Neural networks and statistical analysis for classification of corneal videokeratography maps based on Zernike coefficients: a quantitative comparison

Carvalho, Luciane Bizari Coin de; Barbosa, Maysa Santos

doi:10.1590/s0004-27492008000300006

Cited by 12 publications

(7 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Despite the fact that the researchers used a comparatively small database, the study`s outcomes confirm that for automated diagnosis of videokeratography patterns by the ANNs or discriminant analysis, a possible reliable parameter may be the Zernike coefficients to be used as input data as descriptors of the corneal shape (de Carvalho & Barbosa, 2008).…”

Section: Artificial Neural Network (Anns) Based Classifiersmentioning

confidence: 80%

Artificial intelligence in corneal topography

Saleh

Hussein²

2019

Journal of Intelligent Systems: Theory and Applications

View full text Add to dashboard Cite

The purpose of this paper is to explore the effectiveness and efficiency of various artificial intelligence (AI) techniques in extracting features from corneal topographies. A considerable number of dated and contemporary related research papers have been reviewed. The author has only checked the studies that considered developing at least one AI-based algorithm for data classification of topographic patterns. The results of this review emphasize the effectiveness and efficiency of machine learning algorithms in the clinical diagnosis of various eye refractive problems.

show abstract

Section: Artificial Neural Network (Anns) Based Classifiersmentioning

confidence: 80%

Artificial intelligence in corneal topography

Saleh

Hussein²

2019

Journal of Intelligent Systems: Theory and Applications

View full text Add to dashboard Cite

show abstract

“…In previous studies, researchers used significant corneal parameters to form many intelligent indices to perform screening (Table 3). These previous AI tools were based on only specific parameters or small training data set. However, we chose to use heat maps containing all information related to the cornea, with a relatively large amount of data.…”

Section: Discussionmentioning

confidence: 99%

Screening Candidates for Refractive Surgery With Corneal Tomographic–Based Deep Learning

et al. 2020

View full text Add to dashboard Cite

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.

show abstract

“…26 Current research is directed toward the development of machine learning techniques for the early diagnosis of KC based on medical images. 21,[27][28][29] Several machine learning methods, such as unsupervised learning, 30 convolutional neural networks (CNNs), 20,31 ResNet-18, 32 or support vector machine, 33 have been previously used for disease pathophysiology. CNN is one of the main methods used for recognizing and classifying ophthalmic images.…”

Section: Introductionmentioning

confidence: 99%

KeratoScreen: Early Keratoconus Classification With Zernike Polynomial Using Deep Learning

Gao

Pan

Shen

et al. 2022

Cornea

View full text Add to dashboard Cite

Purpose:We aimed to investigate the usefulness of Zernike coefficients (ZCs) for distinguishing subclinical keratoconus (KC) from normal corneas and to evaluate the goodness of detection of the entire corneal topography and tomography characteristics with ZCs as a screening feature input set of artificial neural networks.Methods: This retrospective study was conducted at the Affiliated Eye Hospital of Wenzhou Medical University, China. A total of 208 patients (1040 corneal topography images) were evaluated. Data were collected between 2012 and 2018 using the Pentacam system and analyzed from February 2019 to December 2021. An artificial neural network (KeratoScreen) was trained using a data set of ZCs generated from corneal topography and tomography. Each image was previously assigned to 3 groups: normal (70 eyes; average age, 28.7 6 2.6 years), subclinical KC (48 eyes; average age, 24.6 6 5.7 years), and KC (90 eyes; average age, 25.9 6 5.4 years). The data set was randomly split into 70% for training and 30% for testing. We evaluated the precision of screening symptoms and examined the discriminative capability of several combinations of the input set and nodes. Results:The best results were achieved using ZCs generated from corneal thickness as an input parameter, determining the 3 categories of clinical classification for each subject. The sensitivity and precision rates were 93.9% and 96.1% in subclinical KC cases and 97.6% and 95.1% in KC cases, respectively.Conclusions: Deep learning algorithms based on ZCs could be used to screen for early KC and for other corneal ectasia during preoperative screening for corneal refractive surgery.

show abstract

Neural networks and statistical analysis for classification of corneal videokeratography maps based on Zernike coefficients: a quantitative comparison

Abstract: ABSTRACT

Cited by 12 publications

References 11 publications

Artificial intelligence in corneal topography

Artificial intelligence in corneal topography

Screening Candidates for Refractive Surgery With Corneal Tomographic–Based Deep Learning

KeratoScreen: Early Keratoconus Classification With Zernike Polynomial Using Deep Learning

Contact Info

Product

Resources

About