Insights into the growing popularity of artificial intelligence in ophthalmology

Dutt, Sreetama; Sivaraman, Anand; Savoy, Florian M.; Rajalakshmi, Ramachandran

doi:10.4103/ijo.ijo_1754_19

Cited by 27 publications

(4 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, in situations of limited resources, the use of alternative AI models for the screening and early detection of DR, resulting in prompt referral for treatment, appears reasonable, given its performance in detecting vision-threatening DR and diabetic macular edema when used in population screening for DR [130]. In DR, DL algorithms diagnose microaneurysms, hemorrhages, hard exudates, cotton-wool spots, and neovascularization in people with DR [131].…”

Section: Artificial Intelligence In Macular Imagingmentioning

confidence: 99%

Macular Imaging

Ndubuisi Okonkwo,

Thelma Agweye,

Akanbi

et al. 2024

Macular Diseases - An Update [Working Title]

View full text Add to dashboard Cite

Since its inception, retinal imaging has been vital in documenting and understanding macular diseases. The early thinking was to document retinal pathology as it became possible to visualize the retina using an ophthalmoscope. This reasoning quickly evolved into the need to monitor disease evolution and treatment changes using digital images. With further rapid advancement in imaging technology, it has become possible to visualize and image at a subcellular level, the macula, in health and disease. Technological advances have resulted in the scanning laser ophthalmoscope, optical coherence tomography, and adaptive optics incorporation into imaging. The “dye” and “non-dye” based evaluation of retinal vasculature has improved our understanding of various macula and retinovascular diseases. The fundus photograph and optical coherence tomography are the most utilized technologies for imaging the macula. With an expected increase in diabetic retinopathy and macular degeneration patients, more macular imaging will be done in years to come. Consequently, more macula image data will be available for data analysis using artificial intelligence, improving our predictive ability and personalization. Therefore, macular imaging will assume increasing significance and imaging techniques for the macula should be known and understood. This chapter provides an exhaustive list of common and less-known imaging techniques for macular imaging and an overview of their use in evaluating the macula in clinical practice and research.

show abstract

Section: Artificial Intelligence In Macular Imagingmentioning

confidence: 99%

Macular Imaging

Ndubuisi Okonkwo,

Thelma Agweye,

Akanbi

et al. 2024

Macular Diseases - An Update [Working Title]

View full text Add to dashboard Cite

show abstract

“…Through recent advances in AI and the rapid progression of analytic techniques, researchers are trying to overcome the main pitfalls of clinical testing, such as the long time required for acquisition and the need for skillful maneuvers [105]. The aim of the computerization of clinical tests is to help clinicians to increase accuracy and reduce the time taken to form a diagnosis.…”

Section: Image Modality Based Computerized Detection Techniquesmentioning

confidence: 99%

Advances in the Noninvasive Diagnosis of Dry Eye Disease

et al. 2021

View full text Add to dashboard Cite

Dry eye disease (DED) is a multifactorial disease that represents one of the most common ophthalmologic conditions encountered in everyday clinical practice. Traditional diagnostic tests for DED, such as subjective questionnaires, tear film break-up time and the Schirmer test, are often associated with poor reproducibility and reliability, which make the diagnosis, follow-up, and management of the disease challenging. New advances in imaging technologies enable objective and reproducible measurements of DED parameters, thus making the diagnosis a multimodal imaging-based process. The aim of this review is to summarize all the current and emerging diagnostic tools available for the diagnosis and monitoring of DED, such as non-invasive tear breakup time, thermography, anterior segment optical coherence tomography, meibography, interferometry, in vivo confocal microscopy, and optical quality assessment. Although there is not a gold standard imaging technique, new multi-imaging-integrated devices are precious instruments to help clinicians to better cope with the diagnostic complexity of DED.

show abstract

“…The growing prevalence of using artificial intelligence (AI) for everything is visible virtually in all aspects of modern life. In the accompanying article,[ 1 ] the authors examined the rising popularity of AI in ophthalmology[ 2 ] by tracing its history across multiple research databases and various crucial studies. They also emphasized the dangers of implicitly trusting machine learning (ML) and AI-based technology.…”

mentioning

confidence: 99%

Commentary: Artificial intelligence for everything: Can we trust it?

Kuriakose

2020

Indian J Ophthalmol

View full text Add to dashboard Cite

Insights into the growing popularity of artificial intelligence in ophthalmology

Cited by 27 publications

References 33 publications

Macular Imaging

Macular Imaging

Advances in the Noninvasive Diagnosis of Dry Eye Disease

Commentary: Artificial intelligence for everything: Can we trust it?

Contact Info

Product

Resources

About