Detection of Red Lesions in Retinal Images Using Image Processing and Machine Learning Techniques

Lokuarachchi, Dulanji; Muthumal, Lahiru; Gunarathna, Kasun; Gamage, Tharindu D.

doi:10.1109/mercon.2019.8818794

Cited by 5 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The fundus image technology provides a convenient way of analyzing abnormalities in the eyes. Typically, when there is some ailment in an eye: either there are red spots [12], yellow circles [13], white spots, or cotton type blurry objects in the eye [14]. There might be a change in the size of the optical disc [15], a change in the number and dimensions of veins/arteries in the eyes, or simply an abnormal variation of texture in the retina area of the cornea area [15].…”

Section: Role Of Image Processingmentioning

confidence: 99%

An Integrated Fundus Image Segmentation Algorithm for Multiple Eye Ailments

Datta

Das

Kumar

2021

IJEER

View full text Add to dashboard Cite

The detection of eye illnesses requires a thorough inspection of all of the eye's structures. Most significantly, the presence of blood vessels, an optical disc, and any other unwelcome objects, if any are discovered, is critical in determining the type of eye disease present. Specifically, the goal of this research is to establish a thorough segmentation framework that will aid in the detection of anatomical anomalies in the eye. A novel segmentation technique for analyzing blood vessels, optical disc health, and the presence of exudates has been added into the software. - It was decided to add the detection of aberrant objects such as exudates into the algorithm in order to develop a generic segmentation method. In order to verify the accuracy of the segmentation at each stage, random sampling is employed at each stage. The segmentation is then validated using the intersection over union metric. The accuracy of the integrated segmentation method as a whole is 91.66 percent.

show abstract

Section: Role Of Image Processingmentioning

confidence: 99%

An Integrated Fundus Image Segmentation Algorithm for Multiple Eye Ailments

Datta

Das

Kumar

2021

IJEER

View full text Add to dashboard Cite

show abstract

“…Lokuarachchi et al 2019 [16] proposed a new method to detect red lesions using image peprocessing followed by detection of red lesion candidates, where some machine learning algorithms such as Support Vector Machines, K-nearest Neighbors, Decision Tree, and Classification Ensemble were used to separate true red lesions from artifacts with SE of 92.1% and SP of 88.7%.…”

Section: Introductionmentioning

confidence: 99%

Automated Approach for Extraction of Microaneurysms and Hemorrhages in Retinal Fundus Images

Jaafar¹,

Al-Libawy²,

Al-Gayem³

2020

IJIES

View full text Add to dashboard Cite

Early detection and quantification of microaneurysms and hemorrhages can potentially help reduce the risk of vision loss. In this paper, an automatic algorithm for extraction of microaneurysms and hemorrhages from color fundus images is presented. The color retinal image is analyzed and segmented using a top-down segmentation after some image enhancement steps, namely shade correction and contrast enhancement. The whole segmented images create a dataset of regions. Edge detection followed by region-growing techniques are also used to refine the top-down segmentation results. Segmented regions could be classified into true lesions and artifacts using a set of prior features like size, edge strength, color and texture. These are extracted and then utilized with a local-region properties classifier. To validate the outcomes of the proposed method, clinician's references were used to calculate the average performance measures. The proposed method achieved sensitivity of 98.8%, specificity of 97.7%, accuracy of 99.3%, and positive predictive value of 83.7% per-pixel basis. Superior performance measures and high computation speed have assured that the proposed method is more efficient and reproducible compared to the manual methods. The significant novelty of this work is in the use of three refining operations, i.e. Edge detection, region growing and classification to achieve optimal performance especially for the sensitivity and positive predictive value. The performance measures of the proposed algorithm are compared against many recent automated systems and are found to outperform most of them. The proposed algorithm performance is very close to that of the specialist ground truth. Hence, premium performance and high computation speed of this algorithm make it promising approach for a computer-aided mass screening of retinal diseases.

show abstract