Keratoconus detection of changes using deep learning of colour-coded maps

Chen, Xu; Zhao, Jiaxin; Iselin, Katja; Borroni, Davide; Romano, Davide; Gokul, Akilesh; McGhee, Charles N J; Zhao, Yitian; Sedaghat, Mohammad-Reza; Momeni‐Moghaddam, Hamed; Ziaei, Mohammed; Kaye, Stephen B.; Romano, Vito; Zheng, Yalin

doi:10.1136/bmjophth-2021-000824

Cited by 35 publications

(34 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Feng et al proposed an end-to-end deep learning approach utilizing raw data obtained by the Pentacam system for keratoconus and subclinical keratoconus detection ( 9 ). Chen et al also showed that convolutional neural network provides excellent performance for keratoconus detection and grading classification using the axial map, anterior and posterior elevation map, and pachymetry maps obtained by the Scheimpflug camera ( 10 ). We assume that the use of a color-coded map has advantages over that of numeric values for machine learning, because it can bring us a larger amount of anterior corneal curvature information than these numeric values.…”

Section: Discussionmentioning

confidence: 99%

Diagnosability of Keratoconus Using Deep Learning With Placido Disk-Based Corneal Topography

Kamiya

Ayatsuka²,

Kato³

et al. 2021

Front. Med.

View full text Add to dashboard Cite

Purpose: Placido disk-based corneal topography is still most commonly used in daily practice. This study was aimed to evaluate the diagnosability of keratoconus using deep learning of a color-coded map with Placido disk-based corneal topography.Methods: We retrospectively examined 179 keratoconic eyes [Grade 1 (54 eyes), 2 (52 eyes), 3 (23 eyes), and 4 (50 eyes), according to the Amsler-Krumeich classification], and 170 age-matched healthy eyes, with good quality images of corneal topography measured with a Placido disk corneal topographer (TMS-4TM, Tomey). Using deep learning of a color-coded map, we evaluated the diagnostic accuracy, sensitivity, and specificity, for keratoconus screening and staging tests, in these eyes.Results: Deep learning of color-coded maps exhibited an accuracy of 0.966 (sensitivity 0.988, specificity 0.944) in discriminating keratoconus from normal eyes. It also exhibited an accuracy of 0.785 (0.911 for Grade 1, 0.868 for Grade 2, 0.920 for Grade 3, and 0.905 for Grade 4) in classifying the stage. The area under the curve value was 0.997, 0.955, 0.899, 0.888, and 0.943 as Grade 0 (normal) to 4 grading tests, respectively.Conclusions: Deep learning using color-coded maps with conventional corneal topography effectively distinguishes between keratoconus and normal eyes and classifies the grade of the disease, indicating that this will become an aid for enhancing the diagnosis and staging ability of keratoconus in a clinical setting.

show abstract

Section: Discussionmentioning

confidence: 99%

Diagnosability of Keratoconus Using Deep Learning With Placido Disk-Based Corneal Topography

Kamiya

Ayatsuka²,

Kato³

et al. 2021

Front. Med.

View full text Add to dashboard Cite

show abstract

“…Another study trained an ensemble CNN on tomography measurements to differentiate between normal eyes and early, moderate, and advanced KCN with a staging accuracy of 98% [42]. Two studies used only topography images to detect and stage KCN [43 ▪ ,44]. Both studies had high overall accuracies (79% [43 ▪ ] 93% [44]), with better performance on color-coded maps than the raw topographic indices.…”

Section: Methodsmentioning

confidence: 99%

Artificial intelligence and corneal diseases

Kang¹,

Ballouz²,

Woodward

2022

Current Opinion in Ophthalmology

View full text Add to dashboard Cite

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

show abstract

“…Prior research has proposed automated methods using quantitative indices [10] (like Percentage Probability of Keratoconus (PPK), Cone Location and Magnitude Index [11]), statistical methods [12,13], and traditional machine learning algorithms [9,14,15] (like logistic regression, K-nearest neighbour, clustering, decision trees, and random forests) to diagnose keratoconus from corneal topography data. However, with the advent of deep learning and its high performance on image classification tasks, deep learning based methods are being widely explored for keratoconus diagnosis and have been shown to be highly accurate [5,6,16]. Lavric and Valentin [16] propose to use a CNN-based classifier for keratoconus detection, however they train and test their model only on synthetic eye data.…”

Section: Related Workmentioning

confidence: 99%

“…They train and test their model on 354 samples, and achieve sensitivity and specificity of above 90%. Chen et al [5] use corneal tomography scans, with four type of heatmaps (axial, anterior elevation, posterior elevation, and pachymetry) per sample, and adopt a VGG16 model to learn a keratoconus detection classifier. They train their model on 1115 samples and test it on 279 samples, achieving a sensitivity of 98.5% and specificity of 90.0%.…”

Section: Related Workmentioning

confidence: 99%

“…Recent works have demonstrated the efficacy of using deep neural networks for accurately detecting keratoconus using color-coded heatmaps obtained from clinical topographers, such as devices based on Optical Coherence Tomography [4], Scheimpflug imaging [5,6,7], and placido disc reflection [8,9]. However, such methods have been limited to medicalgrade topographers.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Keratoconus Classifier for Smartphone-based Corneal Topographer

Gairola¹,

Joshi²,

Balasubramaniam³

et al. 2022

Preprint

View full text Add to dashboard Cite

Keratoconus is a severe eye disease that leads to deformation of the cornea. It impacts people aged 10-25 years and is the leading cause of blindness in that demography. Corneal topography is the gold standard for keratoconus diagnosis. It is a non-invasive process performed using expensive and bulky medical devices called corneal topographers. This makes it inaccessible to large populations, especially in the Global South. Low-cost smartphone-based corneal topographers, such as SmartKC, have been proposed to make keratoconus diagnosis accessible. Similar to medical-grade topographers, SmartKC outputs curvature heatmaps and quantitative metrics that need to be evaluated by doctors for keratoconus diagnosis. An automatic scheme for evaluation of these heatmaps and quantitative values can play a crucial role in screening keratoconus in areas where doctors are not available. In this work, we propose a dual-head convolutional neural network (CNN) for classifying keratoconus on the heatmaps generated by SmartKC. Since SmartKC is a new device and only had a small dataset (114 samples), we developed a 2-stage transfer learning strategy-using historical data collected from a medical-grade topographer and a subset of SmartKC data-to satisfactorily train our network. This, combined with our domain-specific data augmentations, achieved a sensitivity of 91.3% and a specificity of 94.2%.

show abstract

Keratoconus detection of changes using deep learning of colour-coded maps

Cited by 35 publications

References 72 publications

Diagnosability of Keratoconus Using Deep Learning With Placido Disk-Based Corneal Topography

Diagnosability of Keratoconus Using Deep Learning With Placido Disk-Based Corneal Topography

Artificial intelligence and corneal diseases

Keratoconus Classifier for Smartphone-based Corneal Topographer

Contact Info

Product

Resources

About