Ultrasound image segmentation: a survey

Adaptively learning local shape statistics for prostate segmentation in ultrasound

Automatic segmentation of the prostate from 2-D transrectal ultrasound (TRUS) is a highly desired tool in many clinical applications. However, it is a very challenging task, especially for segmenting the base and apex of the prostate due to the large shape variations in those areas compared to the midgland, which leads many existing segmentation methods to fail. To address the problem, this paper presents a novel TRUS video segmentation algorithm using both global population-based and patient-specific local shape statistics as shape constraint. By adaptively learning shape statistics in a local neighborhood during the segmentation process, the algorithm can effectively capture the patient-specific shape statistics and quickly adapt to the local shape changes in the base and apex areas. The learned shape statistics is then used as the shape constraint in a deformable model for TRUS video segmentation. The proposed method can robustly segment the entire gland of the prostate with significantly improved performance in the base and apex regions, compared to other previously reported methods. Our method was evaluated using 19 video sequences obtained from different patients and the average mean absolute distance error was 1.65 ± 0.47 mm.

A 3D freehand ultrasound system for multi-view reconstructions from sparse 2D scanning planes

Background

A significant limitation of existing 3D ultrasound systems comes from the fact that the majority of them work with fixed acquisition geometries. As a result, the users have very limited control over the geometry of the 2D scanning planes.

Methods

We present a low-cost and flexible ultrasound imaging system that integrates several image processing components to allow for 3D reconstructions from limited numbers of 2D image planes and multiple acoustic views. Our approach is based on a 3D freehand ultrasound system that allows users to control the 2D acquisition imaging using conventional 2D probes.

For reliable performance, we develop new methods for image segmentation and robust multi-view registration. We first present a new hybrid geometric level-set approach that provides reliable segmentation performance with relatively simple initializations and minimum edge leakage. Optimization of the segmentation model parameters and its effect on performance is carefully discussed. Second, using the segmented images, a new coarse to fine automatic multi-view registration method is introduced. The approach uses a 3D Hotelling transform to initialize an optimization search. Then, the fine scale feature-based registration is performed using a robust, non-linear least squares algorithm. The robustness of the multi-view registration system allows for accurate 3D reconstructions from sparse 2D image planes.

Results

Volume measurements from multi-view 3D reconstructions are found to be consistently and significantly more accurate than measurements from single view reconstructions. The volume error of multi-view reconstruction is measured to be less than 5% of the true volume. We show that volume reconstruction accuracy is a function of the total number of 2D image planes and the number of views for calibrated phantom. In clinical in-vivo cardiac experiments, we show that volume estimates of the left ventricle from multi-view reconstructions are found to be in better agreement with clinical measures than measures from single view reconstructions.

Conclusions

Multi-view 3D reconstruction from sparse 2D freehand B-mode images leads to more accurate volume quantification compared to single view systems. The flexibility and low-cost of the proposed system allow for fine control of the image acquisition planes for optimal 3D reconstructions from multiple views.

Segmentation of 3D RF echocardiography using a multiframe spatio-temporal predictor

We present an approach for segmenting left ventricular endocardial boundaries from RF ultrasound. Segmentation is achieved jointly using an independent identically distributed (i.i.d.) spatial model for RF intensity and a multiframe conditional model. The conditional model relates neighboring frames in the image sequence by means of a computationally efficient linear predictor that exploits spatio-temporal coherence in the data. Segmentation using the RF data overcomes problems due to image inhomogeneities often amplified in B-mode segmentation and provides geometric constraints for RF phase-based speckle tracking. The incorporation of multiple frames in the conditional model significantly increases the robustness and accuracy of the algorithm. Results are generated using between 2 and 5 frames of RF data for each segmentation and are validated by comparison with manual tracings and automated B-mode boundary detection using standard (Chan and Vese-based) level sets on echocardiographic images from 27 3D sequences acquired from 6 canine studies.

Segmentation of 2D fetal ultrasound images by exploiting context information using conditional random fields

This paper proposes a novel approach for segmenting fetal ultrasound images. This problem presents a variety of challenges including high noise, low contrast, and other US imaging properties such as similarity between texture and gray levels of two organs/ tissues. In this paper, we have proposed a Conditional Random Field (CRF) based framework to handle challenges in segmenting fetal ultrasound images. Clinically, it is known that fetus is surrounded by specific maternal tissues, amniotic fluid and placenta. We exploit this context information using CRFs for segmenting the fetal images accurately. The proposed CRF framework uses wavelet based texture features for representing the ultrasound image and Support Vector Machines (SVM) for initial label prediction. Initial results on a limited dataset of real world ultrasound images of fetus are promising. Results show that proposed method could handle the noise and similarity between fetus and its surroundings in ultrasound images.

Tissue typing using ultrasound RF time series: experiments with animal tissue samples

PURPOSE

This article provides experimental evidence to show that the time series of radiofrequency (RF) ultrasound data can be used for tissue typing. It also explores the tissue typing information in RF time series. Clinical and high-frequency ultrasound are studied.

METHODS

Bovine liver, pig liver, bovine muscle, and chicken breast were used in the experiments as the animal tissue types. In the proposed approach, the authors record RF echo signals backscattered from tissue, while the imaging probe and the tissue are stationary. This sequence of recorded RF data generates a time series of RF echoes for each spatial sample of the RF signal. The authors use spectral and fractal features of ultrasound RF time series averaged over a region of interest, along with feedforward neural networks for tissue typing. The experiments are repeated at ultrasound frequency of 6.6 and also 55 MHz. The effects of increasing power and frame rate are studied.

RESULTS

The methodology yielded an average two-class classification accuracy of 95.1% when ultrasound data were acquired at 6.6 MHz and 98.1% when data were collected with a high-frequency probe operating at 55 MHz. In four-class classification experiments, the recorded accuracies were 78.6% and 86.5% for low and high-frequency ultrasound data, respectively. A set of 12 texture features extracted from the B-mode image equivalents of the RF data yields an accuracy of only 77.5% in typing the analyzed tissues. An increase in acoustic power and the frame rate of ultrasound results in an improvement in classification results.

CONCLUSIONS

The results of this study demonstrate that RF time series can be used for ultrasound-based tissue typing. Further investigation of the underlying physical mechanisms is necessary.

Semi-automatic segmentation for prostate interventions

In this paper we report and characterize a semi-automatic prostate segmentation method for prostate brachytherapy. Based on anatomical evidence and requirements of the treatment procedure, a warped and tapered ellipsoid was found suitable as the a-priori 3D shape of the prostate. By transforming the acquired endorectal transverse images of the prostate into ellipses, the shape fitting problem was cast into a convex problem which can be solved efficiently. The average whole gland error between non-overlapping volumes created from manual and semi-automatic contours from 21 patients was 6.63 ± 0.9%. For use in brachytherapy treatment planning, the resulting contours were modified, if deemed necessary, by radiation oncologists prior to treatment. The average whole gland volume error between the volumes computed from semi-automatic contours and those computed from modified contours, from 40 patients, was 5.82 ± 4.15%. The amount of bias in the physicians' delineations when given an initial semi-automatic contour was measured by comparing the volume error between 10 prostate volumes computed from manual contours with those of modified contours. This error was found to be 7.25 ± 0.39% for the whole gland. Automatic contouring reduced subjectivity, as evidenced by a decrease in segmentation inter- and intra-observer variability from 4.65% and 5.95% for manual segmentation to 3.04% and 3.48% for semi-automatic segmentation, respectively. We characterized the performance of the method relative to the reference obtained from manual segmentation by using a novel approach that divides the prostate region into nine sectors. We analyzed each sector independently as the requirements for segmentation accuracy depend on which region of the prostate is considered. The measured segmentation time is 14 ± 1s with an additional 32 ± 14s for initialization. By assuming 1-3 min for modification of the contours, if necessary, a total segmentation time of less than 4 min is required, with no additional time required prior to treatment planning. This compares favorably to the 5-15 min manual segmentation time required for experienced individuals. The method is currently used at the British Columbia Cancer Agency (BCCA) Vancouver Cancer Centre as part of the standard treatment routine in low dose rate prostate brachytherapy and is found to be a fast, consistent and accurate tool for the delineation of the prostate gland in ultrasound images.

Information tracking approach to segmentation of ultrasound imagery of the prostate

The volume of the prostate is known to be a pivotal quantity used by clinicians to assess the condition of the gland during prostate cancer screening. As an alternative to palpation, an increasing number of methods for estimation of the volume of the prostate are based on using imagery data. The necessity to process large volumes of such data creates a need for automatic segmentation tools which would allow the estimation to be carried out with maximum accuracy and efficiency. In particular, the use of transrectal ultrasound (TRUS) imaging in prostate cancer screening seems to be becoming a standard clinical practice because of the high benefit-to-cost ratio of this imaging modality. Unfortunately, the segmentation of TRUS images is still hampered by relatively low contrast and reduced SNR of the images, thereby requiring the segmentation algorithms to incorporate prior knowledge about the geometry of the gland. In this paper, a novel approach to the problem of segmenting the TRUS images is described. The proposed approach is based on the concept of distribution tracking, which provides a unified framework for modeling and fusing image-related and morphological features of the prostate. Moreover, the same framework allows the segmentation to be regularized by using a new type of weak shape priors, which minimally bias the estimation procedure, while rendering the procedure stable and robust. The value of the proposed methodology is demonstrated in a series of in silico and in vivo experiments.

Robotic tissue tracking for beating heart mitral valve surgery

The rapid motion of the heart presents a significant challenge to the surgeon during intracardiac beating heart procedures. We present a 3D ultrasound-guided motion compensation system that assists the surgeon by synchronizing instrument motion with the heart. The system utilizes the fact that certain intracardiac structures, like the mitral valve annulus, have trajectories that are largely constrained to translation along one axis. This allows the development of a real-time 3D ultrasound tissue tracker that we integrate with a 1 degree-of-freedom (DOF) actuated surgical instrument and predictive filter to devise a motion tracking system adapted to mitral valve annuloplasty. In vivo experiments demonstrate that the system provides highly accurate tracking (1.0 mm error) with 70% less error than manual tracking attempts.

Combined image-processing algorithms for improved optical coherence tomography of prostate nerves

Cavernous nerves course along the surface of the prostate gland and are responsible for erectile function. These nerves are at risk of injury during surgical removal of a cancerous prostate gland. In this work, a combination of segmentation, denoising, and edge detection algorithms are applied to time-domain optical coherence tomography (OCT) images of rat prostate to improve identification of cavernous nerves. First, OCT images of the prostate are segmented to differentiate the cavernous nerves from the prostate gland. Then, a locally adaptive denoising algorithm using a dual-tree complex wavelet transform is applied to reduce speckle noise. Finally, edge detection is used to provide deeper imaging of the prostate gland. Combined application of these three algorithms results in improved signal-to-noise ratio, imaging depth, and automatic identification of the cavernous nerves, which may be of direct benefit for use in laparoscopic and robotic nerve-sparing prostate cancer surgery.

3D prostate segmentation in ultrasound images based on tapered and deformed ellipsoids

Prostate segmentation from trans-rectal transverse B-mode ultrasound images is required for radiation treatment of prostate cancer. Manual segmentation is a time-consuming task, the results of which are dependent on image quality and physicians' experience. This paper introduces a semi-automatic 3D method based on super-ellipsoidal shapes. It produces a 3D segmentation in less than 15 seconds using a warped, tapered ellipsoid fit to the prostate. A study of patient images shows good performance and repeatability. This method is currently in clinical use at the Vancouver Cancer Center where it has become the standard segmentation procedure for low dose-rate brachytherapy treatment.

Three-dimensional ultrasound imaging

This review is about the development of three-dimensional (3D) ultrasonic medical imaging, how it works, and where its future lies. It assumes knowledge of two-dimensional (2D) ultrasound, which is covered elsewhere in this issue. The three main ways in which 3D ultrasound may be acquired are described: the mechanically swept 3D probe, the 2D transducer array that can acquire intrinsically 3D data, and the freehand 3D ultrasound. This provides an appreciation of the constraints implicit in each of these approaches together with their strengths and weaknesses. Then some of the techniques that are used for processing the 3D data and the way this can lead to information of clinical value are discussed. A table is provided to show the range of clinical applications reported in the literature. Finally, the discussion relating to the technology and its clinical applications to explain why 3D ultrasound has been relatively slow to be adopted in routine clinics is drawn together and the issues that will govern its development in the future explored.

Ultrasound image segmentation and tissue characterization

Ultrasound image segmentation deals with delineating the boundaries of structures, as a step towards semi-automated or fully automated measurement of dimensions or for characterizing tissue regions. Ultrasound tissue characterization (UTC) is driven by knowledge of the physics of ultrasound and its interactions with biological tissue, and has traditionally used signal modelling and analysis to characterize and differentiate between healthy and diseased tissue. Thus, both aim to enhance the capabilities of ultrasound as a quantitative tool in clinical medicine, and the two end goals can be the same, namely to characterize the health of tissue. This article reviews both research topics, and finds that the two fields are becoming more tightly coupled, even though there are key challenges to overcome in each area, influenced by factors such as more open software-based ultrasound system architectures, increased computational power, and advances in imaging transducer design.

A review of noninvasive ultrasound image processing methods in the analysis of carotid plaque morphology for the assessment of stroke risk

Noninvasive ultrasound imaging of carotid plaques allows for the development of plaque-image analysis methods associated with the risk of stroke. This paper presents several plaque-image analysis methods that have been developed over the past years. The paper begins with a review of clinical methods for visual classification that have led to standardized methods for image acquisition, describes methods for image segmentation and denoising, and provides an overview of the several texture-feature extraction and classification methods that have been applied. We provide a summary of emerging trends in 3-D imaging methods and plaque-motion analysis. Finally, we provide a discussion of the emerging trends and future directions in our concluding remarks.

Endocardial boundary extraction in left ventricular echocardiographic images using fast and adaptive B-spline snake algorithm

PURPOSE

A fast and robust algorithm was developed for automatic segmentation of the left ventricular endocardial boundary in echocardiographic images. The method was applied to calculate left ventricular volume and ejection fraction estimation.

METHODS

A fast adaptive B-spline snake algorithm that resolves the computational concerns of conventional active contours and avoids computationally expensive optimizations was developed. A combination of external forces, adaptive node insertion, and multiresolution strategy was incorporated in the proposed algorithm. Boundary extraction with area and volume estimation in left ventricular echocardiographic images was implemented using the B-spline snake algorithm. The method was implemented in MATLAB and 50 medical images were used to evaluate the algorithm performance. Experimental validation was done using a database of echocardiographic images that had been manually evaluated by experts.

RESULTS

Comparison of methods demonstrates significant improvement over conventional algorithms using the adaptive B-spline technique. Moreover, our method reached a reasonable agreement with the results obtained manually by experts. The accuracy of boundary detection was calculated with Dice's coefficient equation (91.13%), and the average computational time was 1.24 s in a PC implementation.

CONCLUSION

In sum, the proposed method achieves satisfactory results with low computational complexity. This algorithm provides a robust and feasible technique for echocardiographic image segmentation. Suggestions for future improvements of the method are provided.

A coupled deformable model for tracking myocardial borders from real-time echocardiography using an incompressibility constraint

Real-time three-dimensional (RT3D) echocardiography is a new image acquisition technique that allows instantaneous acquisition of volumetric images for quantitative assessment of cardiac morphology and function. To quantify many important diagnostic parameters, such as ventricular volume, ejection fraction, and cardiac output, an automatic algorithm to delineate the left ventricle (LV) from RT3D echocardiographic images is essential. While a number of efforts have been made towards segmentation of the LV endocardial (ENDO) boundaries, the segmentation of epicardial (EPI) boundaries remains problematic. In this paper, we present a coupled deformable model that addresses this problem. The idea behind our method is that the volume of the myocardium is close to being constant during a cardiac cycle and our model uses this coupling as an important constraint. We employ two surfaces, each driven by the image-derived information that takes into account ultrasound physics by modeling the speckle statistics using the Nakagami distribution while maintaining the coupling. By simultaneously evolving two surfaces, the final segmentation of the myocardium is thus achieved. Results from 80 sets of synthetic data and 286 sets of real canine data were evaluated against the ground truth and against outlines from three independent observers, respectively. We show that results obtained with our incompressibility constraint were more accurate than those obtained without constraint or with a wall thickness constraint, and were comparable to those from manual segmentation.

Registering preprocedure volumetric images with intraprocedure 3-D ultrasound using an ultrasound imaging model

For many image-guided interventions there exists a need to compute the registration between preprocedure image(s) and the physical space of the intervention. Real-time intraprocedure imaging such as ultrasound (US) can be used to image the region of interest directly and provide valuable anatomical information for computing this registration. Unfortunately, real-time US images often have poor signal-to-noise ratio and suffer from imaging artefacts. Therefore, registration using US images can be challenging and significant preprocessing is often required to make the registrations robust. In this paper we present a novel technique for computing the image-to-physical registration for minimally invasive cardiac interventions using 3-D US. Our technique uses knowledge of the physics of the US imaging process to reduce the amount of preprocessing required on the 3-D US images. To account for the fact that clinical US images normally undergo significant image processing before being exported from the US machine our optimization scheme allows the parameters of the US imaging model to vary. We validated our technique by computing rigid registrations for 12 cardiac US/magnetic resonance imaging (MRI) datasets acquired from six volunteers and two patients. The technique had mean registration errors of 2.1-4.4 mm, and 75% capture ranges of 5-30 mm. We also demonstrate how the same approach can be used for respiratory motion correction: on 15 datasets acquired from five volunteers the registration errors due to respiratory motion were reduced by 45%-92%.

Automated border detection in three-dimensional echocardiography: principles and promises

Several automated border detection approaches for three-dimensional echocardiography have been developed in recent years, allowing quantification of a range of clinically important parameters. In this review, the background and principles of these approaches and the different classes of methods are described from a practical perspective, as well as the research trends to achieve a robust method.

Discrete deformable model guided by partial active shape model for TRUS image segmentation

Automatic prostate segmentation in transrectal ultrasound (TRUS) images is highly desired in many clinical applications. However, robust and automated prostate segmentation is challenging due to the low SNR in TRUS and the missing boundaries in shadow areas caused by calcifications or hyperdense prostate tissues. This paper presents a novel method of utilizing a priori shapes estimated from partial contours for segmenting the prostate. The proposed method is able to automatically extract prostate boundary from 2-D TRUS images without user interaction for shape correction in shadow areas. During the segmentation process, missing boundaries in shadow areas are estimated by using a partial active shape model, which takes partial contours as input but returns a complete shape estimation. With this shape guidance, an optimal search is performed by a discrete deformable model to minimize an energy functional for image segmentation, which is achieved efficiently by using dynamic programming. The segmentation of an image is executed in a multiresolution fashion from coarse to fine for robustness and computational efficiency. Promising segmentation results were demonstrated on 301 TRUS images grabbed from 19 patients with the average mean absolute distance error of 2.01 mm +/- 1.02 mm.

Automatic segmentation of calcifications in intravascular ultrasound images using snakes and the contourlet transform

It is valuable to detect calcifications in intravascular ultrasound images for studies of coronary artery diseases. An image segmentation method based on snakes and the Contourlet transform is proposed to automatically and accurately detect calcifications. With the Contourlet transform, an original image is decomposed into low-pass bands and band-pass directional sub-bands. The 2-D Renyi's entropy is used to adaptively threshold the low-pass bands in a multiresolution hierarchy to determine regions-of-interest (ROIs). Then a mean intensity ratio, reflecting acoustic shadowing, is presented to classify calcifications from noncalcifications and obtain initial contours of calcifications. The anisotropic diffusion is used in bandpass directional sub-bands to suppress noise and preserve calcific edges. Finally, the contour deformation in the boundary vector field is used to obtain final contours of calcifications. The method was evaluated via 60 simulated images and 86 in vivo images. It outperformed a recently proposed method, the Santos Filho method, by 2.76% and 14.53%, in terms of the sensitivity and specificity of calcification detection, respectively. The area under the receiver operating characteristic curve increased by 0.041. The relative mean distance error, relative difference degree, relative arc difference, relative thickness difference and relative length difference were reduced by 5.73%, 19.79%, 11.62%, 12.06% and 20.51%, respectively. These results reveal that the proposed method can automatically and accurately detect calcifications and delineate their boundaries. (E-mail: yywang@fudan.edu.cn).

Volume quantification by fuzzy logic modelling in freehand ultrasound imaging

INTRODUCTION

Many algorithms exist for 3D reconstruction of data from freehand 2D ultrasound slices. These methods are based on interpolation techniques to fill the voxels from the pixels. For quantification purposes, segmentation is involved to delineate the structure of interest. However, speckle and partial volume effect errors can affect quantification.

OBJECTIVE

This study aimed to assess the effect of the combination of a fuzzy model and 3D reconstruction algorithms of freehand ultrasound images on these errors.

METHODS

We introduced a fuzzification step to correct the initial segmentation, by weighting the pixels by a distribution function, taking into account the local gray levels, the orientation of the local gradient, and the local contrast-to-noise ratio. We then used two of the most wide-spread reconstruction algorithms (pixel nearest neighbour (PNN) and voxel nearest neighbour (VNN)) to interpolate and create the volume of the structure. Finally, defuzzification was used to estimate the optimal volume.

VALIDATION

B-scans were acquired using 5 MHz and 8 MHz ultrasound probes on ultrasound tissue-mimicking phantoms. Quantitative evaluation of the reconstructed structures was done by comparing the method output to the real volumes. Comparison was also done with classical PNN and VNN algorithms.

RESULTS

With the fuzzy model quantification errors were less than 4.3%, whereas with classical algorithms, errors were larger (10.3% using PNN, 17.2% using VNN). Furthermore, for very small structures (0.5 cm(3)), errors reached 24.3% using the classical VNN algorithm, while they were about 9.6% with the fuzzy VNN model.

CONCLUSION

These experiments prove that the fuzzy model allows volumes to be determined with better accuracy and reproducibility, especially for small structures (<3 cm(3)).

A multidimensional segmentation evaluation for medical image data

Evaluation of segmentation methods is a crucial aspect in image processing, especially in the medical imaging field, where small differences between segmented regions in the anatomy can be of paramount importance. Usually, segmentation evaluation is based on a measure that depends on the number of segmented voxels inside and outside of some reference regions that are called gold standards. Although some other measures have been also used, in this work we propose a set of new similarity measures, based on different features, such as the location and intensity values of the misclassified voxels, and the connectivity and the boundaries of the segmented data. Using the multidimensional information provided by these measures, we propose a new evaluation method whose results are visualized applying a Principal Component Analysis of the data, obtaining a simplified graphical method to compare different segmentation results. We have carried out an intensive study using several classic segmentation methods applied to a set of MRI simulated data of the brain with several noise and RF inhomogeneity levels, and also to real data, showing that the new measures proposed here and the results that we have obtained from the multidimensional evaluation, improve the robustness of the evaluation and provides better understanding about the difference between segmentation methods.

Detecting stripe artifacts in ultrasound images

Brain perfusion diseases such as acute ischemic stroke are detectable through computed tomography (CT)-/magnetic resonance imaging (MRI)-based methods. An alternative approach makes use of ultrasound imaging. In this low-cost bedside method, noise and artifacts degrade the imaging process. Especially stripe artifacts show a similar signal behavior compared to acute stroke or brain perfusion diseases. This document describes how stripe artifacts can be detected and eliminated in ultrasound images obtained through harmonic imaging (HI). On the basis of this new method, both proper identification of areas with critically reduced brain tissue perfusion and classification between brain perfusion defects and ultrasound stripe artifacts are made possible.

Automated segmentation of ultrasonic breast lesions using statistical texture classification and active contour based on probability distance

Because of its complicated structure, low signal/noise ratio, low contrast and blurry boundaries, fully automated segmentation of a breast ultrasound (BUS) image is a difficult task. In this paper, a novel segmentation method for BUS images without human intervention is proposed. Unlike most published approaches, the proposed method handles the segmentation problem by using a two-step strategy: ROI generation and ROI segmentation. First, a well-trained texture classifier categorizes the tissues into different classes, and the background knowledge rules are used for selecting the regions of interest (ROIs) from them. Second, a novel probability distance-based active contour model is applied for segmenting the ROIs and finding the accurate positions of the breast tumors. The active contour model combines both global statistical information and local edge information, using a level set approach. The proposed segmentation method was performed on 103 BUS images (48 benign and 55 malignant). To validate the performance, the results were compared with the corresponding tumor regions marked by an experienced radiologist. Three error metrics, true-positive ratio (TP), false-negative ratio (FN) and false-positive ratio (FP) were used for measuring the performance of the proposed method. The final results (TP = 91.31%, FN = 8.69% and FP = 7.26%) demonstrate that the proposed method can segment BUS images efficiently, quickly and automatically.

Online 3-D reconstruction of the right atrium from echocardiography data via a topographic cellular contour extraction algorithm

A computational method providing online, automated 3-D reconstruction of the right atrium of the human heart is presented in this paper. Endocardial boundaries were extracted from transesophageal ultrasound data by a topographic cellular contour extraction (TCCE) algorithm. The TCCE method was implemented on a continuous-time, analog, massively parallel processor, and on a digital serial processor. Processing speeds were 500 or 40 frames per second, depending on the hardware used. Extracted boundary point sets were rendered into a 3-D mesh and the volume of the cavity was quantified. Accuracy of volume quantification was validated on 60 in vitro static phantoms and 12 clinical subjects. For the clinical recordings, reference volumes were estimated from manually delineated endocardial boundaries. The average error of volume quantification by the TCCE method was 8% +/-5% ( n = 12), the average of the interobserver variability between two independent human experts was 5% +/-2% ( n = 6). Interactive planning of atrial septal defect closure in pediatric cardiology is presented as an example that demonstrates a potential clinical application of the method.

Segmentation of white matter flaring areas in ultrasound images of very-low-birth-weight preterm infants

In this article, we present an interactive algorithm segmenting white brain matter, visible as hyperechoic flaring areas in ultrasound (US) images of preterm infants with periventricular leukomalacia (PVL). The algorithm combines both the textural properties of pathological brain tissue and mathematical morphology operations. An initial flaring area estimate is derived from a multifeature multiclassifier tissue texture classifier. This area is refined based on the structural properties of the choroid plexus, a brain feature known to have characteristics similar to flaring. Subsequently, a combination of a morphological closing, gradient and opening by reconstruction operation determines the final flaring area boundaries. Experimental results are compared with a gold standard constructed from manual flaring area delineations of 12 medical experts. In addition, we compared our algorithm to an existing active contour method. The results show our technique agrees to the gold standard with statistical significance and outperforms the existing method in accuracy. Finally, using the flaring area as a criterion we improve the sensitivity of PVL detection up to 98% as compared with the state of the art.

Statistical region-based segmentation of ultrasound images

Segmentation of ultrasound images is a challenging problem due to speckle, which corrupts the image and can result in weak or missing image boundaries, poor signal to noise ratio and diminished contrast resolution. Speckle is a random interference pattern that is characterized by an asymmetric distribution as well as significant spatial correlation. These attributes of speckle are challenging to model in a segmentation approach, so many previous ultrasound segmentation methods simplify the problem by assuming that the speckle is white and/or Gaussian distributed. Unlike these methods, in this article we present an ultrasound-specific segmentation approach that addresses both the spatial correlation of the data as well as its intensity distribution. We first decorrelate the image and then apply a region-based active contour whose motion is derived from an appropriate parametric distribution for maximum likelihood image segmentation. We consider zero-mean complex Gaussian, Rayleigh, and Fisher-Tippett flows, which are designed to model fully formed speckle in the in-phase/quadrature (IQ), envelope detected, and display (log compressed) images, respectively. We present experimental results demonstrating the effectiveness of our method and compare the results with other parametric and nonparametric active contours.

Bone surface reconstruction using localized freehand ultrasound imaging

We propose a bone surface reconstruction method using localized ultrasound imagery. A set of bone contours is first extracted from a series of freehand 2D B-mode localized images, using an automatic segmentation method. This set is then used to reconstruct the bone surface with a tensor product B-splines approximation. Results of the partial surface reconstruction are shown for real bones and for a phantom physical model.

Automated detection of the carotid artery wall in B-mode ultrasound images using active contours initialized by the Hough Transform

Automatic segmentation of the arterial lumen from ultrasound images is an important and often challenging task in clinical diagnosis. We previously used the Hough Transform (HT) to automatically extract circles from sequences of B-mode ultrasound images of transverse sections of the carotid artery. In this paper, an active-contour-based methodology is suggested, initialized by the HT circle, in an attempt to extend previous findings and to accurately detect the arterial wall boundary. The methodology is based on the generation of a gradient vector flow field, an approach attempting to overcome conventional active contours constraints. Contour estimation is then achieved by deforming the initial curve (circle) based on the gradient vector flow field. In ten normal subjects, the specificity and accuracy of the segmentation were on average higher than 0.98, whereas the sensitivity was higher than 0.82. The methodology was also applied to four subjects with atherosclerosis, in which sensitivity, specificity and accuracy were comparable to those of normal subjects. In conclusion, the HT-initialized active contours methodology provides a reliable tool to detect the carotid artery wall in ultrasound images and can be used in clinical practice.

Semi-automated quantification of left ventricular volumes and ejection fraction by real-time three-dimensional echocardiography

BACKGROUND

Recent studies have shown that real-time three-dimensional (3D) echocardiography (RT3DE) gives more accurate and reproducible left ventricular (LV) volume and ejection fraction (EF) measurements than traditional two-dimensional methods. A new semi-automated tool (4DLVQ) for volume measurements in RT3DE has been developed. We sought to evaluate the accuracy and repeatability of this method compared to a 3D echo standard.

METHODS

LV end-diastolic volumes (EDV), end-systolic volumes (ESV), and EF measured using 4DLVQ were compared with a commercially available semi-automated analysis tool (TomTec 4D LV-Analysis ver. 2.2) in 35 patients. Repeated measurements were performed to investigate inter- and intra-observer variability.

RESULTS

Average analysis time of the new tool was 141s, significantly shorter than 261s using TomTec (p < 0.001). Bland Altman analysis revealed high agreement of measured EDV, ESV, and EF compared to TomTec (p = NS), with bias and 95% limits of agreement of 2.1 +/- 21 ml, -0.88 +/- 17 ml, and 1.6 +/- 11% for EDV, ESV, and EF respectively. Intra-observer variability of 4DLVQ vs. TomTec was 7.5 +/- 6.2 ml vs. 7.7 +/- 7.3 ml for EDV, 5.5 +/- 5.6 ml vs. 5.0 +/- 5.9 ml for ESV, and 3.0 +/- 2.7% vs. 2.1 +/- 2.0% for EF (p = NS). The inter-observer variability of 4DLVQ vs. TomTec was 9.0 +/- 5.9 ml vs. 17 +/- 6.3 ml for EDV (p < 0.05), 5.0 +/- 3.6 ml vs. 12 +/- 7.7 ml for ESV (p < 0.05), and 2.7 +/- 2.8% vs. 3.0 +/- 2.1% for EF (p = NS).

CONCLUSION

In conclusion, the new analysis tool gives rapid and reproducible measurements of LV volumes and EF, with good agreement compared to another RT3DE volume quantification tool.

Fully automated common carotid artery and internal jugular vein identification and tracking using B-mode ultrasound

We describe a fully automated ultrasound analysis system that tracks and identifies the common carotid artery (CCA) and the internal jugular vein (IJV). Our goal is to prevent inadvertent damage to the CCA when targeting the IJV for catheterization. The automated system starts by identifying and fitting ellipses to all the regions that look like major arteries or veins throughout each B-mode ultrasound image frame. The spokes ellipse algorithm described in this paper tracks these putative vessels and calculates their characteristics, which are then weighted and summed to identify the vessels. The optimum subset of characteristics and their weights were determined from a training set of 38 subjects, whose necks were scanned with a portable 10 MHz ultrasound system at 10 frames per second. Stepwise linear discriminant analysis (LDA) narrowed the characteristics to the five that best distinguish between the CCA and IJV. A paired version of Fisher's LDA was used to calculate the weights for each of the five parameters. Leave-one-out validation studies showed that the system could track and identify the CCA and IJV with 100% accuracy in this dataset.

Segmentation in ultrasonic B-mode images of healthy carotid arteries using mixtures of Nakagami distributions and stochastic optimization

The goal of this work is to perform a segmentation of the intimamedia thickness (IMT) of carotid arteries in view of computing various dynamical properties of that tissue, such as the elasticity distribution (elastogram). The echogenicity of a region of interest comprising the intima-media layers, the lumen, and the adventitia in an ultrasonic B-mode image is modeled by a mixture of three Nakagami distributions. In a first step, we compute the maximum a posteriori estimator of the proposed model, using the expectation maximization (EM) algorithm. We then compute the optimal segmentation based on the estimated distributions as well as a statistical prior for disease-free IMT using a variant of the exploration/selection (ES) algorithm. Convergence of the ES algorithm to the optimal solution is assured asymptotically and is independent of the initial solution. In particular, our method is well suited to a semi-automatic context that requires minimal manual initialization. Tests of the proposed method on 30 sequences of ultrasonic B-mode images of presumably disease-free control subjects are reported. They suggest that the semi-automatic segmentations obtained by the proposed method are within the variability of the manual segmentations of two experts.

Transcranial sonography in Parkinson’s disease

Transcranial sonography (TCS) is able to image in B-mode infratentorial and supratentorial structures, and can be used for the diagnosis and differential diagnosis of various intracranial pathologies. The authors review the contribution of TCS in the diagnosis and differential diagnosis of Parkinson’s disease (PD). TCS can be used to evaluate changes of echogenicity and in the area of substantia nigra in PD. Hyperechogenic enlarged substantia nigra can be detected in approximately 90% of PD patients and also in approximately 10% of the healthy population as a marker of subclinical injury of the nigrostriatal system. Hypoechogenic nucleus raphe could be detected in PD patients with unipolar depression and this finding also correlates with incontinency. Evaluations of echogenicity of the thalamus, nucleus lentiformis, nucleus caudatus, nucleus dentatus and the cerebellum, and measurement of enlargement of the ventricular system, could be used for differential diagnosis of movement disorders. TCS is a quick, safe and noninvasive method and can be used for early diagnosis of PD.

Speckle-initialized dynamic segmentation of the prostate

Echography is a commonly used modality for prostate imaging. Prostate segmentation is the first step in analyzing echographic prostate images. Because of the nature of these images, traditional local image processing operators are inadequate for finding the prostate boundary. Most automated segmentations described in literature require user interaction for contour initializing or editing. Also shape templates are applied as prior knowledge. In this paper, an automatic segmentation method is presented, based on prostate specific image granulation and image intensity. First, a granulation detector is used to extract granulation. Subsequently, the Hessian is adopted to evaluate granulation shape and intensity for the extraction of the prostate-specific dot pattern. This dot pattern is used to construct the contour initialization. A smooth contour model (discrete dynamic contour; DDC) is evolved from this initialization to the final contour. The guiding vector field for the DDC deformation is the gradient vector flow field calculated from an edge map of the original image. The scale of the relevant edges (large compared to granulation) is estimated from the prostate-specific dot pattern. Comparison of automated segmentations with clinical expert manual segmentations reveals a mean sensitivity and accuracy of 0.90 and 0.93, respectively.

Fast and automatic LV mass calculation from echocardiographic images via B-spline snake model and Markov random fields

Left ventricular (LV) mass has several important diagnostic and indicative implications. In this paper, a fast and accurate technique for detection of inner and outer boundaries of LV and, consequently, calculation of LV mass from apical 4-chamber echocardiographic images is presented. For detection of the inner boundary, a modified B-spline snake is proposed, which relies merely on image intensity and obviates the need for computationally-demanding image forces. The outer boundary is then obtained using a Markov random fields model in the neighborhood of the estimated inner border. Experimental validation of the proposed technique demonstrates remarkable improvement over conventional algorithms.

A Dynamical Shape Prior for LV Segmentation from RT3D Echocardiography

Real-time three-dimensional (RT3D) echocardiography is the newest generation of three-dimensional (3-D) echocardiography. Segmentation of RT3D echocardiographic images is essential for determining many important diagnostic parameters. In cardiac imaging, since the heart is a moving organ, prior knowledge regarding its shape and motion patterns becomes an important component for the segmentation task. However, most previous cardiac models are either static models (SM), which neglect the temporal coherence of a cardiac sequence or generic dynamical models (GDM), which neglect the inter-subject variability of cardiac motion. In this paper, we present a subject-specific dynamical model (SSDM) which simultaneously handles inter-subject variability and cardiac dynamics (intra-subject variability). It can progressively predict the shape and motion patterns of a new sequence at the current frame based on the shapes observed in the past frames. The incorporation of this SSDM into the segmentation process is formulated in a recursive Bayesian framework. This results in a segmentation of each frame based on the intensity information of the current frame, as well as on the prediction from the previous frames. Quantitative results on 15 RT3D echocardiographic sequences show that automatic segmentation with SSDM is superior to that of either SM or GDM, and is comparable to manual segmentation.

A new adaptive interpolation algorithm for 3D ultrasound imaging with speckle reduction and edge preservation

Conventional interpolation algorithms for reconstructing freehand three-dimensional (3D) ultrasound data always contain speckle noises and artifacts. This paper describes a new algorithm for reconstructing regular voxel arrays with reduced speckles and preserved edges. To study speckle statistics properties including mean and variance in sequential B-mode images in 3D space, experiments were conducted on an ultrasound resolution phantom and real human tissues. In the volume reconstruction, the homogeneity of the neighborhood for each voxel was evaluated according to the local variance/mean of neighboring pixels. If a voxel was locating in a homogeneous region, its neighboring pixels were averaged as the interpolation output. Otherwise, the size of the voxel neighborhood was contracted and the ratio was re-calculated. If its neighborhood was deemed as an inhomogeneous region, the voxel value was calculated using an adaptive Gaussian distance weighted method with respect to the local statistics. A novel method was proposed to reconstruct volume data set with economical usage of memory. Preliminary results obtained from the phantom and a subject's forearm demonstrated that the proposed algorithm was able to well suppress speckles and preserve edges in 3D images. We expect that this study can provide a useful imaging tool for clinical applications using 3D ultrasound.

Medical image noise reduction using the Sylvester-Lyapunov equation

Multiplicative noise is often present in medical and biological imaging, such as magnetic resonance imaging (MRI), Ultrasound, positron emission tomography (PET), single photon emission computed tomography (SPECT), and fluorescence microscopy. Noise reduction in medical images is a difficult task in which linear filtering algorithms usually fail. Bayesian algorithms have been used with success but they are time consuming and computationally demanding. In addition, the increasing importance of the 3-D and 4-D medical image analysis in medical diagnosis procedures increases the amount of data that must be efficiently processed. This paper presents a Bayesian denoising algorithm which copes with additive white Gaussian and multiplicative noise described by Poisson and Rayleigh distributions. The algorithm is based on the maximum a posteriori (MAP) criterion, and edge preserving priors which avoid the distortion of relevant anatomical details. The main contribution of the paper is the unification of a set of Bayesian denoising algorithms for additive and multiplicative noise using a well-known mathematical framework, the Sylvester-Lyapunov equation, developed in the context of the Control theory.

Optimally discriminant moments for speckle detection in real B-scan images

The paper presents and evaluates a speckle detection method for B-scan images. This is a fully automatic method and does not require information about the sensor parameters, which is often missing in retrospective studies. The characterization and posterior detection of speckle noise in ultrasound (US) has been regarded as an important research topic in US imaging, for improving signal-to-noise ratio by removing speckle noise and for exploiting speckle correlation information. Most of the existing methods require either manual intervention, the need to know sensor parameters or are based on statistical models which often do not generalize well to B-scans of different imaging areas. The proposed method aims to overcome those limitations. The main novelty of this work is to show that speckle detection can be improved based on finding optimally discriminant low order speckle statistics. In addition, and in contrast with other approaches the presented method is fully automatic and can be efficiently implemented to B-scan images. The method detects speckle patches using an ellipsoid discriminant function which classifies patches based on features extracted from optimally discriminant low order moments of the uncompressed intensity B-scan information. In addition, if the uncompressed signal is not available, we propose and evaluate a method for the estimation of this factor. The computation of low order moments using an optimality criteria, the decompression factor estimation and other key aspects of the method are quantitatively evaluated using both simulated and real (phantom and in vivo) data. Speckle detection results are obtained using again phantom and in vivo studies which show the validity of our approach. In addition, speckle probability images (SPI) are presented which provide valuable information about the distribution of speckle and non-speckle areas in an image. The presented evaluation and results show the effectiveness of our approach. In particular, the need for using discriminant analysis to determine the optimal discriminant power of the statistical moments and that this optimal value strongly depends on the characteristics and imaged tissues in the B-scan data.