Logistic index for keratoconus detection and severity scoring (Logik)

Issarti, Ikram; Consejo, Alejandra; Jiménez‐García, Marta; Kreps, Elke O.; Koppen, Carina; Rozema, Jos J

doi:10.1016/j.compbiomed.2020.103809

Cited by 26 publications

(37 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 20 , 22 Some more recent approaches added more sophisticated analysis techniques based on artificial intelligence (AI) and machine learning algorithms to enhance the detection rate of the early cases. 15 , 24 – 26 These AI-based techniques, although solely based on macroscopic parameters, tend to be more accurate than traditional methods; however, they require large datasets for their development.…”

Section: Discussionmentioning

confidence: 99%

Keratoconus Detection Based on a Single Scheimpflug Image

Consejo

Solarski

Karnowski

et al. 2020

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

To introduce a new approach for keratoconus detection based on corneal microstructure observed in vivo derived from a single Scheimpflug image. Methods: Scheimpflug single-image snapshots from 25 control subjects and 25 keratoconus eyes were analyzed; from each group, five subjects were randomly selected to provide out-of-sample data. Each corneal image was segmented, after which the stromal pixel intensities were statistically modeled with a Weibull distribution. Distribution estimated parameters α and β, characterizing corneal microstructure, were used in combination with a macrostructure parameter, central corneal thickness (CCT), for the detection of keratoconus. In addition, receiver operating characteristic curves were used to determine the sensitivity and specificity of each parameter for keratoconus detection. Results: The combination of CCT (sensitivity = 88%; specificity = 84%) with microscopic parameters extracted from statistical modeling of light intensity distribution, α (sensitivity = 76%; specificity = 76%) and β (sensitivity = 96%; specificity = 88%), from a single Scheimpflug image was found to be a successful tool to differentiate between keratoconus and control eyes with no misclassifications (sensitivity = 100%; specificity = 100%) with coefficients of variation up to 2.5%. Conclusions: The combination of microscopic and macroscopic corneal parameters extracted from a static Scheimpflug image is a promising, non-invasive tool to differentiate corneal diseases without the need to perform measurements based on induced deformation of the corneal structure. Translational Relevance: The proposed methodology has the potential to support clinicians in the detection of keratoconus, without compromising patient comfort.

show abstract

Section: Discussionmentioning

confidence: 99%

Keratoconus Detection Based on a Single Scheimpflug Image

Consejo

Solarski

Karnowski

et al. 2020

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The BAD-D index achieved lower discrimination success when screening subclinical keratoconus from control eyes (sensitivity = 85.0%, specificity = 85.0%, AUC = 0.80 with an optimized cut-off of 0.74; sensitivity = 50.0%, specificity = 95.0%, AUC = 0.60 with a standard cut-off of 1.60), 25 but performed equally well for screening clinical keratoconus from control eyes (sensitivity = 100%, specificity = 100%, AUC = 1.0). The logistic index for keratoconus (Logik), also based on corneal tomography but supported by artificial intelligence, 28 showed a better discriminating rate than BAD-D when screening subclinical keratoconus from control eyes (sensitivity = 85.0%, specificity = 95.0%, AUC = 0.90).…”

Section: Resultsmentioning

confidence: 99%

“…Novel diagnostic indices to detect keratoconus from corneal tomographies based on artificial intelligence have been recently introduced, such as the Enhanced Tomographic Assessment to Detect Corneal Ectasia Based on Artificial Intelligence, the so-called Pentacam Random Forest Index (PRFI), 33 a computer-aided diagnosis system for early keratoconus detection, 27 and Logik. 28 Note that all of these Scheimpflug-based indices have something in common in that they exclusively evaluate the cornea at a macroscopic level, and all are based solely on macroparameters such as corneal curvature, corneal elevation, corneal thickness, or corneal deformation.…”

Section: Discussionmentioning

confidence: 99%

Detection of Subclinical Keratoconus With a Validated Alternative Method to Corneal Densitometry

Consejo

Jiménez‐García

Issarti

et al. 2021

Trans. Vis. Sci. Tech.

Self Cite

View full text Add to dashboard Cite

Purpose To enhance the current standards of subclinical keratoconus screening based on the statistical modeling of the pixel intensity distribution of Scheimpflug images. Methods Scheimpflug corneal tomographies corresponding to 25 corneal meridians of 60 participants were retrospectively collected and divided into three groups: controls (20 eyes), subclinical keratoconus (20 eyes), and clinical keratoconus (20 eyes). Only right eyes were selected. After corneal segmentation, pixel intensities of the stromal tissue were statistically modeled using a Weibull probability density function from which parameter α (pixel brightness) was derived. Further, data were transformed to polar coordinates, smoothed, and interpolated to build a map of the corneal α parameter. The discriminative power of the method was analyzed using receiver operating characteristic curves. Results The proposed platform-independent method achieved a higher performance in discriminating subclinical keratoconus from control eyes (90.0% sensitivity, 95.0% specificity, 0.97 area under the curve [AUC]) than the standard method (Belin–Ambrósio enhanced ectasia display), which uses only corneal morphometry (85.0% sensitivity, 85.0% specificity, 0.80 AUC). Conclusions Analysis of light backscatter at the cornea successfully discriminates subclinical keratoconus from control eyes, upgrading the results previously reported in the literature. Translational Relevance The proposed methodology has the potential to support clinicians in the detection of keratoconus before showing clinical signs.

show abstract

“…Based on the top 10 parameters from that list (see Table S1 ), 6 nonredundant, potentially platform-independent parameters were selected: age, known to affect KC progression [ 11 , 26 ]; the average keratometry in a 3 mm area around the maximum keratometry (KmaxZonalMean3mm) [ 27 ]; the steepest radius (RsF) and best fit sphere over an area of 8 mm (BFSF) of the front surface; and the average radius of the back surface (RmB) and LOGIK [ 18 ], which is based on the elevation maps of both corneal surfaces and the minimum pachymetry. None of the parameters included were based on a single corneal point.…”

Section: Methodsmentioning

confidence: 99%

“…Identifying such “suspect progressive KC” would be valuable to determine whether certain patients might benefit from closer follow-up or a fast-track CXL [ 8 , 15 ], but this would require a forecast of KC evolution. Such predictive tasks are well suited for machine learning, which has been widely used in KC since the 1990s [ 16 ] to distinguish normal from KC corneas [ 17 , 18 , 19 , 20 ]. Forecasting systems based on neural networks have also been extensively used in other fields with long-term time series of balanced data, such as speech or stock markets [ 21 ], and occasionally in medicine [ 22 ], though this approach has not yet been used in KC.…”

Section: Introductionmentioning

confidence: 99%

Forecasting Progressive Trends in Keratoconus by Means of a Time Delay Neural Network

Jiménez‐García

Issarti

Kreps

et al. 2021

JCM

Self Cite

View full text Add to dashboard Cite

Early and accurate detection of keratoconus progression is particularly important for the prudent, cost-effective use of corneal cross-linking and judicious timing of clinical follow-up visits. The aim of this study was to verify whether a progression could be predicted based on two prior tomography measurements and to verify the accuracy of the system when labelling the eye as stable or suspect progressive. Data from 743 patients measured by Pentacam (Oculus, Wetzlar, Germany) were available, and they were filtered and preprocessed to data quality needs. The time delay neural network received six features as input, measured in two consecutive examinations, predicted the future values, and determined the classification (stable or suspect progressive) based on the significance of the change from the baseline. The system showed a sensitivity of 70.8% and a specificity of 80.6%. On average, the positive and negative predictive values were 71.4% and 80.2%. Including data of less quality (as defined by the software) did not significantly worsen the results. This predictive system constitutes another step towards a personalized management of keratoconus. While the results obtained were modest and perhaps insufficient to decide on a surgical procedure, such as cross-linking, they may be useful to customize the timing for the patient’s next follow-up.

show abstract

Logistic index for keratoconus detection and severity scoring (Logik)

Cited by 26 publications

References 42 publications

Keratoconus Detection Based on a Single Scheimpflug Image

Keratoconus Detection Based on a Single Scheimpflug Image

Detection of Subclinical Keratoconus With a Validated Alternative Method to Corneal Densitometry

Forecasting Progressive Trends in Keratoconus by Means of a Time Delay Neural Network

Contact Info

Product

Resources

About