Segmentation of retinal blood vessels using the radial projection and semi-supervised approach

You, Xinge; Peng, Qinmu; Yuan, Yuan; Cheung, Yiu-ming; Lei, Jiajia

doi:10.1016/j.patcog.2011.01.007

Cited by 355 publications

(150 citation statements)

References 26 publications

Supporting

Mentioning

150

Contrasting

Order By: Relevance

“…Although this was the second highest value, the differences in accuracy among all the models were small. Sensitivity and specificity of the proposed model were 72.50% and 98.08% respectively, with the highest sensitivity provided by You et al [8] (72.60%), and the highest specificity by Marin et al (98.19%). …”

Section: Evaluation Experiments and Statistical Analysismentioning

confidence: 80%

“…Examples of such approaches include machine learning, [3][4][5][6][7][8][9][10][11][12] matched filtering, [13,14] vessel tracking, [15,16] mathematical morphology, [17] model approaches, [18,19] and connected operators. [20,21] Machine-learning methods assign one or more groups to pixels in the retinal image, using multiple numeric pixel features to group them.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improved automated vessel segmentation for diagnosing eye diseases using fundus images

Onal¹,

Dabil-Karacal²

2015

JBGC

View full text Add to dashboard Cite

The retina can provide evidence of diseases originating in other parts of the body. Among the eye diseases that can be diagnosed through a retinal examination, age-related macular degeneration, glaucoma, and diabetic retinopathy are the most common, and they cause vision loss. Although these diseases can be diagnosed by examining blood vessels and the optic disk in retinal images, assessment of blood vessels on colored fundus images is a time-consuming and subjective process. Here, we present an automated blood vessel segmentation algorithm that facilitates the evaluation of diabetic retinopathy through assessment of blood vessel abnormalities. The blood vessels are extracted using a random forest classification model combined with wavelet features and local binary pattern texture information. Discriminant analysis is modified and used for feature selection to train the proposed classification model. The boundary of the optic disk is identified using low-pass filtering, fuzzy c-means clustering, and template matching so that it may be removed and not confound the segmentation analysis. Validation test results using three publicly available retinal image datasets demonstrated that our proposed method achieves as good or better blood vessel segmentation accuracy than the other supervised model approaches examined. Results show that the proposed scheme is able to segment the blood vessels and optic disk structures accurately (Accuracy Index) in 95.80%, 95.20%, and 97.10% of the testing Digital Retinal Images for Vessel Extraction (DRIVE), Structured Analysis of the Retina (STARE), and CHASE_DB1 image datasets respectively. The main advantage of our proposed model is that it provides robust and computationally efficient segmentation of blood vessels and the optic disk. The proposed model aims to provide supportive information for cases in which a diagnosis remains unclear following a clinical examination.

show abstract

Section: Evaluation Experiments and Statistical Analysismentioning

confidence: 80%

Section: Introductionmentioning

confidence: 99%

Improved automated vessel segmentation for diagnosing eye diseases using fundus images

Onal¹,

Dabil-Karacal²

2015

JBGC

View full text Add to dashboard Cite

show abstract

“…A combination of the radial projection and support vector machine (SVM) is proposed in [21] for the process of segmenting vessels present in the CT retina images. In their work, the blood vessels are located using radial projections.…”

Section: Intensity Based Medical Image Segmentation Methodsmentioning

confidence: 99%

Intelligent Segmentation of Medical Images Using Fuzzy Bitplane Thresholding

Khan

Kannan

2014

Measurement Science Review

View full text Add to dashboard Cite

The performance of assessment in medical image segmentation is highly correlated with the extraction of anatomic structures from them, and the major task is how to separate the regions of interests from the background and soft tissues successfully. This paper proposes a fuzzy logic based bitplane method to automatically segment the background of images and to locate the region of interest of medical images. This segmentation algorithm consists of three steps, namely identification, rule firing, and inference. In the first step, we begin by identifying the bitplanes that represent the lungs clearly. For this purpose, the intensity value of a pixel is separated into bitplanes. In the second step, the triple signum function assigns an optimum threshold based on the grayscale values for the anatomical structure present in the medical images. Fuzzy rules are formed based on the available bitplanes to form the membership table and are stored in a knowledge base. Finally, rules are fired to assign final segmentation values through the inference process. The proposed new metrics are used to measure the accuracy of the segmentation method. From the analysis, it is observed that the proposed metrics are more suitable for the estimation of segmentation accuracy. The results obtained from this work show that the proposed method performs segmentation effectively for the different classes of medical images.

show abstract

“…In supervised vessel segmentation methods, different algorithms (Nekovei and Sun;Niemeijer et al;Staal et al;Soares et al;Ricci and Perfetti;Osareh and Shadgar;2009;Lupascu et al;Marín et al;You et al;2012c are used for learning the set of rules required for the retinal vessel extraction. A set of manually segmented retinal vessels by experts are considered as the reference images.…”

Section: Introductionmentioning

confidence: 99%

“…The need for a retraining of classifier before applying it on a new dataset also remains the limitation of this method. You et al (2011) combined radial projection with SVM using a semisupervised self-training approach for the segmentation of vessels. Radial projections were used to locate the vessel centre-lines and the low contrast blood vessels.…”

Section: Introductionmentioning

confidence: 99%

Automatic Retinal Vessel Detection and Tortuosity Measurement

Mapayi¹,

Tapamo²,

Viriri³

et al. 2016

Image Anal Stereol

View full text Add to dashboard Cite

As retinopathies continue to be major causes of visual loss and blindness worldwide, early detection and management of these diseases will help achieve significant reduction of blindness cases. However, an efficient automatic retinal vessel segmentation approach remains a challenge. Since efficient vessel network detection is a very important step needed in ophthalmology for reliable retinal vessel characterization, this paper presents the study on the combination of difference image and k-means clustering for the segmentation of retinal vessels. Stationary points in the vessel center-lines are used to model the detection of twists in the vessel segments. The combination of arc-chord ratio with stationary points is used to compute tortuosity index. Experimental results show that the proposed k-means combined with difference image achieved a robust segmentation of retinal vessels. A maximum average accuracy of 0.9556 and a maximum average sensitivity of 0.7581 were achieved on DRIVE database while a maximum average accuracy of 0.9509 and a maximum average sensitivity of 0.7666 were achieved on STARE database. When compared with the previously proposed techniques on DRIVE and STARE databases, the proposed technique yields higher mean sensitivity and mean accuracy rates in the same range of very good specificity. In a related development, a non-normalized tortuosity index that combined distance metric and the vessel twist frequency proposed in this paper also achieved a strong correlation of 0.80 with the expert ground truth.

show abstract

Segmentation of retinal blood vessels using the radial projection and semi-supervised approach

Cited by 355 publications

References 26 publications

Improved automated vessel segmentation for diagnosing eye diseases using fundus images

Improved automated vessel segmentation for diagnosing eye diseases using fundus images

Intelligent Segmentation of Medical Images Using Fuzzy Bitplane Thresholding

Automatic Retinal Vessel Detection and Tortuosity Measurement

Contact Info

Product

Resources

About