Management of keratoconus: an updated review

Frontiers in Medicine, Год журнала: 2023, Номер 10

Опубликована: Июнь 20, 2023

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

Язык: Английский

---

Optimized Artificial Intelligence for Enhanced Ectasia Detection Using Scheimpflug-Based Corneal Tomography and Biomechanical Data

American Journal of Ophthalmology, Год журнала: 2022, Номер 251, С. 126 - 142

Опубликована: Дек. 19, 2022

To optimize artificial intelligence (AI) algorithms to integrate Scheimpflug-based corneal tomography and biomechanics enhance ectasia detection.Multicenter cross-sectional case-control retrospective study.A total of 3886 unoperated eyes from 3412 patients had Pentacam Corvis ST (Oculus Optikgeräte GmbH) examinations. The database included 1 eye randomly selected 1680 normal (N) 1181 "bilateral" keratoconus (KC) patients, along with 551 topography very asymmetric (VAE-NT), their 474 ectatic (VAE-E) eyes. current TBIv1 (tomographic-biomechanical index) was tested, an optimized AI algorithm developed for augmenting accuracy.The area under the receiver operating characteristic curve (AUC) discriminating clinical (KC VAE-E) 0.999 (98.5% sensitivity; 98.6% specificity [cutoff: 0.5]), VAE-NT, 0.899 (76% 89.1% 0.29]). A novel random forest (TBIv2), 18 features in 156 trees using 10-fold cross-validation, a significantly higher AUC (0.945; DeLong, P < .0001) detecting VAE-NT (84.4% sensitivity 90.1% specificity; cutoff: 0.43; similar (0.999; = .818; 98.7% 99.2% 0.8]). Considering all cases, TBIv2 (0.985) than (0.974; .0001).AI optimization biomechanical assessments augments accuracy detection, characterizing susceptibility diverse group. Some VAE may have true unilateral ectasia. Machine learning considering additional data, including epithelial thickness or other parameters multimodal refractive imaging, will continuously accuracy. NOTE: Publication this article is sponsored by American Ophthalmological Society.

Язык: Английский

---

A Deep Feature Fusion of Improved Suspected Keratoconus Detection with Deep Learning

Diagnostics, Год журнала: 2023, Номер 13(10), С. 1689 - 1689

Опубликована: Май 10, 2023

Detection of early clinical keratoconus (KCN) is a challenging task, even for expert clinicians. In this study, we propose deep learning (DL) model to address challenge. We first used Xception and InceptionResNetV2 DL architectures extract features from three different corneal maps collected 1371 eyes examined in an eye clinic Egypt. then fused using detect subclinical forms KCN more accurately robustly. obtained area under the receiver operating characteristic curves (AUC) 0.99 accuracy range 97-100% distinguish normal with established KCN. further validated based on independent dataset 213 Iraq AUCs 0.91-0.92 88-92%. The proposed step toward improving detection

Язык: Английский

---

Systematic reviews of machine learning in healthcare: a literature review

Expert Review of Pharmacoeconomics & Outcomes Research, Год журнала: 2023, Номер 24(1), С. 63 - 115

Опубликована: Ноя. 13, 2023

The increasing availability of data and computing power has made machine learning (ML) a viable approach to faster, more efficient healthcare delivery.

Язык: Английский

---

Artificial intelligence and corneal diseases

Current Opinion in Ophthalmology, Год журнала: 2022, Номер 33(5), С. 407 - 417

Опубликована: Июль 12, 2022

Purpose of review Artificial intelligence has advanced rapidly in recent years and provided powerful tools to aid with the diagnosis, management, treatment ophthalmic diseases. This article aims most current clinical artificial applications anterior segment diseases, an emphasis on microbial keratitis, keratoconus, dry eye syndrome, Fuchs endothelial dystrophy. Recent findings Most approaches have focused developing deep learning algorithms based various imaging modalities. Algorithms been developed detect differentiate keratitis classes quantify features. may early detection staging keratoconus. Many advances made detect, segment, features syndrome Fuchs. There is significant variability reporting methodology, patient population, outcome metrics. Summary shows great promise detecting, diagnosing, grading, measuring a need for standardization improve transparency, validity, comparability algorithms.

Язык: Английский

---

Distinct Clinical Effects of Two RP1L1 Hotspots in East Asian Patients With Occult Macular Dystrophy (Miyake Disease): EAOMD Report 4

Investigative Ophthalmology & Visual Science, Год журнала: 2024, Номер 65(1), С. 41 - 41

Опубликована: Янв. 24, 2024

Purpose: To characterize the clinical effects of two RP1L1 hotspots in patients with East Asian occult macular dystrophy (OMD). Methods: Fifty-one diagnosed OMD harboring monoallelic pathogenic variants (Miyake disease) from Japan, South Korea, and China were enrolled. Patients classified into genotype groups: group A, p.R45W, B, missense located between amino acids (aa) 1196 1201. The parameters genotypes compared, deep learning based on spectral-domain optical coherence tomographic (SD-OCT) images was used to distinguish morphologic differences. Results: Groups A B included 29 22 patients, respectively. median age onset groups 14.0 40.0 years, logMAR visual acuity 0.70 0.51, respectively, survival curve analysis revealed a 15-year difference vision loss (logMAR 0.22). statistically significant observed field classification, but no found multifocal electroretinographic classification. High accuracy (75.4%) achieved classifying SD-OCT using machine learning. Conclusions: Distinct severities phenotypes supported by artificial intelligence–based classification derived investigated hotspots: more severe phenotype (p.R45W) milder (1196–1201 aa). This newly identified genotype–phenotype association will be valuable for medical care design therapeutic trials.

Язык: Английский

---

Keratoconus: imaging modalities and management

Medical Hypothesis Discovery & Innovation in Ophthalmology, Год журнала: 2024, Номер 13(1), С. 44 - 54

Опубликована: Июль 1, 2024

Keratoconus (KCN) is characterized by gradual thinning and steepening of the cornea, which can lead to significant vision problems owing high astigmatism, corneal scarring, or even perforation. The detection KCN in its early stages crucial for effective treatment. In this review, we describe current advances diagnosis treatment KCN.

Язык: Английский

---

Automated cornea diagnosis using deep convolutional neural networks based on cornea topography maps

Scientific Reports, Год журнала: 2023, Номер 13(1)

Опубликована: Апрель 21, 2023

Abstract Cornea topography maps allow ophthalmologists to screen and diagnose cornea pathologies. We aim automatically identify any abnormalities based on such maps, with focus diagnosing keratoconus. To do so, we represent the OCT scans as images apply Convolutional Neural Networks (CNNs) for automatic analysis. The model is a state-of-the-art ConvNeXt CNN architecture weights fine-tuned given specific application using dataset. A set of 1940 consecutive screening from Saarland University Hospital Clinic Ophthalmology was annotated used training validation. All were recorded CASIA2 anterior segment Optical Coherence Tomography (OCT) scanner. proposed achieves sensitivity 98.46% specificity 91.96% when distinguishing between healthy pathological corneas. Our approach enables pathologies classification common like keratoconus . Furthermore, independent scanner visualization those scan regions which drive model’s decisions.

Язык: Английский

---

Artificial intelligence as diagnostic modality for keratoconus: A systematic review and meta-analysis

Journal of Taibah University Medical Sciences, Год журнала: 2024, Номер 19(2), С. 296 - 303

Опубликована: Янв. 1, 2024

The challenges in diagnosing keratoconus (KC) have led researchers to explore the use of artificial intelligence (AI) as a diagnostic tool. AI has emerged new way improve efficiency KC diagnosis. This study analyzed modality for KC.

Язык: Английский

---

Strategies for Early Keratoconus Diagnosis: A Narrative Review of Evaluating Affordable and Effective Detection Techniques

Journal of Clinical Medicine, Год журнала: 2025, Номер 14(2), С. 460 - 460

Опубликована: Янв. 13, 2025

Keratoconus is a progressive corneal disorder that can lead to irreversible visual impairment if not detected early. Despite its high prevalence, early diagnosis often delayed, especially in low-to-middle-income countries due limited awareness and restricted access advanced diagnostic tools such as topography, tomography, optical coherence biomechanical assessments. These technologies are essential for identifying early-stage keratoconus, yet their cost limits accessibility resource-limited settings. While portability important accessibility, the sensitivity specificity of must be considered primary metrics ensure accurate effective detection keratoconus. This review examines both traditional techniques, including use machine learning artificial intelligence, enhance diagnosis. Artificial intelligence-based approaches show significant potential transforming keratoconus by improving accuracy diagnosis, when combined with imaging devices. Notable innovations include SmartKC, smartphone-based machine-learning application, mobile topography through null-screen test, Smartphone-based Keratograph, providing affordable portable solutions. Additionally, contrast testing demonstrates detection, although precise platform routine clinical has established. The emphasizes need increased among clinicians, particularly underserved regions, advocates development accessible, low-cost tools. Further research needed validate effectiveness these emerging detecting

Язык: Английский

---