Artificial Intelligence in Cornea, Refractive Surgery, and Cataract: Basic Principles, Clinical Applications, and Future Directions

Rampat, Radhika; Deshmukh, Rashmi; Chen, Xin; Ting, Daniel Shu Wei; Said, Dalia G.; Dua, Harminder S.; Ting, Darren S J

doi:10.1097/apo.0000000000000394

Cited by 47 publications

(63 citation statements)

References 149 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The issue with low culture yield in infectious keratitis has been a recurrent clinical theme [1,25,45]. In the future, it is envisaged that novel technologies, including polymerase chain reaction (PCR), [46,47], IVCM [48], next-generation sequencing, [49][50][51], matrix-assisted laser/desorption ionisation-time of flight-mass spectrometry (MALDI-TOF-MS) [14,52] and artificial intelligence-assisted platforms [53][54][55][56] would be able to enhance the diagnostic yield and accuracy of infectious keratitis. As contact lenses serve as an important risk factor for FK, future studies examining the influence of the types and brands of CL on the microbiological profiles and risk of infection would be valuable.…”

Section: Discussionmentioning

confidence: 99%

Clinical Characteristics and Outcomes of Fungal Keratitis in the United Kingdom 2011–2020: A 10-Year Study

Ting

Galal

Kulkarni

et al. 2021

JoF

Self Cite

View full text Add to dashboard Cite

Fungal keratitis (FK) is a serious ocular infection that often poses significant diagnostic and therapeutic dilemmas. This study aimed to examine the causes, clinical characteristics, outcomes, and prognostic factors of FK in the UK. All culture-positive and culture-negative presumed FK (with complete data) that presented to Queen’s Medical Centre, Nottingham, and the Queen Victoria Hospital, East Grinstead, between 2011 and 2020 were included. We included 117 patients (n = 117 eyes) with FK in this study. The mean age was 59.0 ± 19.6 years (range, 4–92 years) and 51.3% of patients were female. Fifty-three fungal isolates were identified from 52 (44.4%) culture-positive cases, with Candida spp. (33, 62.3%), Fusarium spp. (9, 17.0%), and Aspergillus spp. (5, 9.4%) being the most common organisms. Ocular surface disease (60, 51.3%), prior corneal surgery (44, 37.6%), and systemic immunosuppression (42, 35.9%) were the three most common risk factors. Hospitalisation for intensive treatment was required for 95 (81.2%) patients, with a duration of 18.9 ± 16.3 days. Sixty-six (56.4%) patients required additional surgical interventions for eradicating the infection. Emergency therapeutic/tectonic keratoplasty was performed in 29 (24.8%) cases, though 13 (44.8%) of them failed at final follow-up. The final corrected-distance-visual-acuity (CDVA) was 1.67 ± 1.08 logMAR. Multivariable logistic regression analyses demonstrated increased age, large infiltrate size (>3 mm), and poor presenting CDVA (<1.0 logMAR) as significant negative predictive factors for poor visual outcome (CDVA of <1.0 logMAR) and poor corneal healing (>60 days of healing time or occurrence of corneal perforation requiring emergency keratoplasty; all p < 0.05). In conclusion, FK represents a difficult-to-treat ocular infection that often results in poor visual outcomes, with a high need for surgical interventions. Innovative treatment strategies are urgently required to tackle this unmet need.

show abstract

Section: Discussionmentioning

confidence: 99%

Clinical Characteristics and Outcomes of Fungal Keratitis in the United Kingdom 2011–2020: A 10-Year Study

Ting

Galal

Kulkarni

et al. 2021

JoF

Self Cite

View full text Add to dashboard Cite

show abstract

“…3 Technological advancements in aberrometry have revolutionised wavefront-based corneal refractive surgery. 4,5 The correction of aberrations using an excimer laser may benefit highly aberrated eyes encountering visual disturbances such as night vision halos and glare. 6 Various sensor technologies are employed in commercially available aberrometers to capture wavefront data at multiple locations within the pupil, such as Hartmann-Shack, Tscherning, ray tracing and automated retinoscopy.…”

Section: Introductionmentioning

confidence: 99%

Wavefront aberrometry repeatability and agreement—A comparison between Pentacam AXL Wave, iTrace and OPD‐Scan III

Wan

Liao

et al. 2022

Ophthalmic Physiologic Optic

View full text Add to dashboard Cite

Introduction To compare intrasession agreement and repeatability of wavefront aberration measurements from three different aberrometers obtained using Hartmann–Shack, ray tracing and automated retinoscopy methods, as well as their interdevice agreement. Methods Three consecutive measurements were obtained using the Pentacam AXL Wave, the iTrace and the OPD‐Scan III in 47 eyes of 47 patients. Wavefront refractions, root mean square of total aberrations (RMS total), RMS of higher‐order aberrations (HOA) and second‐, third‐ and fourth‐order HOAs were exported for 4‐mm pupils. Wavefront refractions were converted into vector components: M, J0 and J45. Intrasession agreement and repeatability were evaluated using intraclass correlation coefficients (ICCs) and repeatability coefficients (RCs); interdevice agreement was assessed using the Bland–Altman method. Results The intrasession agreement and repeatability of RMS HOA were comparable between the three devices; both the Pentacam AXL Wave and the OPD‐Scan III had better intrasession agreement and repeatability for the RMS total than the iTrace (p ≤ 0.02). Intrasession repeatability for the majority of second‐ and third‐order aberrations was better on the Pentacam AXL Wave than on the iTrace (p ≤ 0.01) and OPD‐Scan III (p ≤ 0.04), although their agreement and repeatability in spherical aberration were comparable (p ≥ 0.24). Significant systematic differences and proportional bias were detected for almost all refraction power vectors and Zernike coefficients among the three devices. Conclusions In this study, all three devices provided good‐to‐excellent agreement for aberration measurements. Most of the individual Zernike's components were not exchangeable between different aberrometers. Their relative intrasession performance in agreement and repeatability varied significantly across different ocular aberration parameters.

show abstract

“…So far, AI has shown promises in a broad range of ophthalmic conditions, including diabetic retinopathy, glaucoma, retinopathy of prematurity, cataract, and corneal diseases, amongst others [ [179] , [180] , [181] , [182] ]. Kuo et al [ 183 ] successfully developed a DL-based corneal photograph model to automatically detect fungal keratitis, with a mean accuracy of ∼70% (which was comparable to ophthalmologists who were not corneal specialist).…”

Section: Future Directionsmentioning

confidence: 99%

Diagnostic armamentarium of infectious keratitis: A comprehensive review

et al. 2022

Self Cite

View full text Add to dashboard Cite

Infectious keratitis (IK) represents the leading cause of corneal blindness worldwide, particularly in developing countries. A good outcome of IK is contingent upon timely and accurate diagnosis followed by appropriate interventions. Currently, IK is primarily diagnosed on clinical grounds supplemented by microbiological investigations such as microscopic examination with stains, and culture and sensitivity testing. Although this is the most widely accepted practice adopted in most regions, such an approach is challenged by several factors, including indistinguishable clinical features shared among different causative organisms, polymicrobial infection, long diagnostic turnaround time, and variably low culture positivity rate. In this review, we aim to provide a comprehensive overview of the current diagnostic armamentarium of IK, encompassing conventional microbiological investigations, molecular diagnostics (including polymerase chain reaction and mass spectrometry), and imaging modalities (including anterior segment optical coherence tomography and in vivo confocal microscopy). We also highlight the potential roles of emerging technologies such as next-generation sequencing, artificial intelligence-assisted platforms. and tele-medicine in shaping the future diagnostic landscape of IK.

show abstract

Artificial Intelligence in Cornea, Refractive Surgery, and Cataract: Basic Principles, Clinical Applications, and Future Directions

Cited by 47 publications

References 149 publications

Clinical Characteristics and Outcomes of Fungal Keratitis in the United Kingdom 2011–2020: A 10-Year Study

Clinical Characteristics and Outcomes of Fungal Keratitis in the United Kingdom 2011–2020: A 10-Year Study

Wavefront aberrometry repeatability and agreement—A comparison between Pentacam AXL Wave, iTrace and OPD‐Scan III

Diagnostic armamentarium of infectious keratitis: A comprehensive review

Contact Info

Product

Resources

About