinal imaging", "retinal neurodegeneration", "tele-ophthalmology", "artificial intelligence", "diabetic complications", "diabetic retinopathy and cardiovascular disease", "diabetic retinopathy and dementia". These keywords were used as single search terms or in combination. We also searched the reference list of original articles, clinical guidelines, systematic reviews and meta-analyses for further relevant material. All the authors conducted the literature search but with pre-specified assigned areas. Articles were initially selected for inclusion on the basis of the opinion of the contributing authors, with each section covered by two or three authors with particular expertise. The selected references were reviewed by all the members of the authorship when reading successive drafts. DCCT, UKPDS Chew EY, Davis MD, Danis RP, et al.; Action to Control Cardiovascular Risk in Diabetes Eye Study Research Group. The effects of medical management on the progression of diabetic retinopathy in persons with type 2 diabetes: the Action to Control Cardiovascular Risk in Diabetes (ACCORD) Eye Study. Ophthalmology 2014;121:2443-2451 Action to Control Cardiovascular Risk in Diabetes Follow-On (ACCORDION) Eye Study Group and the Action to Control Cardiovascular Risk in Diabetes Follow-On (ACCORDION) Study Group. Persistent Effects of Intensive Glycemic Control on Retinopathy in Type 2 Diabetes in the Action to Control Cardiovascular Risk in Diabetes (ACCORD) Follow-On Study. Diabetes Care. 2016 Jul;39(7):1089-100 Ot...

show abstract

Section: Approaches To Retinal Image Analysis and Prediction Of Dr Prmentioning

confidence: 99%

Screening for diabetic retinopathy: new perspectives and challenges

Vujosevic

Aldington

Silva

et al. 2020

The Lancet Diabetes & Endocrinology

358

238

View full text Add to dashboard Cite

show abstract

“…In Großbritannien zeigte die Beurteilung von 7-Felder-Aufnahmen einer mydriatischen Funduskamera durch ein Grading Centre eine größere Sensitivität im Vergleich zur binokularen Ophthalmoskopie durch erfahrene Augenärzte (96 % versus 87 %) [16]. In US-amerikanischen Studien wurde die computerunterstützte automatische Bildanalyse von Fundusfotografien geprüft, die 2018 in den zur FDA-Zulassung einer nicht mydriatischen Funduskamera für das Retinopathie-Screening bei Diabetikern führte [17]. Große mediale Aufmerksamkeit erfuhr eine von Google Health untersuchte Deep-Learning-Software, die nach einem auf einer großen Bilddatenbank basierenden Lernprozess eine DR erkennt, die einer Überweisung zum Augenarzt bedarf [18].…”

Section: Fundusfotografieunclassified

Diabetische Retinopathie

Barth¹,

Helbig²

2021

Klin Monbl Augenheilkd

View full text Add to dashboard Cite

ZusammenfassungDie diabetische Retinopathie (DR) ist die häufigste Ursache für schwere Sehbehinderung und Erblindung im erwerbstätigen Alter. Eine subjektive Beeinträchtigung des Sehvermögens tritt häufig erst in fortgeschrittenen Stadien der DR ein. Daher sind Screening-Maßnahmen asymptomatischer Patienten und eine stadiengerechte Behandlung essenziell. Dieser Beitrag gibt einen praxisbezogenen Überblick über diagnostische und therapeutische Prinzipien der nicht-proliferativen und proliferativen Form.

show abstract

“…One of the most obvious extensions of OCTA is in artificial intelligence and automated diagnosis of DR. Expanding the use of artificial intelligence and deep learning techniques in diabetic eye screenings would improve efficiency and drive down costs, which jointly have the potential to improve patient outcomes amid the diabetes epidemic [165]. This may be especially true with regards to rural areas, where eye care providers are found in lower numbers [166].…”

Section: Future Directionsmentioning

confidence: 99%

Review of OCT Angiography Findings in Diabetic Retinopathy: Insights and Perspectives

Moir

Khanna

Skondra

2021

IJTM

View full text Add to dashboard Cite

Diabetes mellitus (DM), a disorder rapidly growing in prevalence, is linked to the retinal microvasculature complication diabetic retinopathy (DR). As one of the leading global causes of vision impairment and loss, imaging techniques to detect and monitor DR must continue to improve in order to address this growing burden. Optical coherence tomography angiography (OCTA) is a nascent imaging modality that generates three-dimensional visualizations of the retinal and choroidal microvasculature. Compared to fluorescein angiography, the gold-standard imaging modality for retinal vessels, OCTA offers the advantages of being non-invasive, quick, and able to resolve the multiple plexuses within the retina. Quantitative OCTA studies have explored parameters such as vessel density (VD), foveal avascular zone (FAZ), acircularity index, vessel tortuosity (VT), and fractal dimension (FD) amongst DR patients. This review synthesizes the main trends emerging from quantitative OCTA-based studies of DR and interrogates them within the context of DR pathophysiology. We offer a glimpse into how analysis techniques have shifted in the years since OCTA came into existence, while speculating on its future role in clinical practice.

show abstract

Artificial Intelligence in Diabetic Eye Disease Screening

Cited by 32 publications

References 0 publications

Screening for diabetic retinopathy: new perspectives and challenges

Screening for diabetic retinopathy: new perspectives and challenges

Diabetische Retinopathie

Review of OCT Angiography Findings in Diabetic Retinopathy: Insights and Perspectives

Contact Info

Product

Resources

About