Automatic Segmentation of Retinal Blood Vessels Based on Improved Multiscale Line Detection

Hou, Yanli

doi:10.5626/jcse.2014.8.2.119

Cited by 50 publications

(12 citation statements)

References 16 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After subtracting the background from the original cineangiogram, the vessels will be enhanced precisely. For LBM, the variation of the length of line detections may merge close vessels, produce false responses at vessel crossovers and introduce much more noise [43]. In LPBM and BBM, morphological filters are utilized, which do not make use of unknown cross-sectional shape information or of overly long structure elements that do not handle well tortuous vessels [6].…”

Section: Discussionmentioning

confidence: 99%

Patch-Based Adaptive Background Subtraction for Vascular Enhancement in X-Ray Cineangiograms

Song

Frangi

Yang

et al. 2019

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Objective: Automatic vascular enhancement in Xray cineangiography is of crucial interest, for instance, for better visualizing and quantifying coronary arteries in diagnostic and interventional procedures. Methods: a novel patch-based adaptive background subtraction method (PABSM) is proposed automatically enhancing vessels in coronary X-ray cineangiography. First, pixels in the cineangiogram is described by the vesselness and Gabor features. Second, a classifier is utilized to separate the cineangiogram into the rough vascular and non-vascular region. Dilation is applied to the classified binary image to include more vascular region. Third, a patch-based background synthesis is utilized to fill the removed vascular region. Results: a database containing 320 cineangiograms of 175 patients was collected, and then an interventional cardiologist annotated all vascular structures. The performance of PABSM is compared with six state-of-the-art vascular enhancement methods regarding the precision-recall curve and Cvalue. The area under the precision-recall curve is, and the C-value is . Conclusion: PABSM can automatically enhance the coronary artery in the cineangiograms. It preserves the integrity of vascular topological structures, particularly in complex vascular regions and removes noise caused by the non-uniform gray level distribution in the cineangiogram. Significance: PABSM can avoid the motion artifacts and eases the subsequent vascular segmentation, which is crucial for the diagnosis and interventional procedures of coronary artery diseases.

show abstract

Section: Discussionmentioning

confidence: 99%

Patch-Based Adaptive Background Subtraction for Vascular Enhancement in X-Ray Cineangiograms

Song

Frangi

Yang

et al. 2019

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…However, scaled images are computed incurring different precision errors, and thus should be weighted differently based on their noise profile. Later on, in a subse-quent research, the authors [25] floated an idea of weighted linear combination instead of a simple addition to mitigate unequal contribution issues with individual line detectors, that is,f…”

Section: Proposed Methodsmentioning

confidence: 99%

GGM classifier with multi-scale line detectors for retinal vessel segmentation

Khan

Naqvi

et al. 2019

SIViP

View full text Add to dashboard Cite

Persistent changes in the diameter of retinal blood vessels may indicate some chronic eye diseases. Computerassisted change observation attempts may become challenging due to the emergence of interfering pathologies around blood vessels in retinal fundus images. The end result is lower sensitivity to thin vessels for certain computerized detection methods. Quite recently, multi-scale line detection method proved to be worthy for improved sensitivity towards lower-caliber vessels detection. This happens largely due to its adaptive property that responds more to the longevity patterns than width of a given vessel. However, the method suffers from the lack of a better aggregation process for individual line detectors. This paper investigates a scenario that introduces a supervised Generalized Gaussian mixture (GGM) classifier as a robust solution for the aggregate process. The classifier is built with class-conditional probability density functions as a logistic function of linear mixtures. To boost the classifier's performance, the weighted scale images are modeled as Gaussian mixtures. The classifier is trained with weighted images modeled on a Gaussian Mixture. The net effect is increased sensitivity for small vessels. The classifier's performance has been tested with three commonly available datasets: DRIVE, SATRE, and CHASE DB1. The results of the proposed method (with an accuracy of 96%,96.1% and 95% on DRIVE, STARE, and CHASE DB1, respectively

show abstract

“…Then morphological opening is applied on the result image to remove the false edges. An automated enhancement and segmentation method for blood vessels is presented in [67]. This method decreases the optic disc influence and emphasizes the vessels by applying a morphological multidirectional top-hat transform with rotating structuring elements to the background of the retinal image.…”

Section: Morphological Based Methodsmentioning

confidence: 99%

Diabetic retinopathy through retinal image analysis: A review

Reddy¹,

Ravindran²,

Kishore³

2017

IJET

View full text Add to dashboard Cite

In this paper, the recent advancement in the Digital Image Processing Aspects in the Diabetic Retinopathy (DR) were been discussed. The major approaches in DR are categorized into four classes namely Preprocessing, Optic Disk Detection, Blood Vessel Extraction and supervised classification. The optic disk, blood vessels and exudates gives more analytical details about the retinal image, segmentation of those features are very important. Further these approaches are classified into finer classes based on the methodologies accomplished in the respective schemes. The details of the database those used for testing the proposed algorithms is also illustrated in this paper. The details of performance metrics such as accuracy, sensitivity, specificity, precision, recall and F-measure are also discussed through their mathematical expressions.

show abstract

Automatic Segmentation of Retinal Blood Vessels Based on Improved Multiscale Line Detection

Cited by 50 publications

References 16 publications

Patch-Based Adaptive Background Subtraction for Vascular Enhancement in X-Ray Cineangiograms

Patch-Based Adaptive Background Subtraction for Vascular Enhancement in X-Ray Cineangiograms

GGM classifier with multi-scale line detectors for retinal vessel segmentation

Diabetic retinopathy through retinal image analysis: A review

Contact Info

Product

Resources

About