A Hybrid PSO-DEFS Based Feature Selection for the Identification of Diabetic Retinopathy

Balakrishnan, Umarani; Venkatachalapathy, K.; Marimuthu, Girirajkumar S.

doi:10.2174/1573399811666150330150038

Cited by 12 publications

(6 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They have combined the genetic algorithm and PSO algorithm for feature selection. Balakrishnan et al 99 designed and developed the hybrid model for DR detection. First, they applied image preprocessing techniques.…”

Section: Image Processing Techniques Applied In Selected Research Art...mentioning

confidence: 99%

Detection of diabetic retinopathy and related retinal disorders using fundus images based on deep learning and image processing techniques: A comprehensive review

Lalithadevi

Krishnaveni²

2022

Concurrency and Computation

View full text Add to dashboard Cite

Diabetes mellitus is a chronic disorder disease in which a person's body fails to adhere insulin produced by their pancreas or unable to segregate enough insulin due to harmonic imbalance. Diabetic people are suffering from eye disorders like diabetic retinopathy (DR), glaucoma and various diseases such as neuropathy, nephropathy, cardiomyopathy over long intervals. One of the most prevalent diabetic consequence is DR. Detecting the morphological variations in retina is difficult and requires an effective automated detection system. DR can be predicted in earlier stage using tremendous development of deep learning models and image processing techniques. Recently, many research articles have been published in DR diagnosis system. This article shows a comprehensive review of automated diagnostic methods for DR detection and other related eye disorders from several points: Causes for DR, publicly available datasets, image preprocessing, segmentation of various DR lesions, feature optimization, various deep learning models, and open research challenges. The study offers a thorough overview of DR detection techniques, which delivers valuable information for researchers, medical professionals, and DR affected patients.

show abstract

Section: Image Processing Techniques Applied In Selected Research Art...mentioning

confidence: 99%

Detection of diabetic retinopathy and related retinal disorders using fundus images based on deep learning and image processing techniques: A comprehensive review

Lalithadevi

Krishnaveni²

2022

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Kavitha and Ramakrishnan [ 29 ] employed an ACO algorithm using an OTSU method which is based on the inputs from optic disc and macula. Balakrishnan et al [ 6 ] came up with a hybrid model for classification and feature extraction from retinal images. Channel extraction and median filter are used for preprocessing.…”

Section: Related Workmentioning

confidence: 99%

“…These algorithms in general have been known to shrink the search space whether it be feature selection or hyperparameter optimization. However, the usage of swarm-based algorithms has been limited to feature selection as demonstrated across in [6][7][8]. Most used cases of swarm-related algorithms in DR classification are restricted to either hyperparameter optimization or feature extraction.…”

Section: Introductionmentioning

confidence: 99%

Early Diagnosis of Retinal Blood Vessel Damage via Deep Learning-Powered Collective Intelligence Models

Bhardwaj

Gupta

Guhan

et al. 2022

Computational and Mathematical Methods in Medicine

View full text Add to dashboard Cite

Early diagnosis of retinal diseases such as diabetic retinopathy has had the attention of many researchers. Deep learning through the introduction of convolutional neural networks has become a prominent solution for image-related tasks such as classification and segmentation. Most tasks in image classification are handled by deep CNNs pretrained and evaluated on imagenet dataset. However, these models do not always translate to the best result on other datasets. Devising a neural network manually from scratch based on heuristics may not lead to an optimal model as there are numerous hyperparameters in play. In this paper, we use two nature-inspired swarm algorithms: particle swarm optimization (PSO) and ant colony optimization (ACO) to obtain TDCN models to perform classification of fundus images into severity classes. The power of swarm algorithms is used to search for various combinations of convolutional, pooling, and normalization layers to provide the best model for the task. It is observed that TDCN-PSO outperforms imagenet models and existing literature, while TDCN-ACO achieves faster architecture search. The best TDCN model achieves an accuracy of 90.3%, AUC ROC of 0.956, and a Cohen’s kappa score of 0.967. The results were compared with the previous studies to show that the proposed TDCN models exhibit superior performance.

show abstract

“…All the particles have its own¯tness function that is de¯ned by the optimization function. 21 The below algorithm is the hybridization of PSO and DEFS. The PSO-GSA and PSO-DEFS approaches are used for the e®ective estimation of the¯tness value.…”

Section: Feature Selectionmentioning

confidence: 99%

An enhanced PSO-DEFS based feature selection with biometric authentication for identification of diabetic retinopathy

Balakrishnan

Venkatachalapathy

Marimuthu³

2016

J. Innov. Opt. Health Sci.

Self Cite

View full text Add to dashboard Cite

Recently, automatic diagnosis of diabetic retinopathy (DR) from the retinal image is the most signi¯cant research topic in the medical applications. Diabetic macular edema (DME) is the major reason for the loss of vision in patients su®ering from DR. Early identi¯cation of the DR enables to prevent the vision loss and encourage diabetic control activities. Many techniques are developed to diagnose the DR. The major drawbacks of the existing techniques are low accuracy and high time complexity. To overcome these issues, this paper proposes an enhanced particle swarm optimization-di®erential evolution feature selection (PSO-DEFS) based feature selection approach with biometric authentication for the identi¯cation of DR. Initially, a hybrid median lter (HMF) is used for pre-processing the input images. Then, the pre-processed images are embedded with each other by using least signi¯cant bit (LSB) for authentication purpose. Simultaneously, the image features are extracted using convoluted local tetra pattern (CLTrP) and Tamura features. Feature selection is performed using PSO-DEFS and PSO-gravitational search algorithm (PSO-GSA) to reduce time complexity. Based on some performance metrics, the PSO-DEFS is chosen as a better choice for feature selection. The feature selection is performed based on the¯tness value. A multi-relevance vector machine (M-RVM) is introduced to classify the 13 normal and 62 abnormal images among 75 images from 60 patients. Finally, the DR patients are further classi¯ed by M-RVM. The experimental results exhibit that the proposed approach achieves better accuracy, sensitivity, and speci¯city than the existing techniques.

show abstract

A Hybrid PSO-DEFS Based Feature Selection for the Identification of Diabetic Retinopathy

Cited by 12 publications

References 0 publications

Detection of diabetic retinopathy and related retinal disorders using fundus images based on deep learning and image processing techniques: A comprehensive review

Detection of diabetic retinopathy and related retinal disorders using fundus images based on deep learning and image processing techniques: A comprehensive review

Early Diagnosis of Retinal Blood Vessel Damage via Deep Learning-Powered Collective Intelligence Models

An enhanced PSO-DEFS based feature selection with biometric authentication for identification of diabetic retinopathy

Contact Info

Product

Resources

About