Keratoconus disease classification with multimodel fusion and vision transformer: a pretrained model approach.

OBJECTIVE: Our objective is to develop a novel keratoconus image classification system that leverages multiple pretrained models and a transformer architecture to achieve state-of-the-art performance in detecting keratoconus. METHODS AND ANALYSIS: Three pretrained models were used to extract features from the input images. These models have been trained on large datasets and have demonstrated strong performance in various computer vision tasks.The extracted features from the three pretrained models were fused using a feature fusion technique. This fusion aimed to combine the strengths of each model and capture a more comprehensive representation of the input images. The fused features were then used as input to a vision transformer, a powerful architecture that has shown excellent performance in image classification tasks. The vision transformer learnt to classify the input images as either indicative of keratoconus or not.The proposed method was applied to the Shahroud Cohort Eye collection and keratoconus detection dataset. The performance of the model was evaluated using standard evaluation metrics such as accuracy, precision, recall and F1 score. RESULTS: The research results demonstrated that the proposed model achieved higher accuracy compared with using each model individually. CONCLUSION: The findings of this study suggest that the proposed approach can significantly improve the accuracy of image classification models for keratoconus detection. This approach can serve as an effective decision support system alongside physicians, aiding in the diagnosis of keratoconus and potentially reducing the need for invasive procedures such as corneal transplantation in severe cases.

Keratoconus Severity Classification Using Features Selection and Machine Learning Algorithms.

Keratoconus is a noninflammatory disease characterized by thinning and bulging of the cornea, generally appearing during adolescence and slowly progressing, causing vision impairment. However, the detection of keratoconus remains difficult in the early stages of the disease because the patient does not feel any pain. Therefore, the development of a method for detecting this disease based on machine and deep learning methods is necessary for early detection in order to provide the appropriate treatment as early as possible to patients. Thus, the objective of this work is to determine the most relevant parameters with respect to the different classifiers used for keratoconus classification based on the keratoconus dataset of Harvard Dataverse. A total of 446 parameters are analyzed out of 3162 observations by 11 different feature selection algorithms. Obtained results showed that sequential forward selection (SFS) method provided a subset of 10 most relevant variables, thus, generating the highest classification performance by the application of random forest (RF) classifier, with an accuracy of 98% and 95% considering 2 and 4 keratoconus classes, respectively. Found classification accuracy applying RF classifier on the selected variables using SFS method achieves the accuracy obtained using all features of the original dataset.

The ABCD Keratoconus Grading System-A Useful Tool to Estimate Keratoconus Progression in the Pediatric Population.

PURPOSE: To evaluate the ABCD grading system in pediatric keratoconus. METHODS: A retrospective cohort analysis of all children with keratoconus followed up at the Shamir medical center between 2010 and 2017. A recommendation by the treating physician to undergo corneal crosslinking (CXL) was used as an estimate for clinically significant disease progression. The ABCD grading was not available to the treating physician and was computed post hoc. The ABCD grading was compared between patients who required CXL with those who did not. A single eye of each patient was included. RESULTS: Fifty eyes of 50 children were analyzed. The mean age at presentation was 15.56 ± 1.36 years. In 23 eyes, progression of keratoconus was recorded and CXL was performed (CXL-group). On presentation, the stable and CXL groups did not differ significantly in their clinical parameters. In the CXL-group, a statistically significant increase was seen in the ABCD staging (P < 0.001). In the stable group, the ABCD staging did not change significantly in parallel visits (P = 0.87). An increase of 1 point in the sum of the ABCD staging showed a 5-fold risk for undergoing CXL (odds ratio = 5.28; 95% CI, 1.82-15.34). There was no significant change in the Amsler-Krumeich classification in the CXL group. CONCLUSIONS: Among a cohort of pediatric patients with keratoconus, worsening in the ABCD grading was associated with disease progression, whereas no significant change was demonstrated in the Amsler-Krumeich classification The ABCD grading system is a useful tool for initial assessment of disease progression in the pediatric population, in which early recognition is of paramount importance.

Scheimpflug Densitometry in Keratoconus: A New Method of Visualizing the Cone.

PURPOSE: To report an observation made while performing Scheimpflug densitometry analysis on the corneal region affected in keratoconus (KC) that seems to delineate the base of the cone. METHODS: Scheimpflug densitometries of 20 healthy subjects and 90 patients with KC were examined. Corneal densitometry was analyzed using both "1-layer" and "2-layer" approaches. The first considers the corneal transparency layer by layer at different depths, whereas the second averages densitometry between 2 corneal layers selected by the examiner. Fixed layers, 120 µm depth, and endothelium were selected. Repeated same-day scans and longitudinal series of scans were also evaluated to see whether the findings evolved over time. RESULTS: Eighty-eight of 90 KC cases displayed a bright area on the densitometry map that corresponded to the cone location. The area's characteristics, such as its brightness, contrast, and the presence of a delimiting arc correlated with KC severity and was more noticeable in advanced cases. No similar marks were found in any of the normal subjects. The shape, location, and extent of the mark were consistent over consecutive measures taken on the same day. Changes over time were also seen in eyes with known clinical progression but was also seen in eyes considered clinically stable. CONCLUSIONS: The densitometry mark seems to correspond with the zone most affected by KC and could be a supplementary tool for documenting KC stage, alongside conventional parameters. Further studies are required to ascertain whether it could prove useful in KC detection, to determine progression, and to relate it to corneal biomechanical behavior.

Baseline Findings in the Retrospective Digital Computer Analysis of Keratoconus Evolution (REDCAKE) Project.

PURPOSE: To present the baseline data for a large cohort of patients with keratoconus enrolled in the Retrospective Digital Computer Analysis of Keratoconus Evolution (REDCAKE) study. METHODS: Eight centers contributed the Scheimpflug tomographical data for 906 patients with keratoconus, 743 measured with a Pentacam and 163 with a Galilei. The stage of keratoconus at baseline, the location of the reference points, minimum pachymetry (Pmin), and maximum keratometry (Kmax) were analyzed. The intereye asymmetry was evaluated for Kmax (anterior and posterior), Pmin, and keratoconus stage. Average maps and elevation profiles were calculated for each degree of keratoconus. RESULTS: Keratoconus was more frequently diagnosed in men (73%) than in women (27%). At baseline, 500/1155 eyes (43%) presented with moderate to severe changes in the posterior surface, whereas moderate/severe changes were only found in 252 and 63 eyes when evaluating anterior surface and pachymetry, respectively. The location of Pmin was usually inferotemporal (94% OD and 94% OS), while the location of Kmax showed more variability and significantly higher distance from apex (P < 0.05). The keratoconus presentation was chiefly asymmetric for all the parameters studied. Clear differences between stages could be identified in the maps and elevation profiles. CONCLUSIONS: The staging map set presented can be used as a graphical guidance to classify keratoconus stage. Keratoconus presented asymmetrically, and generally the posterior surface was more affected than the anterior surface or the thickness. Asymmetry is playing a role in KC detection. Although Pmin was almost invariably located inferotemporally, Kmax location showed higher variability and distance from the apex.

Keratoconus staging by decades: a baseline ABCD classification of 1000 patients in the Homburg Keratoconus Center.

BACKGROUND: This retrospective cross-sectional study aims to analyse the keratoconus (KC) stage distribution at different ages within the Homburg Keratoconus Center (HKC). METHODS: 1917 corneae (1000 patients) were allocated to decades of age, classified according to Belin's ABCD KC grading system and the stage distribution was analysed. RESULTS: 73 per cent (n=728) of the patients were males, 27% (n=272) were females. The highest KC prevalence occurred between 21 and 30 years (n=585 corneae, 294 patients). Regarding anterior (A) and posterior (B) curvature, the frequency of A was significantly higher than B in all age groups for stage 0, 1 and 2 (A0>B0; A1>B1; A2>B2; p<0.03, Wilcoxon matched-pairs test). There was no significant difference between the number of A3 and B3, but significantly more corneae were classified as B4 than A4 in all age groups (p<0.02). The most frequent A|B combinations were A4|B4 (n=451), A0|B0 (n=311), A2|B4 (n=242), A2|B2 (n=189) and A1|B2 (n=154). Concerning thinnest pachymetry (C), most corneae in all age groups were classified as C0>C1>C2>C3>C4 (p<0.04, Wilcoxon matched-pairs test). For the best distance visual acuity (D), a significantly higher number of corneae were classified as D1 compared to D0 (p<0.008; D1>D0>D2>D3>D4). CONCLUSION: The stage distributions in all age groups were similar. Early KC rather becomes manifest in the posterior than the anterior corneal curvature whereas advanced stages of posterior corneal curvature coincide with early and advanced stages of anterior corneal curvature. Thus, this study emphasises the necessity of posterior corneal surface assessment in KC as enabled by the ABCD grading system.

Repeatability of the Pentacam HR in Various Grades of Keratoconus.

PURPOSE: To evaluate the repeatability of an extensive number of relevant indices with the Pentacam HR in keratoconus of varying severity and normal eyes. DESIGN: Reliability analysis. METHODS: This study was performed at Antwerp University Hospital, Belgium, and enrolled 20 healthy volunteers (20 eyes) and 69 patients (69 eyes) with keratoconus. Three consecutive measurements were performed by the same operator with Pentacam HR in keratoconus and normal eyes. Exclusion criteria included past ocular surgery, recent rigid contact lens wear, and corneal scarring. The keratoconus group was subdivided according to the Belin/Ambrosio total deviation value: subclinical, mild, and moderate. The within-subject standard deviation and repeatability limit were computed for repeatability assessment. The tolerance index (TI) was calculated to compare across parameters with different measurement scales. For the sample size included, TI > 0.36 signified statistical significance at the 0.05 level. RESULTS: Repeatability in subclinical keratoconus did not differ significantly from controls (P > .05), except for wavefront aberrations. In mild keratoconus, 11 of 18 (61.1%) anterior corneal, 7 of 14 (50%) posterior corneal, 2 of 5 (40%) pachymetry, 7 of 11 (63.6%) combined, and 1 of 6 (16.7%) densitometry parameters showed significantly worse repeatability compared to controls (TI > 0.36). Repeatability of most parameters worsened in moderate disease. In particular, maximal keratometry and anterior astigmatism showed significantly worse repeatability in moderate keratoconus. CONCLUSIONS: Measurement variability of Pentacam HR is of clinical relevance when assessing for progression of keratoconus. We provide reference repeatability values and scale independent analysis of relevant corneal parameters in keratoconus of varying degrees.

Corneal Topography Raw Data Classification Using a Convolutional Neural Network.

PURPOSE: We investigated the efficiency of a convolutional neural network applied to corneal topography raw data to classify examinations of 3 categories: normal, keratoconus (KC), and history of refractive surgery (RS). DESIGN: Retrospective machine-learning experimental study. METHODS: A total of 3,000 Orbscan examinations (1,000 of each class) of different patients of our institution were selected for model training and validation. One hundred examinations of each class were randomly assigned to the test set. For each examination, the raw numerical data from "elevation against the anterior best fit sphere (BFS)," "elevation against the posterior BFS" "axial anterior curvature," and "pachymetry" maps were used. Each map was a square matrix of 2,500 values. The 4 maps were stacked and used as if they were 4 channels of a single image.A convolutional neural network was built and trained on the training set. Classification accuracy and class wise sensitivity and specificity were calculated for the validation set. RESULTS: Overall classification accuracy of the validation set (n = 300) was 99.3% (98.3%-100%). Sensitivity and specificity were, respectively, 100% and 100% for KC, 100% and 99% (94.9%-100%) for normal examinations, and 98% (97.4%-100%) and 100% for RS examinations. CONCLUSION: Using combined corneal topography raw data with a convolutional neural network is an effective way to classify examinations and probably the most thorough way to automatically analyze corneal topography. It should be considered for other routine tasks performed on corneal topography, such as refractive surgery screening.

Screening Candidates for Refractive Surgery With Corneal Tomographic-Based Deep Learning.

Importance: Evaluating corneal morphologic characteristics with corneal tomographic scans before refractive surgery is necessary to exclude patients with at-risk corneas and keratoconus. In previous studies, researchers performed screening with machine learning methods based on specific corneal parameters. To date, a deep learning algorithm has not been used in combination with corneal tomographic scans. Objective: To examine the use of a deep learning model in the screening of candidates for refractive surgery. Design, Setting, and Participants: A diagnostic, cross-sectional study was conducted at the Zhongshan Ophthalmic Center, Guangzhou, China, with examination dates extending from July 18, 2016, to March 29, 2019. The investigation was performed from July 2, 2018, to June 28, 2019. Participants included 1385 patients; 6465 corneal tomographic images were used to generate the artificial intelligence (AI) model. The Pentacam HR system was used for data collection. Interventions: The deidentified images were analyzed by ophthalmologists and the AI model. Main Outcomes and Measures: The performance of the AI classification system. Results: A classification system centered on the AI model Pentacam InceptionResNetV2 Screening System (PIRSS) was developed for screening potential candidates for refractive surgery. The model achieved an overall detection accuracy of 94.7% (95% CI, 93.3%-95.8%) on the validation data set. Moreover, on the independent test data set, the PIRSS model achieved an overall detection accuracy of 95% (95% CI, 88.8%-97.8%), which was comparable with that of senior ophthalmologists who are refractive surgeons (92.8%; 95% CI, 91.2%-94.4%) (P = .72). In distinguishing corneas with contraindications for refractive surgery, the PIRSS model performed better than the classifiers (95% vs 81%; P < .001) in the Pentacam HR system on an Asian patient database. Conclusions and Relevance: PIRSS appears to be useful in classifying images to provide corneal information and preliminarily identify at-risk corneas. PIRSS may provide guidance to refractive surgeons in screening candidates for refractive surgery as well as for generalized clinical application for Asian patients, but its use needs to be confirmed in other populations.

Classification of Keratoconus Based on Anterior Corneal High-order Aberrations: A Cross-validation Study.

SIGNIFICANCE: Placido disc-based videokeratography is one of the most extensively used methods for corneal topographic assessments in keratoconus. Anterior corneal wavefront analysis has been demonstrated to be an effective tool to manage keratoconus eyes. However, currently, there is no clinically adequate classification system for keratoconus. PURPOSE: The aim of this study was to analyze the usefulness of anterior corneal high-order aberrations in keratoconus classification provided by Placido disc-based videokeratography conducting a cross-validation analysis. METHODS: Corneal topography of 70 normal and 77 keratoconic eyes (divided according to the Amsler-Krumeich classification [n = 21, stage 1; n = 30, stage 2; and n = 26, stage 3]) was assessed using Placido disc-based videokeratography (Oculus Keratograph [Oculus Optikgeräte GmbH, Wetzlar, Germany]). Receiver operating characteristic curve analysis was used to compare the mean values of coma, trefoil, tetrafoil, secondary astigmatism, spherical aberration, and coma-like, third-, and fourth-order root mean square (RMS) to calculate cutoff values, sensitivity, and specificity to discriminate between normal and stage 1 keratoconus eyes and between each keratoconus stage after cross-validation analysis. RESULTS: All wavefront aberrations were significantly different between the normal and keratoconus groups (P ≤ .01). The coma and third-order RMS values (cutoff values, 0.367 and 0.359 µm, respectively) provide better sensitivity (99 and 100%, respectively) and specificity (100%) to discriminate keratoconus (stage 1) from healthy eyes compared with trefoil, tetrafoil, secondary astigmatism, spherical aberration, and coma-like and fourth-order RMS values (sensitivity >84% and specificity >57%). The coma and third-order RMS values showed the highest specificity (100%) and great sensitivity (90 and 87%, respectively) to differentiate between stages 1 and 2 and good sensitivity (97 and 100%) and specificity (81 and 88%) to differentiate between stages 2 and 3. CONCLUSIONS: Anterior corneal high-order aberrations, specifically coma and third-order RMS, could be useful in keratoconus diagnosis and topographical classification. These new cutoff values could improve different stages of keratoconus eyes discrimination.

Standard cross-linking protocol versus accelerated and transepithelial cross-linking protocols for treatment of paediatric keratoconus: a 2-year comparative study.

PURPOSE: To compare the efficacy, safety and stability of standard epithelium-off cross-linking (SCXL) versus accelerated epithelium-off cross-linking (ACXL) and transepithelial epithelium-on cross-linking (TCXL) in the treatment of progressive keratoconus (KC) in children. METHODS: This prospective multicentre controlled trial included 271 eyes (136 children) with grade 1-3 progressive KC who were randomized to undergo SCXL (n = 91, as a control group), ACXL (n = 92) or TCXL (n = 88). Uncorrected and corrected distance visual acuity, subjective refraction, pachymetry, keratometry and corneal topography measurements were recorded preoperatively and 6, 12 and 24 months postoperatively. RESULTS: At 1 year, there was no significant difference in uncorrected distance visual acuity, refractive sphere, cylinder, spherical equivalent or Kmax between the ACXL and SCXL groups; however, during year 2, ACXL regressed while SCXL continued to improve. After 2 years, there were significant differences in all visual, refractive and keratometric components between SCXL and both ACXL and TCXL (p < 0.0001) and between ACXL and TCXL (p < 0.0001). KC progressed in 5.4% of patients who had ACXL and 28.4% of those who had TCXL but in none of those who had SCXL. Vernal keratoconjunctivitis was documented in 43.3% of eyes that progressed postoperatively. CONCLUSION: SCXL was more effective for paediatric KC and achieved greater stability than either ACXL or TCXL, and ACXL was superior to TCXL. SCXL also achieved marked improvement in both myopia and spherical equivalent; however, these refractive outcomes were unpredictable and uncontrollable. TCXL had a 28.4% failure rate within 2 years. SCXL is preferable for management of paediatric KC.

Keratoconus detection using deep learning of colour-coded maps with anterior segment optical coherence tomography: a diagnostic accuracy study.

OBJECTIVE: To evaluate the diagnostic accuracy of keratoconus using deep learning of the colour-coded maps measured with the swept-source anterior segment optical coherence tomography (AS-OCT). DESIGN: A diagnostic accuracy study. SETTING: A single-centre study. PARTICIPANTS: A total of 304 keratoconic eyes (grade 1 (108 eyes), 2 (75 eyes), 3 (42 eyes) and 4 (79 eyes)) according to the Amsler-Krumeich classification, and 239 age-matched healthy eyes. MAIN OUTCOME MEASURES: The diagnostic accuracy of keratoconus using deep learning of six colour-coded maps (anterior elevation, anterior curvature, posterior elevation, posterior curvature, total refractive power and pachymetry map). RESULTS: Deep learning of the arithmetical mean output data of these six maps showed an accuracy of 0.991 in discriminating between normal and keratoconic eyes. For single map analysis, posterior elevation map (0.993) showed the highest accuracy, followed by posterior curvature map (0.991), anterior elevation map (0.983), corneal pachymetry map (0.982), total refractive power map (0.978) and anterior curvature map (0.976), in discriminating between normal and keratoconic eyes. This deep learning also showed an accuracy of 0.874 in classifying the stage of the disease. Posterior curvature map (0.869) showed the highest accuracy, followed by corneal pachymetry map (0.845), anterior curvature map (0.836), total refractive power map (0.836), posterior elevation map (0.829) and anterior elevation map (0.820), in classifying the stage. CONCLUSIONS: Deep learning using the colour-coded maps obtained by the AS-OCT effectively discriminates keratoconus from normal corneas, and furthermore classifies the grade of the disease. It is suggested that this will become an aid for improving the diagnostic accuracy of keratoconus in daily practice. CLINICAL TRIAL REGISTRATION NUMBER: 000034587.

In vivo assessment of the anterior scleral contour assisted by automatic profilometry and changes in conjunctival shape after miniscleral contact lens fitting / Valoración in vivo del contorno de la esclera anterior asistida por perfilometría automática, y de los cambios en la forma conjuntival tras el uso de lentillas mini-esclerales

Purpose: To compare the shape of the anterior sclera of candidates to scleral lens (ScCL) fitting with regular and irregular corneas and analyze the changes induced in the shape of the sclero-conjunctiva after ScCL wear. Methods: Thirty-five eyes of 18 subjects (19 eyes with irregular corneas and 16 with regular corneas) were consecutively recruited. Three measures of sclero-conjunctival shape were taken with Eye Surface Profiler (ESP, Eaglet Eye, Houten, The Netherlands). Tangent angles and ocular sagittal heights (OC-SAG) were analyzed at different chords from 13 to 17 mm in the nasal, temporal, superior and inferior regions. The 19 eyes with irregular cornea were selected to wear ScCL and the changes in their sclero-conjunctival surface parameters were compared before and after 3 h of lens wear. Results: Irregular corneas showed higher OC-SAG values than regular corneas in all the chords analyzed, with statistical significant differences in the temporal region. Regarding tangent angles, regular corneas showed lower values (flatter surface), with statistical significant differences at 8 and 8.50 mm on the nasal and 8.50 mm on the temporal region. Some changes were seen in sclero-conjuctival shape after short-term ScCL wear. There was an augment in OC-SAG after 3h of scleral lens wear and a reduction on tangent angles, namely on the nasal region at 7.5 mm and 8.00 mm chord lengths, which is coincidental with the landing zone of ScCL. Conclusions: ESP shows mild differences in scleral shape between eyes with regular and irregular corneas. ESP might be valuable in quantifying the mechanical impact of the ScCL on the anterior eye surface

Objetivo: Comparar la forma de la esclerótica anterior de los candidatos a utilizar lentes de apoyo escleral (ScCL) con córneas regulares e irregulares, y analizar los cambios inducidos en la forma de la superfície esclero-conjuntival tras el uso de dichas lentes. Métodos: Se incluyeron consecutivamente treinta y cinco ojos de 18 sujetos (19 ojos con córneas irregulares y 16 con córneas regulares). Se realizaron tres mediciones de la forma esclero-conjuntival con el dispositivo Eye Surface Profiler (ESP, Eaglet Eye, Houten, The Netherlands). Se analizaron los ángulos tangenciales y las alturas sagitales oculares (OC-SAG) a diferentes cuerdas, de 13 a 17 mm en las regiones nasal, temporal, superior e inferior. Se seleccionó a los 19 ojos con córnea irregular para utilizar ScCL, comparándose los cambios de los parámetros de su superficie esclero-conjuntival antes y después del uso de lentillas durante 3 horas. Resultados: Las córneas regulares reflejaron valores OC-SAG superiores a las córneas regulares en todas las cuerdas analizadas, con diferencias estadísticamente significativas en la región temporal. En cuanto a los ángulos tangenciales, las córneas regulares reflejaron unos valores inferiores (superficie más plana), con diferencias estadísticamente significativas a 8 y 8,5 mm en la región nasal, y 8,5 mm en la región temporal. También se apreciaron algunos cambios en la forma esclero-conjutival tras el uso a corto plazo de ScCL. Se produjo un aumento de los valores OC-SAG tras 3 h de uso de lentillas esclerales, y una reducción de los ángulos tangenciales, es decir, en las distancais correspondientes a las cuerdas de la región nasal a 7,5 mm y 8 mm, lo cual es coincidente con la zona de apoyo de las ScCL. Conclusiones: El dispositivo ESP muestra leves diferencias en la forma escleral entre los ojos con córneas regulares e irregulares, y ha es capaz de por lo que podría resultar de utilidad para cuantificar el impacto mecánico de las lentes ScCL en la superficie anterior del ojo

Retinoscopy as a Screening Tool for Keratoconus.

PURPOSE: To investigate the validity and reliability of retinoscopy in screening for keratoconus using the rotating Pentacam Scheimpflug camera as the gold standard comparison. METHODS: Patients between the ages of 10 and 30 years who were referred to the outpatient clinic with keratoconus, keratoconus suspect, reduced vision, eye discomfort or frequent change of glasses, or for refraction or refractive surgery, were screened by two independent and masked retinoscopists for the presence of scissoring reflex. Patients then underwent vision testing, slit lamp examination, and Pentacam imaging. A diagnosis of keratoconus by Pentacam was made if the final D index in the Belin and Ambrósio Display was ≥2.69. The results of retinoscopy and Pentacam examinations were compared to assess the validity and reliability of the test. RESULTS: A total of 123 patients (67 male patients and 45 female patients) with a mean age of 21 years ±5.6 (range 10-30 years) comprising 245 eyes were included. There were 87 eyes with keratoconus, and using the Amsler-Krumeich classification, 67.8%, 26.4%, 2.3%, and 3.4% of the eyes had stage I, II, III, and IV, respectively. Sensitivity, specificity, positive predictive value, and negative predictive value of retinoscopy were 97.7%, 79.9%, 70.8%, and 98.4%, respectively. The area under the curve was 0.88 (95% confidence interval, 0.83-0.92). There was excellent agreement between the 2 retinoscopists (Cohen's kappa value 0.84). CONCLUSIONS: Retinoscopy appears to be a very sensitive and reliable test for detecting keratoconus including early disease. Such a test may be implemented in population-based screening programs for keratoconus.

Avaliação da melhora da acuidade visual após adaptação de lentes de contato em pacientes portadores de ceratocone / Evaluation of visual acuity improvement after adaptation of contact lenses in patients with keratoconus

Resumo Objetivo: Avaliar a eficácia na adaptação de lentes de contato em relação à melhora da acuidade visual em pacientes portadores de ceratocone. Métodos: Foi realizado um estudo retrospectivo, através de revisão de prontuários médicos, em 175 pacientes (326 olhos) portadores de ceratocone, atendidos no período de março/2004 a junho/2015. Foram coletados os dados sobre sexo, idade, número de olhos adaptados, severidade do ceratocone e acuidade visual com óculos e com lentes de contato. Resultados: Dos pacientes avaliados, 100 pacientes (57,4%) eram do sexo feminino e 75 pacientes (42,6%) do sexo masculino. Dos olhos classificados, 267 (81,9%) tinham ceratocone moderado (45 a 52D). A faixa etária mais frequente foi de 10-39 anos (84%) e a taxa de sucesso ao fim do tratamento foi de 92,3% (acuidade visual boa ou satisfatória). Conclusão: A adaptação de lentes de contato mostrou-se eficaz em proporcionar importante melhora da acuidade visual em pacientes portadores de ceratocone.

Abstract Objective: To evaluate the efficiency of the contact lens adaptation in relation to the improvement of visual acuity in patients with keratoconus. Methods: A retrospective study of 175 patients (326 eyes) with keratoconus was carried out from March 2004 to June 2015. Data on sex, age, number of adapted eyes, keratoconus severity, and visual acuity with glasses and contact lenses were collected. Results: Of the classified eyes, 267 (81.9%) had moderate keratoconus (45 to 52D). The most frequent age group was 10-39 years of age (84%) and the success rate at the end of treatment was 92.3% (good or satisfactory visual acuity). Conclusion: Adaptation of contact lenses was effective in providing important improvement of visual acuity in patients with keratoconus.

Early Tomographic Changes in the Eyes of Patients With Keratoconus.

PURPOSE: To identify tomographic variables best suited for detecting keratoconus before manifestation of ectatic changes and showing disease progression in the early stage. METHODS: Twenty-seven patients with diagnosed unilateral keratoconus were followed up for their fellow eye, which had not yet shown any ectatic changes, to determine initial change indicators toward keratoconus disease. Variables were compared to 50 normal eyes without any known disease. A following receiver operating characteristic (ROC) analysis was performed to reveal the variables best used to discriminate healthy eyes from early ectatic eyes. RESULTS: The calculated mean difference of the cylinder for total corneal refractive power was only 0.07 ± 0.32 diopters (D) (anterior astigmatism = 0.12 ± 0.28 D and posterior astigmatism = 0.02 ± 0.10 D). ROC revealed the index of height decentration with an area under the curve of 0.788 ± 0.054 as the most suitable to differentiate between eyes of healthy patients and the non-ectatic eye of patients with asymmetrical keratoconus, followed by the index of vertical asymmetry of 0.772 ± 0.057 and a keratoconus index of 0.743 ± 0.062. However, with progression of the eyes into early ectactic stages, the ROC showed the highest area under the curve for D-index (0.876 ± 0.039), followed by index of height decentration (0.855 ± 0.046) and index of vertical asymmetry (0.842 ± 0.046). CONCLUSIONS: Early stages of keratoconus are hard to diagnose and best results can be achieved by using index of height decentration and index of vertical asymmetry. As the disease progresses, D-index is better suited to diagnose an ectasia. Astigmatism, keratometry, and pachymetry barely change in the early stages, so these values are not as fitting as corneal elevation parameters for early diagnosis. [J Refract Surg. 2018;34(4):254-259.].

Comparative evaluation of Scheimpflug tomography parameters between thin non-keratoconic, subclinical keratoconic, and mild keratoconic corneas.

PURPOSE: To evaluate and compare the topographic and topometric parameters, thickness profile data, and data from enhanced elevation maps of thin non-keratoconic, subclinical keratoconic, and mild keratoconic corneas with the Pentacam Scheimpflug corneal tomography and to study the usefulness of different parameters to differentiate keratoconus from topographically normal thin corneas. METHODS: The study included 30 eyes with subclinical keratoconus, 30 eyes with mild-stage keratoconus, and 54 healthy eyes with minimal pachymetry ≤500 µm, with a mean age of 21.19 ± 2.97, 21.75 ± 1.93, and 21.5 ± 2.95 years, respectively. The area under the receiver operating characteristic curves was used to analyze the diagnostic significance of the Pentacam parameters. RESULTS: The anterior and posterior corneal elevations, pachymetric progression, the percentage of thickness increase measurements, overall D value, and topometric indices were statistically significantly higher in subclinical and mild keratoconic corneas than in normal eyes with thin cornea (p < 0.05). All these parameters had sufficient strength (area under the receiver operating characteristic curves >0.90) to differentiate clinical keratoconus. Posterior elevation showed the excellent area under the receiver operating characteristic curves with 100% sensitivity and 100% specificity for this purpose. However, among all parameters studied, the anterior elevation (0.935) showed the excellent area under the receiver operating characteristic curves to differentiate subclinical keratoconus, followed by posterior elevation (0.897), index of height decentration (0.887), and D value (0.882). CONCLUSION: The parameters derived from the Scheimpflug device, such as corneal elevations and overall D value, can effectively differentiate subclinical and clinical keratoconus from non-keratoconic thin cornea eyes. However, the specificity levels of these parameters were relatively limited in the diagnosis of subclinical keratoconus.

[Intraindividual Keratoconus Progression]. / Keratokonusprogression im Seitenvergleich.

Introduction Keratoconus is a typically bilateral, progressive-extending corneal disease. The aim of this work is to evaluate the intraindividual progression of keratoconus. Patients and Methods This single-center retrospective study of disease progression based on topographic data from non-operated keratoconus patients (n = 48) was examined over a period of two years. Seven topographical keratoconus indices derived from Scheimpflug tomography were used to compare both the initial findings, as well as the progression of the fellow eyes. Results The mean observation period was 3.3 ± 0.9 years. The initial findings illustrated that a pair of eyes did not correlate with each other (p > 0.05). When comparing baseline and the progression of the individual indices, a negative correlation was found for all indices (p < 0.05). Progression and age did correlate for index smallest radius (Rmin, (R = 0.376, p = 0.008) and index of height decentration (IHD, R = 0.291, p = 0.045). Regarding the intraindividual progression, we found a weak correlation to the index of surface variance (ISV, R = - 0.399, p = 0.005), index of vertical asymmetry (IVA, R = - 0.291, p = 0.045) and the keratoconus index (KI, R = 0.307, p = 0.038). Conclusions The intraindividual asymmetry, which is typical for keratoconus, could be verified. This study suggests that the progression of keratoconus in one eye is independent of the progression in the fellow eye. In this small group of patients, age relationship to keratoconus could not be demonstrated for all keratoconus indices.

Validation of an Objective Keratoconus Detection System Implemented in a Scheimpflug Tomographer and Comparison With Other Methods.

PURPOSE: To validate a recently developed program for automatic and objective keratoconus detection (Keratoconus Assistant [KA]) by applying it to a new population and comparing it with other methods described in the literature. METHODS: KA uses machine learning and 25 Pentacam-derived parameters to classify eyes into subgroups, such as keratoconus, keratoconus suspect, postrefractive surgery, and normal eyes. To validate this program, it was applied to 131 eyes diagnosed separately by experienced corneal specialists from 2 different centers (Fondation Rothschild, Paris, and Antwerp University Hospital [UZA]). The agreement of the KA classification with 7 other indices from the literature was assessed using interrater reliability and confusion matrices. The agreement of the 2 clinical classifications was also assessed. RESULTS: For keratoconus, KA agreed in 92.6% of cases with the clinical diagnosis by UZA and in 98.0% of cases with the diagnosis by Rothschild. In keratoconus suspect and forme fruste detection, KA agreed in 65.2% (UZA) and 100% (Rothschild) of cases with the clinical assessments. This corresponds with a moderate agreement with a clinical assessment (κ = 0.594 and κ = 0.563 for Rothschild and UZA, respectively). The agreement with the other classification methods ranged from moderate (κ = 0.432; Score) to low (κ = 0.158; KISA%). Both clinical assessments agreed substantially (κ = 0.759) with each other. CONCLUSIONS: KA is effective at detecting early keratoconus and agrees with trained clinical judgment. As keratoconus detection depends on the method used, we recommend using multiple methods side by side.

Double-Pass Retina Point Imaging for the Evaluation of Optical Light Scatter, Retinal Image Quality, and Staging of Keratoconus.

PURPOSE: To measure retinal image quality using point spread function (PSF) analysis by double-pass retina point imaging in patients with keratoconus and to correlate visual quality with disease severity. METHODS: Patients diagnosed as having keratoconus by clinical examination, topography, and tomography and normal eyes were included in this study. A commercially available double-pass retina point imaging instrument (OQAS 108 II AcuTarget HD; Visiometrics S.L., Terrassa, Spain) was used to collect Objective Scatter Index (OSI) values in 21 keratoconic and 22 normal eyes. Eyes were also subjected to corneal topography and tomography, and staged using the Keratoconus Severity Score (KSS) and Amsler-Krumeich (AK) scales. RESULTS: The OSI was increased in keratoconic eyes (5.85 ± 0.98) versus control eyes (0.83 ± 0.12; mean ± SEM), in AK stages 1 to 4, and KSS stages 3 and 4. Receiver-operator characteristic analysis obtained an area under the curve (AUC) of 0.859 when evaluating the OSI as a unimodal diagnostic indicator for any KSS stage and 0.993 for KSS stages 3 and higher. An AUC of 0.949 was obtained in comparing eyes with lower severity topographic aberrations (KSS 1 and 2) versus mild to moderate keratoconus (KSS 3 and 4). Increasing corneal steepening patterns on tomography and topography were associated with PSF broadening and increased OSI. CONCLUSIONS: Double-pass retina point imaging is useful in correlating retinal image quality with keratoconus severity. The OSI may represent a clinically significant parameter for staging keratoconus with a unique ability to directly evaluate quality of vision in this population. [J Refract Surg. 2016;32(11):760-765.].