Difference image and fuzzy c-means for detection of retinal vessels

Mapayi, Temitope; Tapamo, Jules-Raymond

doi:10.1109/ssiai.2016.7459202

Cited by 8 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FCM was also used in the study of Dey et al (6), where the study also did not explain the reasons for selecting FCM and the number of clusters used. The next study was carried out by Mapayi et al (7). In that study, it was almost the same as Mapayi et al 9), which combines FCM with Gabor filter and frangi filter.…”

Section: Introductionmentioning

confidence: 97%

The Comparison of Clustering Algorithms K-Means and Fuzzy C-Means for Segmentation Retinal Blood Vessels

Wiharto

Suryani

2020

Acta Inform Med

View full text Add to dashboard Cite

Introduction:The segmentation method has a number of approaches, one of which is clustering. The clustering method is widely used for segmenting retinal blood vessels, especially the k-mean algorithm and fuzzy c-means (FCM). Unfortunately, so far there have been no studies comparing the two methods for blood vessel segmentation. Many studies do not explain the reason for choosing the method. Aim: This study aims to analyze the performance of the algorithms of k-means and FCM for retinal blood vessel segmentation. Methods: This research method is divided into three stages, namely preprocessing, segmentation, and performance analysis. Preprocessing uses the green channel method, Contrast-limited adaptive histogram equalization (CLAHE) and median filter. Segmentation is divided into three processes, namely clustering, thresholding and determining the region of interest (ROI). In the thresholding process, the determination of the threshold value uses two methods, namely the mean and the median. The third stage performs performance analysis using the performance parameters of the area under the curve (AUC) and statistical tests. Results: The statistical test results comparing FCM with k-means based on AUC values resulted in p-values <0.05 with a confidence level of 95%. Conclusion: Retinal vascular segmentation with the FCM method is significantly better than k-means.

show abstract

Section: Introductionmentioning

confidence: 97%

The Comparison of Clustering Algorithms K-Means and Fuzzy C-Means for Segmentation Retinal Blood Vessels

Wiharto

Suryani

2020

Acta Inform Med

View full text Add to dashboard Cite

show abstract

“…21 , reveals the proposed system’s ability to deal with both normal and abnormal cases encountered in real world clinical applications. To compare different retinal vessel segmentation techniques and other set of state-of-art methods, Table III and Table IV compares our proposed system with other methods [11] – [13] , [21] , [29] , [31] , [54] – [61] published based on both DRIVE and STARE datasets.…”

Section: Resultsmentioning

confidence: 99%

A Multi-Anatomical Retinal Structure Segmentation System for Automatic Eye Screening Using Morphological Adaptive Fuzzy Thresholding

Almotiri

Elleithy

2018

IEEE J. Transl. Eng. Health Med.

View full text Add to dashboard Cite

Eye exam can be as efficacious as physical one in determining health concerns. Retina screening can be the very first clue for detecting a variety of hidden health issues including pre-diabetes and diabetes. Through the process of clinical diagnosis and prognosis; ophthalmologists rely heavily on the binary segmented version of retina fundus image; where the accuracy of segmented vessels, optic disc, and abnormal lesions extremely affects the diagnosis accuracy which in turn affect the subsequent clinical treatment steps. This paper proposes an automated retinal fundus image segmentation system composed of three segmentation subsystems follow same core segmentation algorithm. Despite of broad difference in features and characteristics; retinal vessels, optic disc, and exudate lesions are extracted by each subsystem without the need for texture analysis or synthesis. For sake of compact diagnosis and complete clinical insight, our proposed system can detect these anatomical structures in one session with high accuracy even in pathological retina images. The proposed system uses a robust hybrid segmentation algorithm combines adaptive fuzzy thresholding and mathematical morphology. The proposed system is validated using four benchmark datasets: DRIVE and STARE (vessels), DRISHTI-GS (optic disc), and DIARETDB1 (exudates lesions). Competitive segmentation performance is achieved, outperforming a variety of up-to-date systems and demonstrating the capacity to deal with other heterogeneous anatomical structures.

show abstract

“…The study combines k-mean clustering and image difference for segmentation of the retinal eye vessels. A similar study was carried out by a number of researchers, Mapayi et al [7], Ding et al [8] and Dey et al [9]. In this study, the difference is the use of fuzzy c-means algorithms.…”

Section: Introductionmentioning

confidence: 87%

“…The developed CAD-HR system was used for initial diagnosis, so that performance parameters emphasized high sensitivity. The values of sensitivity and specificity are calculated by referring to the confusion matrix shown in Table 1, with the formula as shown in equation (6)(7).…”

Section: Methodsmentioning

confidence: 99%

“…Researches that have been conducted in using clustering-based segmentation are limited to segmenting retinal blood vessels [6]- [9]. The study uses a number of clustering algorithms for segmentation, namely k-mean clustering algorithm [6] and fuzzy c-means [7]- [9]. Referring to the results of the research [6]- [9] shows that the clustering k-means algorithm is able to provide better performance compared to a number of other clustering algorithms for the segmentation process.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The Segmentation Analysis of Retinal Image Based on K-means Algorithm for Computer-Aided Diagnosis of Hypertensive Retinopathy

Wiharto

Suryani

2020

IJEEI

View full text Add to dashboard Cite

Computer-aided diagnosis of hypertensive retinopathy (CAD-HR) is performed by analyzing the retinal image. The analysis is carried out in several stages, one of which is image segmentation. The segmentation carried out so far generally uses a region-based and threshold-based approach. There is not yet a clustering-based approach, and there has been no previous analysis of why clustering-based is not yet widely used. This study aims to conduct clustering-based Segmentation analysis, specifically k-means clustering in CAD-HR. The research method used is divided into four stages, namely preprocessing, segmentation, feature extraction using fractal dimensions, statistical analysis for classification, and classification. Testing is done using the DRIVE and STARE datasets. The results of statistical tests showed that the number of clusters 3 was able to provide a significant difference between the fractal positive and negative dimensions of hypertensive retinopathy. The model of CAD-RH using the k-means algorithm for segmentation method is able to provide 80% sensitivity performance. The k-mean algorithm can be used as an alternative to segmenting retinal blood vessels.

show abstract

Difference image and fuzzy c-means for detection of retinal vessels

Cited by 8 publications

References 23 publications

The Comparison of Clustering Algorithms K-Means and Fuzzy C-Means for Segmentation Retinal Blood Vessels

The Comparison of Clustering Algorithms K-Means and Fuzzy C-Means for Segmentation Retinal Blood Vessels

A Multi-Anatomical Retinal Structure Segmentation System for Automatic Eye Screening Using Morphological Adaptive Fuzzy Thresholding

The Segmentation Analysis of Retinal Image Based on K-means Algorithm for Computer-Aided Diagnosis of Hypertensive Retinopathy

Contact Info

Product

Resources

About