Diagnosis of diabetic retinopathy based on holistic texture and local retinal features

Frazao, Luis Bastos; Theera-Umpon, Nipon; Auephanwiriyakul, Sansanee

doi:10.1016/j.ins.2018.09.064

Cited by 19 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to human expert analysis and automatic systems performance, holistic texture features were explored with the same dataset using the independent component analysis. 14 The taxonomy of diabetic retinopathy detection techniques in the context of machine learning and deep learning approaches is given in Figure 1.…”

Section: Related Workmentioning

confidence: 99%

“…The performance metrics like accuracy, sensitivity, specificity, precision, recall and F1-score measurement were used to evaluate the proposed recurrent convolution neural network classifier against the existing classifiers. An accuracy of the disease prediction can be computed as given in Equation (14).…”

Section: Predictions In the Recurrent Convolution Neural Network Classifiermentioning

confidence: 99%

See 1 more Smart Citation

Cloud‐based onboard prediction and diagnosis of diabetic retinopathy

Sundharamurthy¹,

Kaliappan

2021

Concurrency and Computation

View full text Add to dashboard Cite

Diabetic retinopathy remains the most daunting microvascular complication of diabetic disease. Major risk factors of diabetic retinopathy include long-term diabetics, improper blood glucose level, and dyslipidemia. In order to investigate the presence of diabetic retinopathy-related features and to deal with the diagnosis of various diabetic severity stages, there is a need for a cloud-based automated screening system. So, the development of novel biomarkers should take the advantage of objective measurement and evaluation indicating the biological and pathogenic processes to all the therapeutic interventions. Current state-of-the-art research studies lack accommodating large sample size, cross-validation among the diverse populations, time, and cost-effective diagnosis techniques. To overcome these challenges, a cloud-based diabetic retinopathy prediction system is proposed using the recurrent convolution neural network classifier model. The proposed prediction system can provide risk stratification, optimized resource allocation, a severe form of disease prediction, risk control, and preventive interventions during the screening and diagnosis process. It also provides prognostic information to patients stating various cost-effective predictive responses according to treatment modalities. Moreover, the proposed system clinical decision-making will outperform the existing classifiers in terms of prediction accuracy, sensitivity, specificity, precision, recall, and F1-score.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Predictions In the Recurrent Convolution Neural Network Classifiermentioning

confidence: 99%

Cloud‐based onboard prediction and diagnosis of diabetic retinopathy

Sundharamurthy¹,

Kaliappan

2021

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Retinal images are used for diagnosis since it holds a lot of information [15]. Undoubtedly, diseases had been detected in early stages possess higher opportunities to be treated [7][8][9]15]. Therefore, the accurate and fast method needs to be designed to detect the DR in its current stage.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Furthermore, 35% never performed regular eye checkups [7]. In this context, the risk of becoming blind because of DR may dramatically be reduced to 50% by proper screening and diagnostics [8,9]. Such screening action is recommended annually for the diabetic patient with no syndromes of either retinopathy or mild retinopathy by most of the guidelines [10].…”

Section: Introductionmentioning

confidence: 99%

Diagnosis of Diabetic Retinopathy Utilizing Computer-Aided Diagnosis System

Mujalled¹,

Kadah²

2020

AJCE

View full text Add to dashboard Cite

Purpose: Diabetes is considered one of most diseases spread among people; blindness is considered the most resulted effect. Diabetes can damage the retinal blood vessels and cause severe problems to the eyes, which may end with sight loss. Such medical condition is known as "diabetic retinopathy" (DR). In such a diagnosis, the retinal microvascular go through several stages of change threat. In the early stages of the DR, detecting the formation that happened to the retinal blood vessels helps prevent the disease's dangerous effects. Therefore, producing a method to diagnose the disease in the early stages is helpful. So, this work aimed to develop a system of detecting and classifying the retina formation, trying to avoid relevant effects.Methodology: The current method depends on vascular edges map extracted from images of retina captured by a fundus camera. Such a map been utilized to extract quantitative texture features. The system tested two independent groups of the region of interest in normal and abnormal images. The two sets were extracted from ground truth images of the 89 fundus images. Fundus images were annotated images from the Standard Diabetic Retinopathy Database (DIARETDB1).Findings: The system provided an accuracy of 71% with a sensitivity of 75%.Recommendation: The current work may open an opportunity for improvement for future work. Other methods may be reached to raise the accuracy and the sensitivity of the system. Besides, the current system may be tested on a larger sample size to study such effects. Finally, the ease of the current method makes it faster in adoption in the appropriate diagnosis especially in the early stages.

show abstract

“…Accuracy of this method is 99.58% and its sensitivity is 72.51%. Face recognition methods were used for fundus images in [17] to detect exudates and their features were extracted very recently. Four classifiers were implemented by the extracted features.…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Networks Based Decision Support System for the Detection of Diabetic Retinopathy

Şentürk

2020

Sakarya University Journal of Science

View full text Add to dashboard Cite

Machine learning methods have been frequently used for the diagnosis of several diseases recently because of its reliability and convenience. In this paper, a comprehensive overview of the literature related to diabetes and diabetic retinopathy has been done and diagnosis of diabetic retinopathy disease is investigated. Artificial Neural Networks (ANN) method has been applied to the problem using Rapid Miner, a data mining tool. Some other methods have also adapted to the problem, but ANN based detection approach gave the best results. 88.52% sensitivity has been obtained using the features of Messidor dataset. Besides showing the success of ANN in diabetic retinopathy detection, this study also proved that Rapid Miner can be used effectively for the analysis of diabetic retinopathy.

show abstract

Diagnosis of diabetic retinopathy based on holistic texture and local retinal features

Cited by 19 publications

References 31 publications

Cloud‐based onboard prediction and diagnosis of diabetic retinopathy

Cloud‐based onboard prediction and diagnosis of diabetic retinopathy

Diagnosis of Diabetic Retinopathy Utilizing Computer-Aided Diagnosis System

Artificial Neural Networks Based Decision Support System for the Detection of Diabetic Retinopathy

Contact Info

Product

Resources

About