Blood Vessels Extraction Using Mathematical Morphology

Abbadi,

doi:10.3844/jcssp.2013.1389.1395

Cited by 27 publications

(5 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These artifacts emerge mainly due to an inhomogeneous contrast agent filling and can lead to imprecise extraction of the vascular network (see Fig 1A and 1B for illustration). The application of morphological operators has proven to be a useful approach for such issues, also in the filtering of vascular networks [ 29 – 31 ]. Thus, in order to minimalize the effect of these spuriosities, a morphological closing operator was applied to the binary model of the vasculature [ 32 ].…”

Section: Methodsmentioning

confidence: 99%

Planar cell polarity genes frizzled4 and frizzled6 exert patterning influence on arterial vessel morphogenesis

et al. 2017

View full text Add to dashboard Cite

Quantitative analysis of the vascular network anatomy is critical for the understanding of the vasculature structure and function. In this study, we have combined microcomputed tomography (microCT) and computational analysis to provide quantitative three-dimensional geometrical and topological characterization of the normal kidney vasculature, and to investigate how 2 core genes of the Wnt/planar cell polarity, Frizzled4 and Frizzled6, affect vascular network morphogenesis. Experiments were performed on frizzled4 (Fzd4-/-) and frizzled6 (Fzd6-/-) deleted mice and littermate controls (WT) perfused with a contrast medium after euthanasia and exsanguination. The kidneys were scanned with a high-resolution (16 μm) microCT imaging system, followed by 3D reconstruction of the arterial vasculature. Computational treatment includes decomposition of 3D networks based on Diameter-Defined Strahler Order (DDSO). We have calculated quantitative (i) Global scale parameters, such as the volume of the vasculature and its fractal dimension (ii) Structural parameters depending on the DDSO hierarchical levels such as hierarchical ordering, diameter, length and branching angles of the vessel segments, and (iii) Functional parameters such as estimated resistance to blood flow alongside the vascular tree and average density of terminal arterioles. In normal kidneys, fractal dimension was 2.07±0.11 (n = 7), and was significantly lower in Fzd4-/- (1.71±0.04; n = 4), and Fzd6-/- (1.54±0.09; n = 3) kidneys. The DDSO number was 5 in WT and Fzd4-/-, and only 4 in Fzd6-/-. Scaling characteristics such as diameter and length of vessel segments were altered in mutants, whereas bifurcation angles were not different from WT. Fzd4 and Fzd6 deletion increased vessel resistance, calculated using the Hagen-Poiseuille equation, for each DDSO, and decreased the density and the homogeneity of the distal vessel segments. Our results show that our methodology is suitable for 3D quantitative characterization of vascular networks, and that Fzd4 and Fzd6 genes have a deep patterning effect on arterial vessel morphogenesis that may determine its functional efficiency.

show abstract

Section: Methodsmentioning

confidence: 99%

Planar cell polarity genes frizzled4 and frizzled6 exert patterning influence on arterial vessel morphogenesis

et al. 2017

View full text Add to dashboard Cite

show abstract

“…The next step of our work is to convert pictures into a binary image [ 26 , 27 , 28 , 29 ]. The binarization process converts a pixel code to multiple bits of 4, 8, or more on a single bit.…”

Section: Methodsmentioning

confidence: 99%

Novel Computerized Method for Measurement of Retinal Vessel Diameters

et al. 2017

View full text Add to dashboard Cite

Several clinical studies reveal the relationship between alterations in the topologies of the human retinal blood vessel, the outcrop and the disease evolution, such as diabetic retinopathy, hypertensive retinopathy, and macular degeneration. Indeed, the detection of these vascular changes always has gaps. In addition, the manual steps are slow, which may be subjected to a bias of the perceiver. However, we can overcome these troubles using computer algorithms that are quicker and more accurate. This paper presents and investigates a novel method for measuring the blood vessel diameter in the retinal image. The proposed method is based on a thresholding segmentation and thinning step, followed by the characteristic point determination step by the Douglas-Peucker algorithm. Thereafter, it uses the active contours to detect vessel contour. Finally, Heron’s Formula is applied to assure the calculation of vessel diameter. The obtained results for six sample images showed that the proposed method generated less errors compared to other techniques, which confirms the high performance of the proposed method.

show abstract

“…To refine the vessels, a top-hat filter was implemented by using a single-disk SE with radii from 5 to 15 pixels [20], producing an image containing the parts that were smaller than the SE and were darker than their surroundings. Blood vessels appeared as clear elongated objects, while the background was black, as shown in Figure 3c.…”

Section: Preprocessing-vessel Segmentationmentioning

confidence: 99%

Exudates as Landmarks Identified through FCM Clustering in Retinal Images

et al. 2020

View full text Add to dashboard Cite

The aim of this work was to develop a method for the automatic identification of exudates, using an unsupervised clustering approach. The ability to classify each pixel as belonging to an eventual exudate, as a warning of disease, allows for the tracking of a patient’s status through a noninvasive approach. In the field of diabetic retinopathy detection, we considered four public domain datasets (DIARETDB0/1, IDRID, and e-optha) as benchmarks. In order to refine the final results, a specialist ophthalmologist manually segmented a random selection of DIARETDB0/1 fundus images that presented exudates. An innovative pipeline of morphological procedures and fuzzy C-means clustering was integrated in order to extract exudates with a pixel-wise approach. Our methodology was optimized, and verified and the parameters were fine-tuned in order to define both suitable values and to produce a more accurate segmentation. The method was used on 100 tested images, resulting in averages of sensitivity, specificity, and accuracy equal to 83.3%, 99.2%, and 99.1%, respectively.

show abstract

Blood Vessels Extraction Using Mathematical Morphology

Cited by 27 publications

References 4 publications

Planar cell polarity genes frizzled4 and frizzled6 exert patterning influence on arterial vessel morphogenesis

Planar cell polarity genes frizzled4 and frizzled6 exert patterning influence on arterial vessel morphogenesis

Novel Computerized Method for Measurement of Retinal Vessel Diameters

Exudates as Landmarks Identified through FCM Clustering in Retinal Images

Contact Info

Product

Resources

About