Model-Based Detection of Tubular Structures in 3D Images

Krissian, Karl; Malandain, Grégoire; Ayache, Nicholas; Vaillant, Régis; Trousset, Yves

doi:10.1006/cviu.2000.0866

Cited by 365 publications

(277 citation statements)

References 37 publications

Supporting

Mentioning

273

Contrasting

Order By: Relevance

“…The proposed method is related to the heuristics that the scale at which the maximum normalized response is obtained is selected as the optimal scale of the tubular structures [9], [10], [11]. The optimal scale σ opt is regarded as the true radius, that is, σ opt = 0.5D, when cross-sectional intensity distributions are Gaussian [9], while the relation σ opt = 0.36D is observed when they have pill-box shapes (as shown in Fig.…”

Section: Discussionmentioning

confidence: 99%

Accurate Quantification of Small-Diameter Tubular Structures in Isotropic CT Volume Data Based on Multiscale Line Filter Responses

Sato

Yamamoto

Tamura

2004

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2004

View full text Add to dashboard Cite

Abstract.A method fully utilizing multiscale line filter responses is presented to estimate the point spread function (PSF) of a CT scanner and diameters of small tubular structures based on the PSF. The estimation problem is formulated as a least square fitting of a sequence of multiscale responses obtained at each medial axis point to the precomputed multiscale response curve for the ideal line model. The method was validated through phantom experiments and demonstrated to accurately measure small-diameter structures which are significantly overestimated by conventional methods based on the full width half maximum (FWHM) and zero-crossing edge detection.

show abstract

Section: Discussionmentioning

confidence: 99%

Accurate Quantification of Small-Diameter Tubular Structures in Isotropic CT Volume Data Based on Multiscale Line Filter Responses

Sato

Yamamoto

Tamura

2004

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2004

View full text Add to dashboard Cite

show abstract

“…The methodology for scale-invariant ridge detection based on maximisation of γ -normalized measures of ridge strength (Lindeberg [97,100]) was extended to three-dimensional images by Sato et al [139], Frangi et al [46] and Krissian et al [76]; see also Kirbas and Quek [67] for a review of vessel extraction techniques. Closely related works on multi-scale ridge detection have presented by Pizer and his co-workers [134] leading to their notion of M-reps (Pizer et al [133]).…”

Section: Related Workmentioning

confidence: 99%

Image Matching Using Generalized Scale-Space Interest Points

Lindeberg

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The performance of matching and object recognition methods based on interest points depends on both the properties of the underlying interest points and the choice of associated image descriptors. This paper demonstrates advantages of using generalized scale-space interest point detectors in this context for selecting a sparse set of points for computing image descriptors for image-based matching. For detecting interest points at any given scale, we make use of the Laplacian ∇ 2 norm L, the determinant of the Hessian det H norm L and four new unsigned or signed Hessian feature strength measures D 1,norm L,D 1,norm L, D 2,norm L and D 2,norm L, which are defined by generalizing the definitions of the Harris and Shi-and-Tomasi operators from the second moment matrix to the Hessian matrix. Then, feature selection over different scales is performed either by scale selection from local extrema over scale of scale-normalized derivates or by linking features over scale into feature trajectories and computing a significance measure from an integrated measure of normalized feature strength over scale. A theoretical analysis is presented of the robustness of the differential entities underlying these interest points under image deformations, in terms of invariance properties under affine image deformations or approximations thereof. Disregarding the effect of the rotationally symmetric scale-space smoothing operation, the determinant of the Hessian det H norm L is a truly affine covariant differential entity and the Hessian feature strength measures D 1,norm L andD 1,norm L have a major contribution from the affine covariant determinant of the Hessian, implying that local extrema of these differen- It is shown how these generalized scale-space interest points allow for a higher ratio of correct matches and a lower ratio of false matches compared to previously known interest point detectors within the same class. The best results are obtained using interest points computed with scale linking and with the new Hessian feature strength measures D 1,norm L,D 1,norm L and the determinant of the Hessian det H norm L being the differential entities that lead to the best matching performance under perspective image transformations with significant foreshortening, and better than the more commonly used Laplacian operator, its difference-of-Gaussians approximation or the Harris-Laplace operator. We propose that these generalized scale-space interest points, when accompanied by associated local scale-invariant image descriptors, should allow for better performance of interest point based methods for image-based matching, object recognition and related visual tasks.

show abstract

“…A number of methods have been proposed for automatic extraction of skeleton curves in an intensity volume without need for segmentation using gradient zero-crossing [10,12], multiscale centerlines [15], and tracking or pruning using local structure tensors [1,29]. While the resulting skeletons are more robust as they do not rely on the quality of segmentation, they can still be disrupted by the presence of noise [17].…”

Section: Previous Workmentioning

confidence: 99%

Interactive skeletonization of intensity volumes

Abeysinghe

2009

Vis Comput

View full text Add to dashboard Cite

We present an interactive approach for identifying skeletons (i.e. centerlines) in intensity volumes, such as those produced by biomedical imaging. While skeletons are very useful for a range of image analysis tasks, it is extremely difficult to obtain skeletons with correct connectivity and shape from noisy inputs using automatic skeletonization methods. In this paper we explore how easy-to-supply user inputs, such as simple mouse clicking and scribbling, can guide the creation of satisfactory skeletons. Our contributions include formulating the task of drawing 3D centerlines given 2D user inputs as a constrained optimization problem, solving this problem on a discrete graph using a shortest-path algorithm, building a graphical interface for interactive skeletonization and testing it on a range of biomedical data.

show abstract

Model-Based Detection of Tubular Structures in 3D Images

Cited by 365 publications

References 37 publications

Accurate Quantification of Small-Diameter Tubular Structures in Isotropic CT Volume Data Based on Multiscale Line Filter Responses

Accurate Quantification of Small-Diameter Tubular Structures in Isotropic CT Volume Data Based on Multiscale Line Filter Responses

Image Matching Using Generalized Scale-Space Interest Points

Interactive skeletonization of intensity volumes

Contact Info

Product

Resources

About