Evaluation of corneal topographic,tomographic and biomechanical indices for detecting clinical and subclinical keratoconus:a comprehensive three-device study

AIM:To evaluate the diagnostic ability of topographic and tomographic indices with Pentacam and Sirius as well as biomechanical parameters with Corvis ST for the detection of clinical and subclinical forms of keratoconus(KCN).METHODS:In this prospective diagnostic test study,70 patients with clinical KCN,79 patients with abnormal findings in topography and tomography maps with no evidence on clinical examination(subclinical KCN),and 68 normal control subjects were enrolled.The accuracy of topographic,tomographic,and biomechanical parameters was evaluated using the area under the receiver operating characteristic curve(AUC)and cross-validation analysis.The Delong method was used for comparing AUCs.RESULTS:In distinguishing KCN from normal,all parameters showed statistically significant differences between the two groups(P<0.001).Indices with the perfect diagnostic ability(AUC≥0.999)were Sirius KCN vertex of back(KVb),Pentacam random forest index(PRFI),Pentacam index of height decentration(IHD),and Corvis integrated tomographic/biomechanical index(TBI).In distinguishing subclinical KCN from normal,Sirius symmetry index of back(SIb;AUC=0.908),Pentacam inferior-superior difference(IS)value(AUC=0.862),PRFI(AUC=0.847),and Corvis TBI(AUC=0.820)performed best.There were no significant differences between the highest AUCs within keratoconic groups(De Long,P>0.05).CONCLUSION:In clinical KCN,all topographic,tomographic,and biomechanical indices have acceptable outcomes in terms of sensitivity and specificity.However,in differentiating subclinical forms of KCN from normal corneas,curvature-based parameters(SIb and IS value)followed by integrated indices(PRFI and TBI)are the most powerful tools for early detection of KCN.

Machine learning helps improve diagnostic ability of subclinical keratoconus using Scheimpflug and OCT imaging modalities

Purpose:To develop an automated classification system using a machine learning classifier to distinguish clinically unaffected eyes in patients with keratoconus from a normal control population based on a combination of Scheimpflug camera images and ultra-high-resolution optical coherence tomography(UHR-OCT)imaging data.Methods:A total of 121 eyes from 121 participants were classified by 2 cornea experts into 3 groups:normal(50 eyes),with keratoconus(38 eyes)or with subclinical keratoconus(33 eyes).All eyes were imaged with a Scheimpflug camera and UHR-OCT.Corneal morphological features were extracted from the imaging data.A neural network was used to train a model based on these features to distinguish the eyes with subclinical keratoconus from normal eyes.Fisher’s score was used to rank the differentiable power of each feature.The receiver operating characteristic(ROC)curves were calculated to obtain the area under the ROC curves(AUCs).Results:The developed classification model used to combine all features from the Scheimpflug camera and UHR-OCT dramatically improved the differentiable power to discriminate between normal eyes and eyes with subclinical keratoconus(AUC=0.93).The variation in the thickness profile within each individual in the corneal epithelium extracted from UHR-OCT imaging ranked the highest in differentiating eyes with subclinical keratoconus from normal eyes.Conclusion:The automated classification system using machine learning based on the combination of Scheimpflug camera data and UHR-OCT imaging data showed excellent performance in discriminating eyes with subclinical keratoconus from normal eyes.The epithelial features extracted from the OCT images were the most valuable in the discrimination process.This classification system has the potential to improve the differentiable power of subclinical keratoconus and the efficiency of keratoconus screening.

Presence of Fleischer ring and prominent corneal nerves in keratoconus relatives and normal controls

AIMTo examine the occurrence of commonly known clinical signs of keratoconus (KC), i.e. Fleischer ring, prominent corneal nerves and thinning, among unaffected family members of KC patients and healthy control individuals.METHODSData of both eyes of 117 relatives of KC patients having no manifest disease based on videokeratography indices (KC relatives), and 142 controls were used for Pearson correlation and t-test statistics. Correlation of Fleischer ring, prominent corneal nerves and central pachymetry data were tested with each other and with videokeratography indices (KSI, KISA, 3 and 6 mm Fourier asymmetry, and I-S).RESULTSA moderate correlation was found between Fleischer ring and all examined topographical indices. Most important correlation was present with 6 mm Fourier asymmetry, and corneal pachymetry (r=0.272, P&#x0003c;0.001; r=-0.234, P=0.027, respectively). Similar correlations were found with prominent corneal nerves (r=0.234, P&#x0003c;0.001 for 6 mm Fourier asymmetry and r=-0.235, P=0.0265 for pachymetry). KC family members who exhibited Fleischer ring or prominent nerves had thinner and more asymmetric corneas than those without Fleischer ring or prominent corneal nerves (P&#x0003c;0.05 for pachymetry and topographic indices with t-test and Mann-Whitney rank sum test). Though rarely, Fleischer ring and prominent corneal nerves occurred among normal controls, indicating the existence of forme fruste cases in the normal population. Control subjects, who had corneal Fleischer ring or prominent nerves had corneas more similar to KC than other controls (t-test: increased KSI and KISA, P=0.048 and 0.012, respectively).CONCLUSIONIn KC family members and healthy individuals, Fleischer ring and prominent corneal nerves are associated with features of KC and may suggest a possibility of forme fruste KC. Searching for the possible presence of Fleischer ring or prominent nerves on the cornea may help in the decision whether or not to diagnose subclinical KC in a borderline case.