Analysis and classification of tissue with scatterer structure templates

Donohue, Kevin D.; Forsberg, Flemming; Piccoli, C.V.; Goldberg, Barry B.

doi:10.1109/58.753018

Cited by 47 publications

(38 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The characterization of the calcium tissue seems to be the less difficult one since the calcium tissue has a very high echo-reflectivity and homogeneity (see 3). When compared with the fibrous plaque, the Adaboost procedure refines the classification increasing the recognition rates to an average of 88%.…”

Section: Fig 3 Classification Of Plaquesmentioning

confidence: 99%

“…The unreliability of gray level only methods to achieve good discrimination among the different kind of tissues forced us to use more complex measures, usually based on texture analysis. Several researching groups have reported different approximations to characterize the tissue of intravascular ultrasound images [1] [2] [3]. Most of the literature found in the tissue characterization matters use texture features, being co-occurrence matrices the most popular of all feature extractors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Adaboost to Classify Plaque Appearance in IVUS Images

Pujol

Radeva

Vitrià

et al. 2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Intravascular Ultrasound images represent a unique tool to analyze the morphological vessel structures and make decisions about plaque presence. Texture analysis is a robust way to detect and characterize different kind of vessel plaques. In this article, we make exhaustive comparison between different feature spaces to optimally describe plaque appearance and show that applying advanced classification techniques based on multiple classifiers (adaboost) significantly improves the final results. The validation tests on different kind of plaques are very encouraging.

show abstract

Section: Fig 3 Classification Of Plaquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Adaboost to Classify Plaque Appearance in IVUS Images

Pujol

Radeva

Vitrià

et al. 2004

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…28 Therefore, the maximization in Equation (12) produces a taper that is optimal in the sense that it minimizes an upper bound on spectral bias. The solution to the maximization problem in Equation (12) is given by the eigenvector corresponding to the largest eigenvalue of the matrix given by 17 (13) for m, n = 1, 2, …, N. The process for converting the optimization problem in Equation (12) to the eigenvector analysis problem in Equation (13) can be found in a previous work. 18 The PR taper with gaps corresponding to gap pattern vector I is found by solving for the eigenvector corresponding to the largest eigenvalue of the matrix given by 17 (14) The gapped PR tapers were computed using the process described in a previous study.…”

Section: Spectrum Estimation: Tapers With Gapsmentioning

confidence: 99%

Backscatter coefficient estimation using tapers with gaps

Luchies

Oelze

2014

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

When using the backscatter coefficient (BSC) to estimate quantitative ultrasound parameters such as the effective scatterer diameter (ESD) and the effective acoustic concentration (EAC), it is necessary to assume that the interrogated medium contains diffuse scatterers. Structures that invalidate this assumption can affect the estimated BSC parameters in terms of increased bias and variance and decrease performance when classifying disease. In this work, a method was developed to mitigate the effects of echoes from structures that invalidate the assumption of diffuse scattering, while preserving as much signal as possible for obtaining diffuse scatterer property estimates. Backscattered signal sections that contained nondiffuse signals were identified and a windowing technique was used to provide BSC estimates for diffuse echoes only. Experiments from physical phantoms were used to evaluate the effectiveness of the proposed BSC estimation methods. Tradeoffs associated with effective mitigation of specular scatterers and bias and variance introduced into the estimates were quantified. Analysis of the results suggested that discrete prolate spheroidal (PR) tapers with gaps provided the best performance for minimizing BSC error. Specifically, the mean square error for BSC between measured and theoretical had an average value of approximately 1.0 and 0.2 when using a Hanning taper and PR taper respectively, with six gaps. The BSC error due to amplitude bias was smallest for PR (Nω = 1) tapers. The BSC error due to shape bias was smallest for PR (Nω = 4) tapers. These results suggest using different taper types for estimating ESD versus EAC.

show abstract

“…This method gives two types of diffuse images: a diffuse friction coefficient image and a diffuse forced frequency image, with the latter showing better contrast between tissues. Other methods 2,4,8 exist for detecting specular reflectors; however, these methods using generalized spectrum techniques often do not aim to detect the class of specular reflectors that are directionally dependent. Instead, any reflection that is strong compared to the surrounding weak reflections is viewed as specular, and the goal is to identify all such strong reflections.…”

mentioning

confidence: 99%

Multidirectional Scattering Models for 3-Dimensional Ultrasound Imaging

Ijaz

Housden

Treece

et al. 2013

Journal of Ultrasound in Medicine

View full text Add to dashboard Cite

An ultrasound image is created from backscattered echoes originating from both diffuse and directional scattering. It is potentially useful to separate these two components for the purpose of tissue characterization. This article presents several models for visualization of scattering fields on 3-dimensional (3D) ultrasound imaging. By scanning the same anatomy from multiple directions, we can observe the variation of specular intensity as a function of the viewing angle. This article considers two models for estimating the diffuse and specular components of the backscattered intensity: a modification of the well-known Phong reflection model and an existing exponential model. We examine 2-dimensional implementations and also propose novel 3D extensions of these models in which the probe is not constrained to rotate within a plane. Both simulation and experimental results show that improved performance can be achieved with 3D models.Key Words-diffuse; scattering; specular; 3-dimensional ultrasound imaging specular, and quasiperiodic structures by using harmonic models for particle movements. This method gives two types of diffuse images: a diffuse friction coefficient image and a diffuse forced frequency image, with the latter showing better contrast between tissues. Other methods 2,4,8 exist for detecting specular reflectors; however, these methods using generalized spectrum techniques often do not aim to detect the class of specular reflectors that are directionally dependent. Instead, any reflection that is strong compared to the surrounding weak reflections is viewed as specular, and the goal is to identify all such strong reflections.Recently, multidirectional ultrasound echo signals have been considered for differentiation and characterization of specular reflection. 1 In this work, the authors have utilised limited-angle spatial compound imaging at each point of the image plane as a function of angle of insonification. A symmetric 2-dimensional (2D) exponential model is fitted in terms of least squares to the measured backscatter over different angles of insonification. The above procedure has promising prospects for differentiation of scar tissues from the surroundings based on the specular reflections.In this article, we are extending this work to consider an alternative reflection model. Our motivation for this research comes from the Phong reflection model 9 that has become the de facto standard as an illumination model in computer graphics applications. This model is an empirical model and considers that the specular reflection is stronger in one direction and falls off rapidly as we move away from it. This approach has the advantage of being conceptually simple and in a different context 10 has previously been used as a reflection model for deconvolution of a single 2D ultrasound image. That approach estimates the specular direction using an edge detection approach from the image data. In comparison, we use multiple scans from different directions to determine the true reflection properties of the un...

show abstract

Analysis and classification of tissue with scatterer structure templates

Cited by 47 publications

References 19 publications

Adaboost to Classify Plaque Appearance in IVUS Images

Adaboost to Classify Plaque Appearance in IVUS Images

Backscatter coefficient estimation using tapers with gaps

Multidirectional Scattering Models for 3-Dimensional Ultrasound Imaging

Contact Info

Product

Resources

About