KerNet: A Novel Deep Learning Approach for Keratoconus and Sub-Clinical Keratoconus Detection Based on Raw Data of the Pentacam HR System

Feng, Ruiwei; Xu, Zhe; Zheng, Xiao; Hu, He; Jin, Xiuming; Chen, Danny Z.; Yao, Ke; Wu, Jian

doi:10.1109/jbhi.2021.3079430

Cited by 29 publications

(23 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feng et al [ 20 ] have proposed a customized CNN, KerNet, for detecting keratoconus and subclinical keratoconus, from the Pentacam data. The data selected from Pentacam included the curvature of the front and back surfaces, elevation of the front and back surfaces, and the pachymetry data in the form of numerical matrices.…”

Section: Related Workmentioning

confidence: 99%

[Retracted] Keratoconus Classification with Convolutional Neural Networks Using Segmentation and Index Quantification of Eye Topography Images by Particle Swarm Optimisation

Subramanian

Ramesh

2022

BioMed Research International

View full text Add to dashboard Cite

In keratoconus, the cornea assumes a conical shape due to its thinning and protrusion. Early detection of keratoconus is vital in preventing vision loss or costly repairs. In corneal topography maps, curvature and steepness can be distinguished by the colour scales, with warm colours representing curved steep areas and cold colours representing flat areas. With the advent of machine learning algorithms like convolutional neural networks (CNN), the identification and classification of keratoconus from these topography maps have been made faster and more accurate. The classification and grading of keratoconus depend on the colour scales used. Artefacts and minimal variations in the corneal shape, in mild or developing keratoconus, are not represented clearly in the image gradients. Segmentation of the maps needs to be carried out for identifying the severity of the keratoconus as well as for identifying the changes in the severity. In this paper, we are considering the use of particle swarm optimisation and its modifications for segmenting the topography image. Pretrained CNN models are then trained with the dataset and tested. Results show that the performance of the system in terms of accuracy is 95.9% compared to 93%, 95.3%, and 84% available in the literature for a 3-class classification that involved mild keratoconus or forme fruste keratoconus.

show abstract

Section: Related Workmentioning

confidence: 99%

[Retracted] Keratoconus Classification with Convolutional Neural Networks Using Segmentation and Index Quantification of Eye Topography Images by Particle Swarm Optimisation

Subramanian

Ramesh

2022

BioMed Research International

View full text Add to dashboard Cite

show abstract

“…Performance of these models must be validated under different datasets, and can be extended via use of Dense Convolutional Neural Network [17], fuzzy logic-based classification [18], Deep Multiple instance Learning via Multiple Modalities [19], ensemble classification models [20], semi supervised Multitask Learning (SSMTL) [21], and Variance Maximized Deep Networks [22], which assist in improving feature variance for better signal representation under different datasets. Specialized approaches that utilize Deep Learning Models for Keratoconus and Sub-Clinical Keratoconus Detection [23], Multivariate Analysis using CNNs & Decision Trees [24], Learning from Label Fuzzy Proportions (LLFP) [25], and Gaussian mixture models (GMM) with sensor CNN (SCNN) [26] are discussed which assist in improving correlative feature mapping between clinical & test features in order to improve overall classification performance. Extensions to these approaches are proposed in [27,28,29] [30,31,32], wherein Residual CNN, Robust sleep Network, and Graph Convolutional Networks are proposed.…”

Section: Literature Reviewmentioning

confidence: 99%

Design of an intrinsically scalable model for medical disease identification using hybrid swarm intelligence with augmented transfer learning

Kaabra¹,

Rungta²

2022

ijhs

View full text Add to dashboard Cite

People's lives could be in danger if a contagious disease spreads quickly, Corona-2019 virus disease (COVID-19) is one. The coronavirus epidemic rapidly spread over the world. The Corona virus has had a major impact on the health of populations and healthcare systems all over the world. RT-PCR (RT-Reverse transcription, PCR-polymerase chain reaction) testing can benefit from the use of computed tomography images. Most available methods use large training data, and the detection accuracy needs to be improved due to the inadequate border segment of symptom descriptions. This study proposes a robust and effective way for identifying normal and COVID-19 patients using small training data. Deep learning quickly creates accurate models. Data augmentation increases the training dataset to reduce over fitting and improve model generalisation. Using data augmentation, we evaluated Xception and VGG-19. The study showed that deep learning can detect COVID-19.

show abstract

“…(1) A CNN based algorithm was proposed in [11] by analyzing the raw data of the Pentacam HR system for detection of the subclinical keratoconus by considering an inhouse dataset, here attempt is made to collect a raw data of specific format with 5 numerical matrices, the work mainly concentrates on detection of Subclinical keratoconus. The work considers 854 samples including both men and women of age around 20-30 years of age.…”

Section: Related Workmentioning

confidence: 99%

“…The network makes use of small three x three filters. Otherwise, the community is characterized with the aid of using its simplicity: the most effective different additives being pooling layers and a completely linked layer [11]. Vgg 19 is a CNN model that consists of 16 convolution layers, 5 Max pool, 3 fully connected and 1 SoftMax layer.Vgg net is the successor of the AlexNet .Vgg19 takes a fixed size image (RGB) input of size 224 x 224 x 3 pixels.…”

Section: Vggmentioning

confidence: 99%

Con-Ker: A Convolutional Neural Network Based Approach for Keratoconus Detection and Classification

Shashank¹,

Priya²,

Mamatha³

et al. 2021

JUSST

View full text Add to dashboard Cite

The paper is on the detection of keratoconus a corneal progressive disorder leading to the thinning and also protrusion of the cornea associated with symptoms like astigmatism, increased sensitivity to bright light, glare, clouded vision, eye irritation, and others, In recent times there has been increasing in a number of keratoconus cases. Keratoconus is normally described as a non-inflammatory pathology. The main contribution of the paper is to facilitate detection and also classification of the keratoconus based on the progression using Convolution neural networks. The paper is about the implementation of different CNN algorithms which will classify the disorder based on the progression into 4 different classes. The CNN algorithms analyze the corneal topography of the eye and classify based on the severity of the disorder. We introduce an effective CNN model called CON-KER for the detection and classification of the disorder. Further CNN algorithms like Alexnet and Vgg 19 were implemented for the same. The results show that the CON-KER model has yielded an accuracy of 96.26% compared to other algorithms like vgg19 which yielded 94.76% and AlexNet with 86% accuracy. This work can help by assisting the ophthalmologist in reducing diagnostic errors and also help in the rapid screening of the patients.

show abstract

KerNet: A Novel Deep Learning Approach for Keratoconus and Sub-Clinical Keratoconus Detection Based on Raw Data of the Pentacam HR System

Cited by 29 publications

References 49 publications

[Retracted] Keratoconus Classification with Convolutional Neural Networks Using Segmentation and Index Quantification of Eye Topography Images by Particle Swarm Optimisation

[Retracted] Keratoconus Classification with Convolutional Neural Networks Using Segmentation and Index Quantification of Eye Topography Images by Particle Swarm Optimisation

Design of an intrinsically scalable model for medical disease identification using hybrid swarm intelligence with augmented transfer learning

Con-Ker: A Convolutional Neural Network Based Approach for Keratoconus Detection and Classification

Contact Info

Product

Resources

About