Novel artificial intelligence index based on Scheimpflug corneal tomography to distinguish subclinical keratoconus from healthy corneas

Repeatability of Epithelium Thickness Measured by an AS-OCT in Different Grades of Keratoconus and Compared to AS-OCT/Placido Topography

PURPOSE

To compare agreement of corneal epithelium thickness (ET) between AS-OCT system (RTVue, Optovue) and AS-OCT/Placido topographer (MS-39, CSO) in eyes with different stages of keratoconus (KC), and to assess the repeatability of RTVue AS-OCT.

DESIGN

Prospective reliability analysis.

METHODS

KC eyes were classified into forme fruste KC (FFKC), mild, moderate, and severe KC. Agreement was evaluated with Bland-Altman plots and 95% limits of agreement (LoA). The repeatability of RTVue was assessed via within-subject standard deviation (Sw), test-retest variability (TRT), coefficient of variation (CoV), and intraclass correlation coefficient (ICC).

RESULTS

A total of 119 KC eyes were enrolled, with 21 being FFKC, 26 mild, 39 moderate, and 34 severe. The 95% LoA ranged between -5.9 and 4.8 µm for center epithelium thickness (CET), between -5.7 and 8.2 µm for thinnest epithelium thickness (TET). At 1-mm measuring points, the 95% LoA of superior, inferior, nasal, and temporal were -4.2 to 4.7 µm, -5.2 to 6.0 µm, -7.9 to 10.2 µm, and -11.2 to 6.0 µm. At 3-mm measuring points, the corresponding values were -2.8 to 9.3 µm, -2.0 to 13.0 µm, -4.6 to 9.6 µm, and -6.3 to 9.7 µm, indicating that the 2 instruments were not interchangeable without adjustment. Despite that the repeatability of RTVue measurements in KC patients were acceptable, repeatability decreased gradually with the peripheralization of the measurement points.

CONCLUSIONS

The 2 OCT-based devices, RTVue and MS-39, do not provide interchangeable measurements of epithelium thickness in KC patients. Repeatability decreases in cases of more severe KC, emphasizing the importance of grading before clinical examination to avoid diagnostic errors.

Role of artificial intelligence, machine learning and deep learning models in corneal disorders - A narrative review

In the last decade, artificial intelligence (AI) has significantly impacted ophthalmology, particularly in managing corneal diseases, a major reversible cause of blindness. This review explores AI's transformative role in the corneal subspecialty, which has adopted advanced technology for superior clinical judgment, early diagnosis, and personalized therapy. While AI's role in anterior segment diseases is less documented compared to glaucoma and retinal pathologies, this review highlights its integration into corneal diagnostics through imaging techniques like slit-lamp biomicroscopy, anterior segment optical coherence tomography (AS-OCT), and in vivo confocal biomicroscopy. AI has been pivotal in refining decision-making and prognosis for conditions such as keratoconus, infectious keratitis, and dystrophies. Multi-disease deep learning neural networks (MDDNs) have shown diagnostic ability in classifying corneal diseases using AS-OCT images, achieving notable metrics like an AUC of 0.910. AI's progress over two decades has significantly improved the accuracy of diagnosing conditions like keratoconus and microbial keratitis. For instance, AI has achieved a 90.7% accuracy rate in classifying bacterial and fungal keratitis and an AUC of 0.910 in differentiating various corneal diseases. Convolutional neural networks (CNNs) have enhanced the analysis of color-coded corneal maps, yielding up to 99.3% diagnostic accuracy for keratoconus. Deep learning algorithms have also shown robust performance in detecting fungal hyphae on in vivo confocal microscopy, with precise quantification of hyphal density. AI models combining tomography scans and visual acuity have demonstrated up to 97% accuracy in keratoconus staging according to the Amsler-Krumeich classification. However, the review acknowledges the limitations of current AI models, including their reliance on binary classification, which may not capture the complexity of real-world clinical presentations with multiple coexisting disorders. Challenges also include dependency on data quality, diverse imaging protocols, and integrating multimodal images for a generalized AI diagnosis. The need for interpretability in AI models is emphasized to foster trust and applicability in clinical settings. Looking ahead, AI has the potential to unravel the intricate mechanisms behind corneal pathologies, reduce healthcare's carbon footprint, and revolutionize diagnostic and management paradigms. Ethical and regulatory considerations will accompany AI's clinical adoption, marking an era where AI not only assists but augments ophthalmic care.

Effect of corneal diameter on preoperative screening results for corneal refractive surgery

AIMS

To investigate the impact of different corneal diameters on corneal morphology and biomechanical outcome during preoperative screening for corneal refractive surgery.

METHODS

A retrospective analysis was conducted on 300 patients who underwent corneal refractive surgery at Eye and ENT Hospital, Fudan University between October 2023 and December 2023. All patients had no history of keratoconus or previous corneal surgery. Patients were categorized into two groups based on corneal topography measurements: (1) normal corneal diameter group (n=159), those with corneal diameter ranging from 11.5 mm to 12.0 mm; (2) abnormal corneal diameter group (n=141), those with corneal diameter smaller than 10.0 mm or larger than 12.5 mm. Corneal thickness, morphologic data, and biomechanical data were measured using Pentacam corneal topography. Correlation analysis was conducted to explore the relationship between corneal diameter and various corneal topography and biomechanical data.

RESULTS

Significant differences were observed in corneal topography data including BFSf (F=43.21), BFSb (F=30.24), Df (F=15.32), Dp (F=32.36), Da (F=9.66), D (F=58.36), PPIavg (F=32.64), and ARTmax (F=12.06) between the groups (P<0.05). Additionally, BFSf, BFSb, Db, Dp, D, and PPIavg exhibited statistically significant differences between any two groups (P<0.05). Significant differences were also found in Df, Da, and ARTmax between small and large corneas, as well as between normal-sized and large corneas (P<0.05). Correlation analysis indicated negative correlations between corneal diameter and A1V (r=-0.12), HCdArcLength (r=-0.17), CBI (r=-0.27), bIOP (r=-0.13), Df (r=-0.025), PPIavg (r=-0.028), and TBI (r=-0.27). Conversely, BFSf (r=0.009), BFSb (r=0.001), PD (r=0.15), and ARTH (r=0.37) displayed positive correlations with corneal diameter.

CONCLUSIONS

Corneal diameter significantly affects preoperative screening for corneal refractive surgery. Smaller corneal diameters exhibit a greater influence on the corneal topography BAD analysis system.

Detecting Keratoconus in Adolescents with Anterior Segment Optical Coherence Tomography

Purpose

Assessing the applicability of an algorithm developed for keratoconus detection in adolescents. This algorithm relies on optical coherence tomography (OCT) and incorporates features related to corneal pachymetric and epithelial thickness alterations.

Methods

We retrospectively reviewed charts of patients under the age of 18 and divided them into four groups according to the Belin-Ambrosio display (Pentacam): normal, manifest, and subclinical keratoconus, as well as very asymmetric eye with normal topography and tomography (VAE-NTT). Corneal and epithelial thickness maps (Cirrus 5000 HD-OCT, Carl Zeiss Meditec, Germany) were evaluated by a human grader. In the first step, if at least one of four parameters (pachymetry minimum (pachy min), pachy minimum-median (min-med), pachy superonasal-inferotemporal (SN-IT), or epithelial (epi SN-IT)) exceeded its cut-off value, the eye was considered as suspect. In the second step, the combined presence of coincident thinning of total cornea and epithelium as well as concentric epithelial thinning lead to the diagnosis of keratoconus. Receiver operating characteristic (ROC) curves were generated to determine area under the curve (AUC), sensitivity, and specificity for the parameters.

Results

The study involved 19 pediatric patients diagnosed with keratoconus, comprising 29 manifest keratoconic eyes, 3 eyes with subclinical keratoconus, and 5 VAE-NTT eyes. In addition, 22 eyes from 11 normal adolescents were included in the analysis. The AUC values of parameters in step 1 were 0.889 for pachy min, 0.997 for pachy min-med, 0.893 for pachy SN-IT, and 0.998 for epi SN-IT. When both steps were performed, this algorithm captured all manifest and subclinical pediatric keratoconic eyes. When all eyes of the keratoconus patients were combined, step 1 had 97.3% sensitivity and step 2 had 100% specificity.

Conclusion

Using this OCT-based approach in adolescents yielded a high level of agreement with the current gold standard, tomography. Using them together, potentially also with other examinations may improve the diagnostic accuracy of KC in the pediatric population. Integration of this approach into the software of the device to facilitate automated evaluations is desired.

Utility of artificial intelligence in the diagnosis and management of keratoconus: a systematic review

Introduction

The application of artificial intelligence (AI) systems in ophthalmology is rapidly expanding. Early detection and management of keratoconus is important for preventing disease progression and the need for corneal transplant. We review studies regarding the utility of AI in the diagnosis and management of keratoconus and other corneal ectasias.

Methods

We conducted a systematic search for relevant original, English-language research studies in the PubMed, Web of Science, Embase, and Cochrane databases from inception to October 31, 2023, using a combination of the following keywords: artificial intelligence, deep learning, machine learning, keratoconus, and corneal ectasia. Case reports, literature reviews, conference proceedings, and editorials were excluded. We extracted the following data from each eligible study: type of AI, input used for training, output, ground truth or reference, dataset size, availability of algorithm/model, availability of dataset, and major study findings.

Results

Ninety-three original research studies were included in this review, with the date of publication ranging from 1994 to 2023. The majority of studies were regarding the use of AI in detecting keratoconus or subclinical keratoconus (n=61). Among studies regarding keratoconus diagnosis, the most common inputs were corneal topography, Scheimpflug-based corneal tomography, and anterior segment-optical coherence tomography. This review also summarized 16 original research studies regarding AI-based assessment of severity and clinical features, 7 studies regarding the prediction of disease progression, and 6 studies regarding the characterization of treatment response. There were only three studies regarding the use of AI in identifying susceptibility genes involved in the etiology and pathogenesis of keratoconus.

Discussion

Algorithms trained on Scheimpflug-based tomography seem promising tools for the early diagnosis of keratoconus that can be particularly applied in low-resource communities. Future studies could investigate the application of AI models trained on multimodal patient information for staging keratoconus severity and tracking disease progression.

Potential applications of artificial intelligence in image analysis in cornea diseases: a review

Artificial intelligence (AI) is an emerging field which could make an intelligent healthcare model a reality and has been garnering traction in the field of medicine, with promising results. There have been recent developments in machine learning and/or deep learning algorithms for applications in ophthalmology-primarily for diabetic retinopathy, and age-related macular degeneration. However, AI research in the field of cornea diseases is relatively new. Algorithms have been described to assist clinicians in diagnosis or detection of cornea conditions such as keratoconus, infectious keratitis and dry eye disease. AI may also be used for segmentation and analysis of cornea imaging or tomography as an adjunctive tool. Despite the potential advantages that these new technologies offer, there are challenges that need to be addressed before they can be integrated into clinical practice. In this review, we aim to summarize current literature and provide an update regarding recent advances in AI technologies pertaining to corneal diseases, and its potential future application, in particular pertaining to image analysis.

Subclinical Keratoconus Detection and Characterization Using Motion-Tracking Brillouin Microscopy

PURPOSE

To characterize focal biomechanical alterations in subclinical keratoconus (SKC) using motion-tracking (MT) Brillouin microscopy and evaluate the ability of MT Brillouin metrics to differentiate eyes with SKC from normal control eyes.

DESIGN

Prospective cross-sectional study.

PARTICIPANTS

Thirty eyes from 30 patients were evaluated, including 15 eyes from 15 bilaterally normal patients and 15 eyes with SKC from 15 patients.

METHODS

All patients underwent Scheimpflug tomography and MT Brillouin microscopy using a custom-built device. Mean and minimum MT Brillouin values within the anterior plateau region and anterior 150 μm were generated. Scheimpflug metrics evaluated included inferior-superior (IS) value, maximum keratometry (Kmax), thinnest corneal thickness, asymmetry indices, Belin/Ambrosio display total deviation, and Ambrosio relational thickness. Receiver operating characteristic (ROC) curves were generated for all Scheimpflug and MT Brillouin metrics evaluated to determine the area under the ROC curve (AUC), sensitivity, and specificity for each variable.

MAIN OUTCOME MEASURES

Discriminative performance based on AUC, sensitivity, and specificity.

RESULTS

No significant differences were found between groups for age, sex, manifest refraction spherical equivalent, corrected distance visual acuity, Kmax, or KISA% index. Among Scheimpflug metrics, significant differences were found between groups for thinnest corneal thickness (556 μm vs. 522 μm; P < 0.001), IS value (0.29 diopter [D] vs. 1.05 D; P < 0.001), index of vertical asymmetry (IVA; 0.10 vs. 0.19; P < 0.001), and keratoconus index (1.01 vs. 1.05; P < 0.001), and no significant differences were found for any other Scheimpflug metric. Among MT Brillouin metrics, clear differences were found between control eyes and eyes with SKC for mean plateau (5.71 GHz vs. 5.68 GHz; P < 0.0001), minimum plateau (5.69 GHz vs. 5.65 GHz; P < 0.0001), mean anterior 150 μm (5.72 GHz vs. 5.68 GHz; P < 0.0001), and minimum anterior 150 μm (5.70 GHz vs. 5.66 GHz; P < 0.001). All MT Brillouin plateau and anterior 150 μm mean and minimum metrics fully differentiated groups (AUC, 1.0 for each), whereas the best performing Scheimpflug metrics were keratoconus index (AUC, 0.91), IS value (AUC, 0.89), and IVA (AUC, 0.88).

CONCLUSIONS

Motion-tracking Brillouin microscopy metrics effectively characterize focal corneal biomechanical alterations in eyes with SKC and clearly differentiated these eyes from control eyes, including eyes that were not differentiated accurately using Scheimpflug metrics.

FINANCIAL DISCLOSURE(S)

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Longitudinal Evaluation of Biomechanical Indices in Fellow Eyes of Patients With Keratoconus Classified as Having Very Asymmetric Ectasia With Normal Topography

PURPOSE

To evaluate the biomechanical longitudinal variability and progression of tomographically normal fellow eyes of patients with keratoconus.

METHODS

Of 513 patients with keratoconus, 30 patients with tomographically normal fellow eyes were included in this study. Tomographic and biomechanical parameters of the Pentacam and Corvis ST (Oculus Optikgeräte GmbH) were analyzed in multiple follow-up examinations, including the ABCD grading, Belin/Ambrósio Enhanced Ectasia total deviation index (BAD-D), Corvis Biomechanical Index (CBI), Corvis Biomechanical Factor (CBiF), and Tomographic and Biomechanical Index (TBI). A mixed regression model was applied. The results were compared to a healthy control group (n = 17) and a keratoconus group (n = 20).

RESULTS

Within a maximum observation period of 3.3 years, no fellow eye (0%) showed a progression to tomographically evident keratoconus. No significant change in tomographic or biomechanical parameters was detected over the study period. The indices BAD-D, CBI, CbiF, and TBI exhibited a certain variability over time, whereas the tomographic ABC parameters and maximum keratometry barely changed. This was also shown in the control group and for all parameters in the keratoconus group, except the TBI.

CONCLUSIONS

During the observation period none of the normal fellow eyes progressed to tomographically detectable keratoconus. However, biomechanical parameters CBI, CbiF, and TBI showed pathological values in 43.3% of eyes and certain variability. Subsequent studies with a longer observation period are warranted to confirm the biomechanical trends seen in this study and to rate the ability of single measurements to diagnose early keratoconus. [J Refract Surg. 2024;40(1):e48-e56.].

Artificial intelligence for detecting keratoconus

BACKGROUND

Keratoconus remains difficult to diagnose, especially in the early stages. It is a progressive disorder of the cornea that starts at a young age. Diagnosis is based on clinical examination and corneal imaging; though in the early stages, when there are no clinical signs, diagnosis depends on the interpretation of corneal imaging (e.g. topography and tomography) by trained cornea specialists. Using artificial intelligence (AI) to analyse the corneal images and detect cases of keratoconus could help prevent visual acuity loss and even corneal transplantation. However, a missed diagnosis in people seeking refractive surgery could lead to weakening of the cornea and keratoconus-like ectasia. There is a need for a reliable overview of the accuracy of AI for detecting keratoconus and the applicability of this automated method to the clinical setting.

OBJECTIVES

To assess the diagnostic accuracy of artificial intelligence (AI) algorithms for detecting keratoconus in people presenting with refractive errors, especially those whose vision can no longer be fully corrected with glasses, those seeking corneal refractive surgery, and those suspected of having keratoconus. AI could help ophthalmologists, optometrists, and other eye care professionals to make decisions on referral to cornea specialists. Secondary objectives To assess the following potential causes of heterogeneity in diagnostic performance across studies. • Different AI algorithms (e.g. neural networks, decision trees, support vector machines) • Index test methodology (preprocessing techniques, core AI method, and postprocessing techniques) • Sources of input to train algorithms (topography and tomography images from Placido disc system, Scheimpflug system, slit-scanning system, or optical coherence tomography (OCT); number of training and testing cases/images; label/endpoint variable used for training) • Study setting • Study design • Ethnicity, or geographic area as its proxy • Different index test positivity criteria provided by the topography or tomography device • Reference standard, topography or tomography, one or two cornea specialists • Definition of keratoconus • Mean age of participants • Recruitment of participants • Severity of keratoconus (clinically manifest or subclinical) SEARCH METHODS: We searched CENTRAL (which contains the Cochrane Eyes and Vision Trials Register), Ovid MEDLINE, Ovid Embase, OpenGrey, the ISRCTN registry, ClinicalTrials.gov, and the World Health Organization International Clinical Trials Registry Platform (WHO ICTRP). There were no date or language restrictions in the electronic searches for trials. We last searched the electronic databases on 29 November 2022.

SELECTION CRITERIA

We included cross-sectional and diagnostic case-control studies that investigated AI for the diagnosis of keratoconus using topography, tomography, or both. We included studies that diagnosed manifest keratoconus, subclinical keratoconus, or both. The reference standard was the interpretation of topography or tomography images by at least two cornea specialists.

DATA COLLECTION AND ANALYSIS

Two review authors independently extracted the study data and assessed the quality of studies using the Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2) tool. When an article contained multiple AI algorithms, we selected the algorithm with the highest Youden's index. We assessed the certainty of evidence using the GRADE approach.

MAIN RESULTS

We included 63 studies, published between 1994 and 2022, that developed and investigated the accuracy of AI for the diagnosis of keratoconus. There were three different units of analysis in the studies: eyes, participants, and images. Forty-four studies analysed 23,771 eyes, four studies analysed 3843 participants, and 15 studies analysed 38,832 images. Fifty-four articles evaluated the detection of manifest keratoconus, defined as a cornea that showed any clinical sign of keratoconus. The accuracy of AI seems almost perfect, with a summary sensitivity of 98.6% (95% confidence interval (CI) 97.6% to 99.1%) and a summary specificity of 98.3% (95% CI 97.4% to 98.9%). However, accuracy varied across studies and the certainty of the evidence was low. Twenty-eight articles evaluated the detection of subclinical keratoconus, although the definition of subclinical varied. We grouped subclinical keratoconus, forme fruste, and very asymmetrical eyes together. The tests showed good accuracy, with a summary sensitivity of 90.0% (95% CI 84.5% to 93.8%) and a summary specificity of 95.5% (95% CI 91.9% to 97.5%). However, the certainty of the evidence was very low for sensitivity and low for specificity. In both groups, we graded most studies at high risk of bias, with high applicability concerns, in the domain of patient selection, since most were case-control studies. Moreover, we graded the certainty of evidence as low to very low due to selection bias, inconsistency, and imprecision. We could not explain the heterogeneity between the studies. The sensitivity analyses based on study design, AI algorithm, imaging technique (topography versus tomography), and data source (parameters versus images) showed no differences in the results.

AUTHORS' CONCLUSIONS

AI appears to be a promising triage tool in ophthalmologic practice for diagnosing keratoconus. Test accuracy was very high for manifest keratoconus and slightly lower for subclinical keratoconus, indicating a higher chance of missing a diagnosis in people without clinical signs. This could lead to progression of keratoconus or an erroneous indication for refractive surgery, which would worsen the disease. We are unable to draw clear and reliable conclusions due to the high risk of bias, the unexplained heterogeneity of the results, and high applicability concerns, all of which reduced our confidence in the evidence. Greater standardization in future research would increase the quality of studies and improve comparability between studies.

Multimodal diagnostics for keratoconus and ectatic corneal diseases: a paradigm shift

Different diagnostic approaches for ectatic corneal diseases (ECD) include screening, diagnosis confirmation, classification of the ECD type, severity staging, prognostic evaluation, and clinical follow-up. The comprehensive assessment must start with a directed clinical history. However, multimodal imaging tools, including Placido-disk topography, Scheimpflug three-dimensional (3D) tomography, corneal biomechanical evaluations, and layered (or segmental) tomography with epithelial thickness by optical coherence tomography (OCT), or digital very high-frequency ultrasound (dVHF-US) serve as fundamental complementary exams for measuring different characteristics of the cornea. Also, ocular wavefront analysis, axial length measurements, corneal specular or confocal microscopy, and genetic or molecular biology tests are relevant for clinical decisions. Artificial intelligence enhances interpretation and enables combining such a plethora of data, boosting accuracy and facilitating clinical decisions. The applications of diagnostic information for individualized treatments became relevant concerning the therapeutic refractive procedures that emerged as alternatives to keratoplasty. The first paradigm shift concerns the surgical management of patients with ECD with different techniques, such as crosslinking and intrastromal corneal ring segments. A second paradigm shift involved the quest for identifying patients at higher risk of progressive iatrogenic ectasia after elective refractive corrections on the cornea. Beyond augmenting the sensitivity to detect very mild (subclinical or fruste) forms of ECD, ectasia risk assessment evolved to characterize the inherent susceptibility for ectasia development and progression. Furthermore, ectasia risk is also related to environmental factors, including eye rubbing and the relational impact of the surgical procedure on the cornea.

Localized Corneal Biomechanical Alteration Detected In Early Keratoconus Based on Corneal Deformation Using Artificial Intelligence

PURPOSE

This study aimed to develop a novel method to diagnose early keratoconus by detecting localized corneal biomechanical changes based on dynamic deformation videos using machine learning.

DESIGN

Diagnostic research study.

METHODS

We included 917 corneal videos from the Tianjin Eye Hospital (Tianjin, China) and Shanxi Eye Hospital (Xi'an, China) from February 6, 2015, to August 25, 2022. Scheimpflug technology was used to obtain dynamic deformation videos under forced puffs of air. Fourteen new pixel-level biomechanical parameters were calculated based on a spline curve equation fitting by 115,200-pixel points from the corneal contour extracted from videos to characterize localized biomechanics. An ensemble learning model was developed, external validation was performed, and the diagnostic performance was compared with that of existing clinical diagnostic indices. The performance of the developed machine learning model was evaluated using precision, recall, F1 score, and the area under the receiver operating characteristic curve.

RESULTS

The ensemble learning model successfully diagnosed early keratoconus (area under the curve = 0.9997) with 95.73% precision, 95.61% recall, and 95.50% F1 score in the sample set (n=802). External validation on an independent dataset (n=115) achieved 91.38% precision, 92.11% recall, and 91.18% F1 score. Diagnostic accuracy was significantly better than that of existing clinical diagnostic indices (from 86.28% to 93.36%, all P <0.01).

CONCLUSIONS

Localized corneal biomechanical changes detected using dynamic deformation videos combined with machine learning algorithms were useful for diagnosing early keratoconus. Focusing on localized biomechanical changes may guide ophthalmologists, aiding the timely diagnosis of early keratoconus and benefiting the patient's vision.

Keratoconus Diagnosis: From Fundamentals to Artificial Intelligence: A Systematic Narrative Review

The remarkable recent advances in managing keratoconus, the most common corneal ectasia, encouraged researchers to conduct further studies on the disease. Despite the abundance of information about keratoconus, debates persist regarding the detection of mild cases. Early detection plays a crucial role in facilitating less invasive treatments. This review encompasses corneal data ranging from the basic sciences to the application of artificial intelligence in keratoconus patients. Diagnostic systems utilize automated decision trees, support vector machines, and various types of neural networks, incorporating input from various corneal imaging equipment. Although the integration of artificial intelligence techniques into corneal imaging devices may take time, their popularity in clinical practice is increasing. Most of the studies reviewed herein demonstrate a high discriminatory power between normal and keratoconus cases, with a relatively lower discriminatory power for subclinical keratoconus.

Biomechanical Analysis of Tomographically Regular Keratoconus Fellow Eyes Using Corvis ST

BACKGROUND

Keratoconus is a bilateral, yet asymmetric disease. In rare cases, the second eye may show no signs of tomographic changes. The purpose of this study was to analyze the biomechanical characteristics in tomographically regular keratoconus fellow eyes.

MATERIALS AND METHODS

This retrospective, consecutive case series analyzed 916 eyes of 458 patients who presented to our keratoconus clinic between November 2020 and October 2022. Primary outcome measures included best-corrected visual acuity (BCVA), tomographic Scheimpflug analysis using Pentacam AXL (Oculus, Wetzlar, Germany), and biomechanical assessment using Corvis ST (Oculus, Wetzlar, Germany). Tomographic changes were assessed via analysis of the anterior and posterior curvature, K-max, thinnest corneal thickness (TCT), the Belin/Ambrosio Deviation Display (BAD-D), and the ABCD-Grading. Biomechanical changes were analyzed using Corvis Biomechanical Index (CBI) and Tomographic Biomechanical Index (TBI).

RESULTS

Of 916 eyes, 34 tomographically regular fellow eyes (7.4%) were identified and included in the analysis. Overall, the mean BCVA was - 0.02 ± 0.13 logMAR. Tomographic analysis showed mean K-max of 43.87 ± 1.21 D, mean TCT of 532 ± 23 µm, and mean BAD-D of 1.02 ± 0.43. Biomechanical analysis demonstrated mean CBI of 0.28 ± 0.26 and mean TBI of 0.34 ± 0.30. While normal CBI-values were observed in 16 (47%) of 34 eyes, only 13 eyes (38%) showed a regular TBI and only 7 eyes (21%) showed regular TBI and CBI. The sensitivity of CBI and TBI to detect a tomographically normal keratoconus fellow eye was 53% and 62%, respectively.

CONCLUSION

A highly asymmetric corneal ectasia with regular tomographic finding in a fellow eye is rare among keratoconus patients. In such cases, a biomechanical analysis may be useful in detecting early signs of corneal ectasia. In our analysis, the TBI showed high sensitivity for detecting a biomechanical abnormality in tomographically regular fellow eyes.

Artificial intelligence in ophthalmology: The path to the real-world clinic

Artificial intelligence (AI) has great potential to transform healthcare by enhancing the workflow and productivity of clinicians, enabling existing staff to serve more patients, improving patient outcomes, and reducing health disparities. In the field of ophthalmology, AI systems have shown performance comparable with or even better than experienced ophthalmologists in tasks such as diabetic retinopathy detection and grading. However, despite these quite good results, very few AI systems have been deployed in real-world clinical settings, challenging the true value of these systems. This review provides an overview of the current main AI applications in ophthalmology, describes the challenges that need to be overcome prior to clinical implementation of the AI systems, and discusses the strategies that may pave the way to the clinical translation of these systems.

Management of keratoconus: an updated review

Keratoconus is the most common corneal ectatic disorder. It is characterized by progressive corneal thinning with resultant irregular astigmatism and myopia. Its prevalence has been estimated at 1:375 to 1:2,000 people globally, with a considerably higher rate in the younger populations. Over the past two decades, there was a paradigm shift in the management of keratoconus. The treatment has expanded significantly from conservative management (e.g., spectacles and contact lenses wear) and penetrating keratoplasty to many other therapeutic and refractive modalities, including corneal cross-linking (with various protocols/techniques), combined CXL-keratorefractive surgeries, intracorneal ring segments, anterior lamellar keratoplasty, and more recently, Bowman's layer transplantation, stromal keratophakia, and stromal regeneration. Several recent large genome-wide association studies (GWAS) have identified important genetic mutations relevant to keratoconus, facilitating the development of potential gene therapy targeting keratoconus and halting the disease progression. In addition, attempts have been made to leverage the power of artificial intelligence-assisted algorithms in enabling earlier detection and progression prediction in keratoconus. In this review, we provide a comprehensive overview of the current and emerging treatment of keratoconus and propose a treatment algorithm for systematically guiding the management of this common clinical entity.