Artificial intelligence applications in different imaging modalities for corneal topography

Shanthi, S. Anita; Aruljyothi, Lokeshwari; Balasundaram, Manohar Babu; Janakiraman, Anuja; Nirmaladevi, K.; Pyingkodi, M.

doi:10.1016/j.survophthal.2021.08.004

Cited by 21 publications

(12 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Published systematic reviews of AI in keratoconus diagnosis draw similar conclusions regarding accuracy (19,21,22). The studies in keratoconus diagnosis report high sensitivity (0.89-1.00), speci city (0.82-1.00), and area under the curve (AUC, 0.87-1.00) with the use of AI (21).…”

Section: Reddy Et Al (2022) Concluded That Keratoconus Progression Ca...mentioning

confidence: 66%

Artificial intelligence – can technology help predict the progression of keratoconus? A systematic review

Watson,

Jiang,

Durakovic

et al. 2024

Preprint

View full text Add to dashboard Cite

Background Keratoconus in patients can progress at different ages and rates. This creates difficulty in determining optimal timing for follow-up interventions such as corneal cross-linking. Previous studies have shown that artificial intelligence (AI) can accurately diagnose keratoconus. Less is known on AI use in predicting progression of keratoconus. Methods A systematic review of peer-reviewed articles was performed in February 2023 using medical databases (Medline, PubMed, EMBASE, Cochrane) and engineering databases (IEEE Xplore, ACM Digital Library). Studies were included if they were published in peer-reviewed journals, reported at least one accuracy measure, and investigated keratoconus progression rather than diagnosis or treatment efficacy. The outcome measures included accuracy in predicting keratoconus progression, type of AI method, input details, number of parameters and AI algorithm. Results 455 records were identified. Following duplicate removal, abstract and full-text screening, six studies (total eyes n = 3 151; patients n = 5 083; mean proportion of males 62.8%±13.4%; mean age 36.9 ± 18.7 years) were included. AI methods used were convolutional neural networks, machine learning, and random forests. Input modalities included Optical Coherence Tomography (OCTs), Anterior-segment OCTs and Pentacam. Overall, the studies reported good utility of AI [Areas under the Curve (AUC, 0.814–0.93), accuracy (71.5–97.5%), sensitivity (70.9–95.5%) and specificity (41.9–82%)] in predicting keratoconus progression. Conclusion Emerging evidence indicates that AI may have a role in predicting keratoconus progression. Further high-quality studies are needed to establish the utility of AI in clinical practice.

show abstract

Section: Reddy Et Al (2022) Concluded That Keratoconus Progression Ca...mentioning

confidence: 66%

Artificial intelligence – can technology help predict the progression of keratoconus? A systematic review

Watson,

Jiang,

Durakovic

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…A review of the literature on the application of AI to evaluate corneal topography for the diagnosis and early detection of corneal ectasias was recently published [56]. That article summarized significant advances in corneal imaging and the application of AI in KC as viewed by an Eye Care Professional, a biomedical engineer, and a data scientist.…”

Section: Discussionmentioning

confidence: 99%

Accuracy of Machine Learning Assisted Detection of Keratoconus: A Systematic Review and Meta-Analysis

Cao

Verspoor

Sahebjada

et al. 2022

JCM

View full text Add to dashboard Cite

(1) Background: The objective of this review was to synthesize available data on the use of machine learning to evaluate its accuracy (as determined by pooled sensitivity and specificity) in detecting keratoconus (KC), and measure reporting completeness of machine learning models in KC based on TRIPOD (the transparent reporting of multivariable prediction models for individual prognosis or diagnosis) statement. (2) Methods: Two independent reviewers searched the electronic databases for all potential articles on machine learning and KC published prior to 2021. The TRIPOD 29-item checklist was used to evaluate the adherence to reporting guidelines of the studies, and the adherence rate to each item was computed. We conducted a meta-analysis to determine the pooled sensitivity and specificity of machine learning models for detecting KC. (3) Results: Thirty-five studies were included in this review. Thirty studies evaluated machine learning models for detecting KC eyes from controls and 14 studies evaluated machine learning models for detecting early KC eyes from controls. The pooled sensitivity for detecting KC was 0.970 (95% CI 0.949–0.982), with a pooled specificity of 0.985 (95% CI 0.971–0.993), whereas the pooled sensitivity of detecting early KC was 0.882 (95% CI 0.822–0.923), with a pooled specificity of 0.947 (95% CI 0.914–0.967). Between 3% and 48% of TRIPOD items were adhered to in studies, and the average (median) adherence rate for a single TRIPOD item was 23% across all studies. (4) Conclusions: Application of machine learning model has the potential to make the diagnosis and monitoring of KC more efficient, resulting in reduced vision loss to the patients. This review provides current information on the machine learning models that have been developed for detecting KC and early KC. Presently, the machine learning models performed poorly in identifying early KC from control eyes and many of these research studies did not follow established reporting standards, thus resulting in the failure of these clinical translation of these machine learning models. We present possible approaches for future studies for improvement in studies related to both KC and early KC models to more efficiently and widely utilize machine learning models for diagnostic process.

show abstract

“…Several studies have focused on COVID-19, pneumonia detection, and analysis with various algorithms. Most healthcare applications are gaining popularity with highlighted features supported by Artificial intelligence (AI), Machine Learning, and Deep Learning [17] , [18] , [19] .…”

Section: Literature Reviewmentioning

confidence: 99%

A deep transfer learning-based convolution neural network model for COVID-19 detection using computed tomography scan images for medical applications

Kathamuthu¹,

Shanthi²,

et al. 2023

Advances in Engineering Software

View full text Add to dashboard Cite

Artificial intelligence applications in different imaging modalities for corneal topography

Cited by 21 publications

References 54 publications

Artificial intelligence – can technology help predict the progression of keratoconus? A systematic review

Artificial intelligence – can technology help predict the progression of keratoconus? A systematic review

Accuracy of Machine Learning Assisted Detection of Keratoconus: A Systematic Review and Meta-Analysis

A deep transfer learning-based convolution neural network model for COVID-19 detection using computed tomography scan images for medical applications

Contact Info

Product

Resources

About