Learning to estimate out-of-plane motion in ultrasound imagery of real tissue

Laporte, Catherine

doi:10.1016/j.media.2010.08.006

Cited by 22 publications

(10 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although precisely identical tissues cannot be observed in 2D US slices differing by out-of-plane rotation, image similarity measures can be effective at identifying similar image patches in US images acquired with minor differences in probe position. For example, image intensity correlation is known to degrade smoothly with out-of-plane displacement due to non-zero US slice thickness, and this principle is used in speckle-decorrelation methods [17], [18], [19] that determine elevational separation between US images as a function of an intensity decorrelation profile.…”

Section: Methodsmentioning

confidence: 99%

Phantomless Auto-Calibration and Online Calibration Assessment for a Tracked Freehand 2-D Ultrasound Probe

Toews

Wells

2018

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

This paper presents a method for automatically calibrating and assessing the calibration quality of an externally tracked 2-D ultrasound (US) probe by scanning arbitrary, natural tissues, as opposed a specialized calibration phantom as is the typical practice. A generative topic model quantifies the posterior probability of calibration parameters conditioned on local 2-D image features arising from a generic underlying substrate. Auto-calibration is achieved by identifying the maximum a-posteriori image-to-probe transform, and calibration quality is assessed online in terms of the posterior probability of the current image-to-probe transform. Both are closely linked to the 3-D point reconstruction error (PRE) in aligning feature observations arising from the same underlying physical structure in different US images. The method is of practical importance in that it operates simply by scanning arbitrary textured echogenic structures, e.g., in-vivo tissues in the context of the US-guided procedures, without requiring specialized calibration procedures or equipment. Observed data take the form of local scale-invariant features that can be extracted and fit to the model in near real-time. Experiments demonstrate the method on a public data set of in vivo human brain scans of 14 unique subjects acquired in the context of neurosurgery. Online calibration assessment can be performed at approximately 3 Hz for the US images of pixels. Auto-calibration achieves an internal mean PRE of 1.2 mm and a discrepancy of [2 mm, 6 mm] in comparison to the calibration via a standard phantom-based method.

show abstract

Section: Methodsmentioning

confidence: 99%

Phantomless Auto-Calibration and Online Calibration Assessment for a Tracked Freehand 2-D Ultrasound Probe

Toews

Wells

2018

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…Other efforts intend to increase the motion estimation accuracy by adapting the correlation curve and compensating the loss of coherency by using additional information such as correlation in the axial and lateral directions 8 , beam steering 9 , developing a heuristic method to consider the coherent part of the image 10 , using Maximum Likelihood Estimators (MLE) for motion estimation 11 , or incorporating the information of several noisy measurements in a probabilistic framework 12 . Recently a new learning based method of out-of-plane motion estimation on imagery of real tissue has been introduced 13 . They adapt the scale factor of the nominal correlation curve based on training data.…”

Section: Introductionmentioning

confidence: 99%

Out-of-plane motion estimation based on a Rician-Inverse Gaussian model of RF ultrasound signals: speckle tracking without fully developed speckle

et al. 2012

View full text Add to dashboard Cite

Fully developed speckle has been used previously to estimate the out-of-plane motion of ultrasound images. However, in real tissue the rarity of such patterns and the presence of coherency diminish both the precision and the accuracy of the out-of-plane motion estimation. In this paper, for the first time, we propose a simple mathematical derivation for out-ofplane motion estimation in which the coherent and non-coherent parts of the RF echo signal are separated. This method is based on the Rician-Inverse Gaussian stochastic model of the speckle formation process, which can be considered as a generalized form of the K-distribution with richer parameterization. The flexibility of the proposed method allows considering any patch of the RF echo signal for the purpose of displacement estimation. The experimental results on real tissue demonstrate the potential of the proposed method for accurate out-of-plane estimation. The underestimation of motion in ex vivo bovine tissue at 1 mm displacement is reduced to 15.5% compared to 37% for a base-line method.

show abstract

“…Ultrasound is often the preferred modality as it is non-invasive, cheap, widely available and easy to use. Commonly used techniques to determine strain in ultrasound imaging include tracking of anatomical landmarks, 8 Doppler-mode imaging, 9 speckle decorrelation analysis [10][11][12][13] and speckle tracking (on the radio-frequency signal [14][15][16] or on the B-mode images [17][18][19][20] ). All of these methods have one or more limitations.…”

Section: Introductionmentioning

confidence: 99%

Tendon strain imaging using non-rigid image registration: a validation study

et al. 2012

View full text Add to dashboard Cite

Ultrasound image has already been proved to be a useful tool for non-invasive strain quantifications in soft tissue. While clinical applications only include cardiac imaging, the development of techniques suitable for musculoskeletal system is an active area of research. On this study, a technique for speckle tracking on ultrasound images using non-rigid image registration is presented. This approach is based on a single 2D+t registration procedure, in which the temporal changes on the B-mode speckle patterns are locally assessed. This allows estimating strain from ultrasound image sequences of tissues under deformation while imposing temporal smoothness in the deformation field, originating smooth strain curves. METHODS: The tracking algorithm was systematically tested on synthetic images and gelatin phantoms, under sinusoidal deformations with amplitudes between 0.5% and 4.0%, at frequencies between 0.25Hz and 2.0Hz. Preliminary tests were also performed on Achilles tendons isolated from human cadavers. RESULTS: The strain was estimated with deviations of −0.011% ± 0.053% on the synthetic images and agreements of ±0.28% on the phantoms. Some tests with real tendons show good tracking results. However, significant variability between the trials still exists. CONCLUSIONS: The proposed image registration methodology constitutes a robust tool for motion and deformation tracking in both simulated and real phantom data. Strain estimation in both cases reveals that the proposed method is accurate and provides good precision. Although the ex-vivo results are still preliminary, the potential of the proposed algorithm is promising. This suggests that further improvements, together with systematic testing, can lead to in-vivo and clinical applications.

show abstract

Learning to estimate out-of-plane motion in ultrasound imagery of real tissue

Cited by 22 publications

References 45 publications

Phantomless Auto-Calibration and Online Calibration Assessment for a Tracked Freehand 2-D Ultrasound Probe

Phantomless Auto-Calibration and Online Calibration Assessment for a Tracked Freehand 2-D Ultrasound Probe

Out-of-plane motion estimation based on a Rician-Inverse Gaussian model of RF ultrasound signals: speckle tracking without fully developed speckle

Tendon strain imaging using non-rigid image registration: a validation study

Contact Info

Product

Resources

About