Vesselness enhancement diffusion

Cañero, C.; Radeva, Petia

doi:10.1016/j.patrec.2003.08.001

Cited by 53 publications

(30 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Let be the Hessian matrix for at point . Following (1) and (10), the Hessian matrix for at point is then (11) Eigenvectors and the corresponding eigenvalues , where , , of give interesting measures of structures along the local line. Notice that and are functions of .…”

Section: A Local Line Integralsmentioning

confidence: 99%

“…In order to find the probing line that can best approximate the vessel segment, it is observed that, at a vessel point , when the integral line is aligned with the vessel, it will also have the following relationships , , , which are the same to the relationships as listed previously. 1 At the vessel point, becomes the average of the similar Hessian matrices along according to (11), given the assumption that the intensity variations are relatively small along the vessel. By replacing the Hessian matrix of each pixel along the line with the average Hessian matrix defined in (11), it can result in smoothed Hessian matrices with the reduction in sharp transitions across matrices because smoothing Hessian matrices is equivalent to smoothing the second partial derivatives of the image.…”

Section: A Local Line Integralsmentioning

confidence: 99%

“…1 At the vessel point, becomes the average of the similar Hessian matrices along according to (11), given the assumption that the intensity variations are relatively small along the vessel. By replacing the Hessian matrix of each pixel along the line with the average Hessian matrix defined in (11), it can result in smoothed Hessian matrices with the reduction in sharp transitions across matrices because smoothing Hessian matrices is equivalent to smoothing the second partial derivatives of the image. As noise can cause the sharp transitions in Hessian matrices, thus, this averaging process makes more resistant to noise.…”

Section: A Local Line Integralsmentioning

confidence: 99%

“…While the Hessian-based methods are widely used in different areas of image processing [7]- [11], its drawback is obvious due to the fact that the Hessian matrix is based upon second derivatives, which are local measures. Therefore, without a relatively global view of the vasculatures, the Hessian-based methods only offer local shape descriptions.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

VE-LLI-VO: Vessel Enhancement Using Local Line Integrals and Variational Optimization

Yuan¹,

Luo²,

Chung³

2011

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Abstract-Vessel enhancement is a primary preprocessing step for vessel segmentation and visualization of vasculatures. In this paper, a new vessel enhancement technique is proposed in order to produce accurate vesselness measures and vessel direction estimations that are less subject to local intensity abnormalities. The proposed method is called vessel enhancement using local line integrals and variational optimization . First, vessel enhancement using local line integrals is introduced in which a vessel model is embedded by regarding a vessel segment as a straight line based upon the second order information of the local line integrals. Useful quantities similar to the eigenvalues and eigenvectors of the Hessian matrix are produced. Moreover, based upon the local line integrals, junctions can be detected and handled effectively. This can help deal with the bifurcation suppression problem which exists in the Hessian-based enhancement methods. Then a more generic curve model is embedded to model vessels and a variational optimization framework is introduced to generate optimized vesselness measures. Experiments have been conducted on both synthetic images and retinal images. It is experimentally demonstrated that produces improved performance as compared with the widely used techniques in terms of both vesselness measurement and vessel direction estimation.

show abstract

Section: A Local Line Integralsmentioning

confidence: 99%

Section: A Local Line Integralsmentioning

confidence: 99%

Section: A Local Line Integralsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

VE-LLI-VO: Vessel Enhancement Using Local Line Integrals and Variational Optimization

Yuan¹,

Luo²,

Chung³

2011

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Furthermore, diffusion filtering have been used for enhancing vessels, e.g. Cañero and Radeva (2003); Manniesing et al (2006); Krissian (2002). Unfortunately, these last-mentioned methods rely on the estimation of the Hessian at different scales.…”

Section: Introductionmentioning

confidence: 99%

Gradient-based enhancement of tubular structures in medical images

Moreno

Smedby

2015

Medical Image Analysis

View full text Add to dashboard Cite

Vesselness filters aim at enhancing tubular structures in medical images. The most popular vesselness filters are based on eigenanalyses of the Hessian matrix computed at different scales. However, Hessian-based methods have well-known limitations, most of them related to the use of second order derivatives. In this paper, we propose an alternative strategy in which ring-like patterns are sought in the local orientation distribution of the gradient. The method takes advantage of symmetry properties of ring-like patterns in the spherical harmonics domain. For bright vessels, gradients not pointing towards the center are filtered out from every local neighborhood in a first step. The opposite criterion is used for dark vessels. Afterwards, structuredness, evenness and uniformness measurements are computed from the power spectrum in spherical harmonics of both the original and the half-zeroed orientation distribution of the gradient. Finally, the features are combined into a single vesselness measurement. Alternatively, a structure tensor that is suitable for vesselness can be estimated before the analysis in spherical harmonics. The two proposed methods are called Ring Pattern Detector (RPD) and Filtered Structure Tensor (FST) respectively. Experimental results with computed tomography angiography data show that the proposed filters perform better compared to the state-of-the-art.

show abstract