Optimized convolution neural network based multiple eye disease detection

subin, P. Glaret; Muthukannan, P.

doi:10.1016/j.compbiomed.2022.105648

Cited by 27 publications

(8 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning has been demonstrated to achieve remarkable results in eye detection tasks, including glaucoma and DR, in recent years. [10], [37]- [39]. Therefore, our proposed model leverages DCGAN to synthesize high-quality images and utilizes the CNN ensemble method for classification.…”

Section: Methodsmentioning

confidence: 99%

“…The DVE algorithm achieves superior accuracy rates on both the DDR and EyePACS datasets, validating its effectiveness in fine grading of DR images. As a future work, the performance of the proposed model can be compared with the performance of a capsule network-based approach because capsule networks can preserve spatial relationships of learned features and have been used recently for recognitions and classifications[37]-[39].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Ensembled Deep Convolutional Generative Adversarial Network for Grading Imbalanced Diabetic Retinopathy Recognition

Naz,

Nijhawan,

Ahuja

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) is one of the leading causes of blindness and vision loss worldwide. According to the International Diabetes Federation (IDF), approximately one-third of individuals with diabetes, equivalent to 32.2%, are affected by some form of DR. Due to the uneven data distribution, intra-class variance, and a dearth of ophthalmologists, DR diagnosis is considered challenging. In recent years, Convolutional Neural Networks (CNN) and supervised learning techniques have been potentially useful in computer vision applications. However, unsupervised CNN has received less attention. Moreover, it is more manageable to use synthetic images for model training with the recent advancements in graphics. Therefore, the proposed method combines the actual and augmented views using the Deep Convolutional Generative Adversarial Network (DCGAN) algorithm. The generated views are implemented to balance the minority class in the imbalanced dataset. Furthermore, a novel ensemble convolutional neural network algorithm named Different View Ensemble (DVE) that merges the weighted average prediction of CNN, CNN-i, and CNN+i algorithms has been proposed. The proposed algorithm is evaluated on the DDR and EyePACS datasets, and its performance is compared with K-Means, Fuzzy C-Means (FCM), and Autoencoder-based Deep Embedded Clustering Techniques (DEC).The results demonstrate the superiority of the proposed algorithm, achieving an accuracy rate of 97.4%, specificity of 99.6%, and sensitivity of 92.3%. The promising results underscore the potential impact of this methodology in enhancing the accuracy and reliability of automated diagnostic systems in the field of ophthalmology. Notably, the evaluation considers imbalanced data and a DCGAN-balanced dataset, where the proposed approach exhibits even better performance with balanced classes. INDEX TERMSDiabetic Retinopathy detection, Imbalance data, Ensembled GAN, Healthcare, Health risksFIGURE 1. Fundus Images and Abnormal DR Grades (a) Mild NPDR (b) Moderate NPDR (c) Severity NPDR (d) PDR [1]

show abstract

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

Ensembled Deep Convolutional Generative Adversarial Network for Grading Imbalanced Diabetic Retinopathy Recognition

Naz,

Nijhawan,

Ahuja

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Tan et al [6] applied a deep CNN for predicting AMD with 10-fold cross-validation principle. Gulshan et al [7] used DL for automated prediction of DR and DME in retinal fundus images on EyePACS-1 dataset as well as Messidor-2 dataset, correspondingly.…”

Section: Literature Reviewmentioning

confidence: 99%

Eye Disease Diagnosis and Classification using Deep Convolution Neural Network

Dr. N. Rajkumar, Dr. S. Megala, S. Muthukumaran

2023

tjjpt

View full text Add to dashboard Cite

Human eye plays a vital role in everyone’s life. If retinal diseases occur it could cause complete or partial vision loss. Objective: To overcome that situation, the fundus images can be utilized by the ophthalmologists to automatically diagnose the retinal diseases. At the same time, the development of latest Artificial Intelligence (AI) techniques, especially Deep Learning (DL) models finds useful for object detection in several application areas, including medical imaging. Methods: In this view, this paper presents an automated DL based multi-retinal disease diagnosis and classification model. The presented technique comprises three processes, such as pre-processing, feature extraction, and classification. For feature extraction purposes, AlexNet and Residual Network (ResNet) models are employed. Besides, Convolutional Neural Network (CNN) and Deep Neural Network (DNN) models are applied to classify the retinal fundus images into different retinal diseases. The incorporation of DL models for feature extraction and classification resulted to enhanced diagnostic performance. Findings: A series of experiments were conducted on benchmark dataset and the experimental results are examined under different aspects. The experimental values exhibited that the ResNet-CNN model has achieved better performance with the accuracy of 98.84%, precision of 98.84%, recall of 98.17%, and F1-score of 98.48%. Novelty: With the help of such methods and techniques those latest findings indicate that some human eye diseases which can be alleviated by pharmacological interventions in an easy manner.

show abstract

“…The first ophthalmic AI device, IDx-DR, was approved for listing with landmark significance on 11 April 2018, opening a new chapter on the combination of AI with ophthalmology. Since then, the application of AI in the ophthalmology has entered a new stage of development, leading to a series of satisfactory research results in the diagnosis, classification, recognition, and screening of ophthalmic diseases, such as diabetic retinopathy (Deepa et al, 2022;Hardas et al, 2022;, age-related macular degeneration (Glaret Subin and Muthukannan, 2022;Sotoudeh-Paima et al, 2022;, retinopathy of prematurity (Coyner et al, 2022;Wu et al, 2022), glaucoma (Dong et al, 2022;Xiong et al, 2022), and retinal vein occlusion (Miao et al, 2022;Ren et al, 2022;.…”

Section: Introductionmentioning

confidence: 99%

Advances in artificial intelligence models and algorithms in the field of optometry

Wang

Wen

et al. 2023

Front. Cell Dev. Biol.

View full text Add to dashboard Cite

The rapid development of computer science over the past few decades has led to unprecedented progress in the field of artificial intelligence (AI). Its wide application in ophthalmology, especially image processing and data analysis, is particularly extensive and its performance excellent. In recent years, AI has been increasingly applied in optometry with remarkable results. This review is a summary of the application progress of different AI models and algorithms used in optometry (for problems such as myopia, strabismus, amblyopia, keratoconus, and intraocular lens) and includes a discussion of the limitations and challenges associated with its application in this field.

show abstract

Optimized convolution neural network based multiple eye disease detection

Cited by 27 publications

References 20 publications

Ensembled Deep Convolutional Generative Adversarial Network for Grading Imbalanced Diabetic Retinopathy Recognition

Ensembled Deep Convolutional Generative Adversarial Network for Grading Imbalanced Diabetic Retinopathy Recognition

Eye Disease Diagnosis and Classification using Deep Convolution Neural Network

Advances in artificial intelligence models and algorithms in the field of optometry

Contact Info

Product

Resources

About