Search

Visual inspection of histopathology images of stained biopsy tissue by expert pathologists is the standard method for grading of prostate cancer (PCa). However, this process is time-consuming and subject to high inter-observer variability. Machine learning-based methods have the potential to improve efficient throughput of large volumes of slides while decreasing variability, but they are not easy to develop because they require substantial amounts of labeled training data. In this paper, we propose a deep learning-based classification technique and data augmentation methods for accurate grading of PCa in histopathology images in the presence of limited data. Our method combines the predictions of three separate convolutional neural networks (CNNs) that work with different patch sizes. This enables our method to take advantage of the greater amount of contextual information in larger patches as well as greater quantity of smaller patches in the labeled training data. The predictions produced by the three CNNs are combined using a logistic regression model, which is trained separately after the CNN training. To effectively train our models, we propose new data augmentation methods and empirically study their effects on the classification accuracy. The proposed method achieves an accuracy of [Formula: see text] in classifying cancerous patches versus benign patches and an accuracy of [Formula: see text] in classifying low-grade (i.e., Gleason grade 3) from high-grade (i.e., Gleason grades 4 and 5) patches. The agreement level of our automatic grading method with expert pathologists is within the range of agreement between pathologists. Our experiments indicate that data augmentation is necessary for achieving expert-level performance with deep learning-based methods. A combination of image-space augmentation and feature-space augmentation leads to the best results. Our study shows that well-designed and properly trained deep learning models can achieve PCa Gleason grading accuracy that is comparable to an expert pathologist.

Importance: Proper evaluation of the performance of artificial intelligence techniques in the analysis of digitized medical images is paramount for the adoption of such techniques by the medical community and regulatory agencies., Objectives: To compare several cross-validation (CV) approaches to evaluate the performance of a classifier for automatic grading of prostate cancer in digitized histopathologic images and compare the performance of the classifier when trained using data from 1 expert and multiple experts., Design, Setting, and Participants: This quality improvement study used tissue microarray data (333 cores) from 231 patients who underwent radical prostatectomy at the Vancouver General Hospital between June 27, 1997, and June 7, 2011. Digitized images of tissue cores were annotated by 6 pathologists for 4 classes (benign and Gleason grades 3, 4, and 5) between December 12, 2016, and October 5, 2017. Patches of 192 µm2 were extracted from these images. There was no overlap between patches. A deep learning classifier based on convolutional neural networks was trained to predict a class label from among the 4 classes (benign and Gleason grades 3, 4, and 5) for each image patch. The classification performance was evaluated in leave-patches-out CV, leave-cores-out CV, and leave-patients-out 20-fold CV. The analysis was performed between November 15, 2018, and January 1, 2019., Main Outcomes and Measures: The classifier performance was evaluated by its accuracy, sensitivity, and specificity in detection of cancer (benign vs cancer) and in low-grade vs high-grade differentiation (Gleason grade 3 vs grades 4-5). The statistical significance analysis was performed using the McNemar test. The agreement level between pathologists and the classifier was quantified using a quadratic-weighted κ statistic., Results: On 333 tissue microarray cores from 231 participants with prostate cancer (mean [SD] age, 63.2 [6.3] years), 20-fold leave-patches-out CV resulted in mean (SD) accuracy of 97.8% (1.2%), sensitivity of 98.5% (1.0%), and specificity of 97.5% (1.2%) for classifying benign patches vs cancerous patches. By contrast, 20-fold leave-patients-out CV resulted in mean (SD) accuracy of 85.8% (4.3%), sensitivity of 86.3% (4.1%), and specificity of 85.5% (7.2%). Similarly, 20-fold leave-cores-out CV resulted in mean (SD) accuracy of 86.7% (3.7%), sensitivity of 87.2% (4.0%), and specificity of 87.7% (5.5%). Results of McNemar tests showed that the leave-patches-out CV accuracy, sensitivity, and specificity were significantly higher than those for both leave-patients-out CV and leave-cores-out CV. Similar results were observed for classifying low-grade cancer vs high-grade cancer. When trained on a single expert, the overall agreement in grading between pathologists and the classifier ranged from 0.38 to 0.58; when trained using the majority vote among all experts, it was 0.60., Conclusions and Relevance: Results of this study suggest that in prostate cancer classification from histopathologic images, patch-wise CV and single-expert training and evaluation may lead to a biased estimation of classifier's performance. To allow reproducibility and facilitate comparison between automatic classification methods, studies in the field should evaluate their performance using patient-based CV and multiexpert data. Some of these conclusions may be generalizable to other histopathologic applications and to other applications of machine learning in medicine.

We compare different possible scanning geometries for prostate photoacoustic tomography (PAT) while considering a realistic reconstruction scenario in which the limited view of the prostate and the directivity effect of the transducer are considered. Simulations and experiments confirm that an intra-operative configuration in which the photoacoustic signal is received by a pickup transducer from the anterior surface of the prostate provides the best approach. We propose a PAT acquisition system that includes a da Vinci system controlled by the da Vinci Research Kit, an illumination laser, and an ultrasound machine with parallel data acquisition. The robot maneuvers the pickup transducer to form a cylindrical detection surface around the prostate. The robot is programmed to acquire trajectories in which the transducer face is parallel to and oriented toward a rotational tomography axis, while the laser is fired and PAT data are collected at regular intervals. We present our initial images acquired with this novel system.

Temporal-enhanced ultrasound (TeUS) is a novel noninvasive imaging paradigm that captures information from a temporal sequence of backscattered US radio frequency data obtained from a fixed tissue location. This technology has been shown to be effective for classification of various in vivo and ex vivo tissue types including prostate cancer from benign tissue. Our previous studies have indicated two primary phenomena that influence TeUS: 1) changes in tissue temperature due to acoustic absorption and 2) micro vibrations of tissue due to physiological vibration. In this paper, first, a theoretical formulation for TeUS is presented. Next, a series of simulations are carried out to investigate micro vibration as a source of tissue characterizing information in TeUS. The simulations include finite element modeling of micro vibration in synthetic phantoms, followed by US image generation during TeUS imaging. The simulations are performed on two media, a sparse array of scatterers and a medium with pathology mimicking scatterers that match nuclei distribution extracted from a prostate digital pathology data set. Statistical analysis of the simulated TeUS data shows its ability to accurately classify tissue types. Our experiments suggest that TeUS can capture the microstructural differences, including scatterer density, in tissues as they react to micro vibrations.

Purpose: Ultrasound imaging provides a low-cost, real-time modality to guide needle insertion procedures, but localizing the needle using conventional ultrasound images is often challenging. Estimating the needle trajectory can increase the success rate of ultrasound-guided needle interventions and improve patient comfort. In this study, a novel method is introduced to localize the needle trajectory in curvilinear ultrasound images based on the needle reflection pattern of circular ultrasound waves., Methods: A circular ultrasound wave was synthesized by sequentially firing the elements of a curvilinear transducer and recording the radio-frequency signals received by each element. Two features, namely, the large amplitude and repetitive reflection pattern, were used to identify the needle echoes in the received signals. The trajectory of the needle was estimated by fitting the arrival times of needle echoes to an equation that describes needle reflection of circular waves. The method was employed to estimate the trajectories of needles inserted in agar phantom, beef muscle, and porcine tissue specimens., Results: The maximum error rates of estimating the needle trajectories were on the order of 1 mm and 3° for the radial and azimuth coordinates, respectively., Conclusions: These results suggest that the proposed method can improve the robustness and accuracy of needle segmentation methods by adding signature-based detection of the needle trajectory in curvilinear ultrasound images. The method can be implemented on conventional ultrasound imaging systems.

Purpose: In conventional three-dimensional magnetic resonance elastography, motion encoding gradients (MEGs) synchronized to a mechanical excitation are applied separately in each direction to encode tissue displacement generated by the corresponding waves. This requires long acquisition times that introduce errors due to patient motion and may hinder clinical deployment of magnetic resonance elastography. In this article, a framework for MEGs sequence design is proposed to reduce scanning time and increase signal-to-noise ratio., Theory and Methods: The approach is based on applying MEGs in all three directions simultaneously with varying parameters, and formulation of the problem as a linear estimation of the wave properties. Multidirectional MEGs sequences are derived by setting the problem in an experimental design framework. Such designs are implemented and evaluated on simulation and phantom data., Results: Estimation error of the displacement using the proposed MEGs designs is reduced up to a factor of two in comparison with a unidirectional design with a same number of acquisitions. Alternatively, for the same error, scanning time is reduced up to a factor of three using the multidirectional designs., Conclusion: The proposed framework generalizes acquisition of magnetic resonance elastography, and allows quantification of design performance, and optimization-based derivation of designs., (© 2014 Wiley Periodicals, Inc.)

This work reports the use of ultrasound radio frequency (RF) time series analysis as a method for ultrasound-based classification of malignant breast lesions. The RF time series method is versatile and requires only a few seconds of raw ultrasound data with no need for additional instrumentation. Using the RF time series features, and a machine learning framework, we have generated malignancy maps, from the estimated cancer likelihood, for decision support in biopsy recommendation. These maps depict the likelihood of malignancy for regions of size 1 mm(2) within the suspicious lesions. We report an area under receiver operating characteristics curve of 0.86 (95% confidence interval [CI]: 0.84%-0.90%) using support vector machines and 0.81 (95% CI: 0.78-0.85) using Random Forests classification algorithms, on 22 subjects with leave-one-subject-out cross-validation. Changing the classification method yielded consistent results which indicates the robustness of this tissue typing method. The findings of this report suggest that ultrasound RF time series, along with the developed machine learning framework, can help in differentiating malignant from benign breast lesions, subsequently reducing the number of unnecessary biopsies after mammography screening.

This article presents a new approach to magnetic resonance elastography of the prostate using transperineal mechanical excitation. This approach is validated using a prostate elasticity phantom and in vivo studies of healthy volunteers. It is demonstrated that the transperineal approach can generate shear wave amplitudes on the order of 6-30 μm in the mid-gland region. The driver was implemented using an electromagnetic actuator with a hydraulic transmission system. The magnetic resonance elastography acquisition time has been reduced significantly by using a "second harmonic" approach. Displacement fields are processed using the established three-dimensional local frequency estimation algorithm. The three-dimensional curl-based direct inversion was used to calculate the local wavelength. The traveling wave expansion algorithm was used to reconstruct the wave damping image for one case. Using the proposed method, it was possible to resolve lesions of 0.5 cc in the phantom study. Repeatability experiments were performed and analyzed. The results from this study indicate that transperineal magnetic resonance elastography--without an endorectal coil--is a suitable candidate for a patient study involving multiparametric magnetic resonance imaging of prostate cancer, where magnetic resonance elastography may provide additional information for improved diagnosis and image-based surveillance., (Copyright © 2012 Wiley Periodicals, Inc.)

The finite element method is commonly used to model tissue deformation in order to solve for unknown parameters in the inverse problem of viscoelasticity. Typically, a (regular-grid) structured mesh is used since the internal geometry of the domain to be identified is not known a priori. In this work, the generation of problem-specific meshes is studied and such meshes are shown to significantly improve inverse-problem elastic parameter reconstruction. Improved meshes are generated from axial strain images, which provide an approximation to the underlying structure, using an optimization-based mesh adaptation approach. Such strain-based adapted meshes fit the underlying geometry even at coarse mesh resolutions, therefore improving the effective resolution of the reconstruction at a given mesh size/complexity. Elasticity reconstructions are then performed iteratively using the reflective trust-region method for optimizing the fit between estimated and observed displacements. This approach is studied for Young's modulus reconstruction at various mesh resolutions through simulations, yielding 40%-72% decrease in root-mean-square reconstruction error and 4-52 times improvement in contrast-to-noise ratio in simulations of a numerical phantom with a circular inclusion. A noise study indicates that conventional structured meshes with no noise perform considerably worse than the proposed adapted meshes with noise levels up to 20% of the compression amplitude. A phantom study and preliminary in vivo results from a breast tumor case confirm the benefit of the proposed technique. Not only conventional axial strain images but also other elasticity approximations can be used to adapt meshes. This is demonstrated on images generated by combining axial strain and axial-shear strain, which enhances lateral image contrast in particular settings, consequently further improving mesh-adapted reconstructions.

Delineation of the prostate from transrectal ultrasound images is a necessary step in several computer-assisted clinical interventions, such as low dose rate brachytherapy. Current approaches to user segmentation require user intervention and therefore it is subject to user errors. It is desirable to have a fully automatic segmentation for improved segmentation consistency and speed. In this paper, we propose a multi-atlas fusion framework to automatically segment prostate transrectal ultrasound images. The framework initially registers a dataset of a priori segmented ultrasound images to a target image. Subsequently, it uses the pairwise similarity of registered prostate shapes, which is independent of the image-similarity metric optimized during the registration process, to prune the dataset prior to the fusion and consensus segmentation step. A leave-one-out cross-validation of the proposed framework on a dataset of 50 transrectal ultrasound volumes obtained from patients undergoing brachytherapy treatment shows that the proposed is clinically robust, accurate and reproducible.

Purpose: To develop an image-based technique capable of detection and grading of prostate cancer, which combines features extracted from multiparametric MRI into a single parameter map of cancer probability., Materials and Methods: A combination of features extracted from diffusion tensor MRI and dynamic contrast enhanced MRI was used to characterize biopsy samples from 29 patients. Support vector machines were used to separate the cancerous samples from normal biopsy samples and to compute a measure of cancer probability, presented in the form of a cancer colormap. The classification results were compared with the biopsy results and the classifier was tuned to provide the largest area under the receiver operating characteristic (ROC) curve. Based solely on the tuning of the classifier on the biopsy data, cancer colormaps were also created for whole-mount histopathology slices from four radical prostatectomy patients., Results: An area under ROC curve of 0.96 was obtained on the biopsy dataset and was validated by a "leave-one-patient-out" procedure. The proposed measure of cancer probability shows a positive correlation with Gleason score. The cancer colormaps created for the histopathology patients do display the dominant tumors. The colormap accuracy increases with measured tumor area and Gleason score., Conclusion: Dynamic contrast enhanced imaging and diffusion tensor imaging, when used within the framework of supervised classification, can play a role in characterizing prostate cancer., (Copyright © 2012 Wiley Periodicals, Inc.)

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., (Copyright © 2010 Elsevier B.V. All rights reserved.)

In medical simulations involving tissue deformation, the finite element method (FEM) is a widely used technique, where the size, shape, and placement of the elements in a model are important factors that affect the interpolation and numerical errors of a solution. Conventional model generation schemes for FEM consist of a segmentation step delineating the anatomy followed by a meshing step generating elements conforming to this segmentation. In this paper, a single-step model generation technique is proposed based on optimization. Starting from an initial mesh covering the domain of interest, the mesh nodes are adjusted to minimize an objective function which penalizes intra-element intensity variations and poor element geometry for the entire mesh. Trade-offs between mesh geometry quality and intra-element variance are achieved by adjusting the relative weights of the geometric and intensity variation components of the cost function. This meshing approach enables a more accurate rendering of shapes with fewer elements and provides more accurate models for deformation simulation, especially when the image intensities represent a mechanical feature of the tissue such as the elastic modulus. The use of the proposed mesh optimization is demonstrated in 2-D and 3-D on synthetic phantoms, MR images of the brain, and CT images of the kidney. A comparison with previous meshing techniques that do not account for image intensity is also provided demonstrating the benefits of our approach.

A novel registration method between 3D ultrasound and stereoscopic cameras is proposed based on tracking a registration tool featuring both ultrasound fiducials and optical markers. The registration tool is pressed against an air-tissue boundary where it can be seen both in ultrasound and in the camera view. By localizing the fiducials in the ultrasound volume, knowing the registration tool geometry, and tracking the tool with the cameras, a registration is found. This method eliminates the need for external tracking, requires minimal setup, and may be suitable for a range of minimally invasive surgeries. A study of the appearance of ultrasound fiducials on an air-tissue boundary is presented, and an initial assessment of the ability to localize the fiducials in ultrasound with sub-millimeter accuracy is provided. The overall accuracy of registration (1.69 +/- 0.60 mm) is a noticeable improvement over other reported methods and warrants patient studies.

In this paper we propose a fully automatic 2D prostate segmentation algorithm using fused ultrasound (US) and elastography images. We show that the addition of information from mechanical tissue properties acquired from elastography to acoustic information from B-mode ultrasound, can improve segmentation results. Gray level edge similarity and edge continuity in both US and elastography images deform an Active Shape Model. Comparison of automatic and manual contours on 107 transverse images of the prostate show a mean absolute error of 2.6 +/- 0.9 mm and a running time of 17.9 +/- 12.2 s. These results show that the combination of the high contrast elastography images with the more detailed but low contrast US images can lead to very promising results for developing an automatic 3D segmentation algorithm.

In this paper, we propose an interpolation-based method for simulating needle images in B-mode ultrasound. We parametrize the needle image as a function of needle position and orientation. We collect needle images under various spatial configurations in a water-tank using a guidance robot. Then we use multi-dimensional tensor-product interpolation to simulate images of needles with arbitrary poses and positions using the collected images. Interpolated needle images are superimposed on top of phantom image backgrounds. The similarity between the simulated and the real images is measured using a correlation metric. A comparison with in-vivo images is also performed. The simulation procedure is demonstrated using transverse needle images and extended to sagittal needle images and brachytherapy seed images. The proposed method could be used in clinical procedure training simulators.

In this paper, the effect of the boundary conditions and excitation dimensions on the speed of longitudinal waves in a medium is investigated. It is shown that with appropriate boundary conditions, a low-speed longitudinal wave can be generated in the medium which can be tracked by standard pulse-echo ultrasound motion tracking techniques. Three different cases of boundary conditions are explored in which the longitudinal wave speed in an incompressible material can be as high as the acoustic wave speed or as low as the shear wave speed. It is shown that the displacement spectrum can be used to estimate the wave speed in a viscoelastic medium. Numerical simulations with 3D viscoelastic finite element models and experiments on tissue-mimicking phantoms are performed to validate the theory.

In finite element simulation, size, shape, and placement of the elements in a model are significant factors that affect the interpolation and numerical errors of a solution. In medical simulations, such models are desired to have higher accuracy near features such as anatomical boundaries (surfaces) and they are often required to have element faces lying along these surfaces. Conventional modelling schemes consist of a segmentation step delineating the anatomy followed by a meshing step generating elements conforming to this segmentation. In this paper, a one-step energy-based model generation technique is proposed. An objective function is minimized when each element of a mesh covers similar image intensities while, at the same time, having desirable FEM characteristics. Such a mesh becomes essential for accurate models for deformation simulation, especially when the image intensities represent a mechanical feature of the tissue such as the elastic modulus. The use of the proposed mesh optimization is demonstrated on synthetic phantoms, 2D/3D brain MR images, and prostate ultrasound-elastography data.

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.

We show that vibro-elastography, an ultrasound-based method that creates images of tissue viscoelasticity contrast, can be used for visualization and segmentation of the prostate. We use MRI as the gold standard and show that VE images yield more accurate 3D volumes of the prostate gland than conventional B-mode imaging. Furthermore, we propose two novel measures characterizing the strength and continuity of edges in noisy images. These measures, as well as contrast to noise ratio, demonstrate the utility of VE as a prostate imaging modality. The results of our study show that in addition to mapping the visco-elastic properties of tissue, VE can play a central role in improving the anatomic visualization of the prostate region and become an integral component of interventional procedures such as brachytherapy.

Motion estimation in sequences of ultrasound echo signals is essential for a wide range of modern ultrasound-based signal processing applications. Pattern matching algorithms are generally used for finding the motion within sampling accuracy. Subsequently, 1D interpolation techniques are employed to find any motion smaller than sampling accuracy. In this paper, we propose several interpolation schemes that are suited for 2D motion estimation. Simulations using Field II ultrasound simulation software and experiments using an Ultrasonix Sonix RP imaging system with a L9-4/38 linear array transducer are used to study these techniques and compare their performance to other methods reported in the literature. The results show that the proposed interpolation methods outperform other common techniques in terms of bias and jitter. The axial and the lateral bias of the proposed methods are measured to be less than 1 microm and 5 microm, respectively, in both the simulated and the experimental data.

Needle insertion simulators are in demand to train physicians for surgical procedures such as prostate brachytherapy. In order to design a needle insertion simulator, a needle-tissue interaction model is necessary. Such a model can be identified using force and displacement data measured during the insertion of the needle. In this paper, an experiment is conducted in which a needle is inserted into a two-layered PVC phantom, while the needle position and insertion forces are measured and the tissue is imaged using a trans-rectal probe in the sagittal plane. A 2D block matching algorithm is used to estimate tissue deformation from the envelope of the recorded radio-frequency signals. This algorithm can be used to estimate the rotation and displacement of the prostate during prostate brachytherapy. The block matching method was validated in an independent experiment. With the measured force, needle position and tissue displacements, a finite element simulation was conducted to identify the parameters of a needle-tissue force distribution model and Young's moduli of each part of the tissue phantom.

This paper presents a 3D semi-automatic prostate segmentation method for B-mode trans-rectal ultrasound (TRUS) images. Segmentation is based on prior knowledge of the prostate transversal section shape which is assumed to be a tapered ellipse. The approach consists of an initial untapering and warping of the image to make the shape of the prostate approximately elliptical. The prostate contour is found in the untapered, warped images by edge detection and 2D/3D ellipsoidal curve fitting, performed by solving convex optimization problem. This leads to an average total segmentation duration of 7.42s which is more than 40 times faster than manual segmentation. Clinical studies carried out on 58 prostate volume studies show a volume sensitivity and accuracy of approximately 94% and 73% respectively.

The performances of various signal-processing applications in ultrasound medical imaging, including elastography, blood flow imaging, tissue velocity imaging, and acoustic radiation force impulse imaging, depend on their time-delay estimators. In this paper, we introduced a new class of time-delay estimator based on the tracking of individual samples using a continuous representation of the echo signal. Simulation results show that the sample tracking algorithms significantly outperformed the conventional window-based algorithms in terms of bias and jitter when individual estimates from the samples are averaged over the same window length. Simulations further showed similar performance to that of recently introduced spline-based continuous time-delay estimators only if all the samples in the window had identical delays. When the samples inside a window experienced different delays, sample tracking algorithms considerably outperformed the continuous delay estimators. In addition, the sample tracking algorithms showed to have much higher resolution and sensitivity when compared to all the other window-based techniques, including the continuous delay estimators.

A method for vessel segmentation and tracking in ultrasound images using Kalman filters is presented. A modified Star-Kalman algorithm is used to determine vessel contours and ellipse parameters using an extended Kalman filter with an elliptical model. The parameters can be used to easily calculate the transverse vessel area which is of clinical use. A temporal Kalman filter is used for tracking the vessel center over several frames, using location measurements from a handheld sensorized ultrasound probe. The segmentation and tracking have been implemented in real-time and validated using simulated ultrasound data with known features and real data, for which expert segmentation was performed. Results indicate that mean errors between segmented contours and expert tracings are on the order of 1%-2% of the maximum feature dimension, and that the transverse cross-sectional vessel area as computed from estimated ellipse parameters a, b as determined by our algorithm is within 10% of that determined by experts. The location of the vessel center was tracked accurately for a range of speeds from 1.4 to 11.2 mm/s.

A new method is proposed to estimate the motion and relative local compression between two successive ultrasound RF signals under different compression states. The algorithm uses the continuous wavelet transform to locate the peaks in the RF signals. The estimated peaks in the pre- and post-compression signals are assigned to each other by a peak matching technique with the goal of minimizing the number of false matches. The method allows local shifts of the tissue to be estimated. The method has been tested in one-dimensional simulations and phantom experiments. The signal-to-noise ratio and the rms error are shown to be better than for the standard cross-correlation method (CC). The new estimator remains unbiased for up to 10% strain which is a larger range than that of CC. The maximum signal-to-noise ratio is 3 times as high as that of the CC method, showing higher sensitivity as well. The method is computationally efficient, achieving 0.7 msec/RF line on a standard personal computer.

This paper presents a fast image synthesis procedure for elastic volumes under deformation. Given the node displacements of a mesh and the 3D image voxel data of an undeformed volume, the method maps the image plane pixels to be synthesized from the deformed configuration back to the nominal pre-deformed configuration, where the pixel intensities are obtained easily through interpolation in the regular-grid structure of the voxel volume. For smooth interpolation, this mapping requires the identification of the mesh element enclosing each image pixel. To accelerate this point location procedure, a fast method of marking the image pixels is employed by finding the intersection of the mesh and the image, and marking this intersection on the image pixels using Bresenham's line drawing algorithm. A deformable tissue phantom was constructed, it was modeled using the finite element method, and its 3D ultrasound volume was acquired in its undeformed state. Actual B-mode images of the phantom under deformation by the ultrasound probe were then compared with the corresponding synthesized images simulated for the same deformations. Results show that realistic images can be synthesized in real-time using the proposed technique.

In this paper we introduce a new speckle tracking method that is based on the standard time-domain cross correlation strain estimation (TDE). We call this method time-domain cross-correlation with prior estimates (TDPE), because it uses prior displacement estimates of neighboring windows to speed up computation. TDPE has all the advantages of TDE, but is much faster. Simulations, as well as experiments with phantoms and tissue, indicate that TDPE is capable of reliably estimating tissue displacement and strain over a large range of displacements in real time. The computational efficiency of TDPE is compared with current time-efficient methods that have been used in real time strain imaging systems. The results show that TDPE is the most time efficient algorithm to date, and is roughly 10 times faster than the TDE. The implementation of TDPE on an Ultrasonix RP500 ultrasound machine runs at 30 fps for strain images of 16000 pixels.

Ultrasound-guided percutaneous needle insertions are widely used techniques in current clinical practice. Some of these procedures have a high degree of difficulty because of poor observability of the needle in the ultrasound image. There have been recent efforts to improve guidance by computer assisted needle detection. These software techniques are often limited by not representing needle curvature. We present two methods to detect the needle in 2D ultrasound that specifically address needle curvature. Firstly, we demonstrate a real-time needle segmentation algorithm based on the Hough transform which detects the needle and represents its curved shape. Secondly, we demonstrate how a new coordinate transformation can transform detection of a curved needle to a linear fit. These methods are demonstrated on ultrasound and photographic images.

A system for objective vessel compression assessment for deep venous thrombosis characterization using ultrasound image data and a sensorized ultrasound probe is presented. Two new objective measures calculated from applied force and transverse vessel area are also presented and used to describe vessel compressibility. A modified star-Kalman algorithm is used for feature detection in acquired ultrasound images, and objective measures of vessel compressibility are calculated from the detected features and acquired force and location data from the sensorized probe. A three-dimensional shape model of the examined vessel that includes compressibility measures mapped as colors to its surface is presented on the user interface, as well as a virtual representation of the image plane. The compressibility measures were validated using expert segmentation of healthy and diseased vessels and compared using paired t-tests, which showed a significant difference between healthy and diseased cases for both measures. 100% sensitivity and specificity were obtained for both measures. The system was implemented in real-time (16 Hz) and evaluated using a tissue phantom and on healthy human subjects. Sensitivity was 100% and 60%, while specificity was 97% for both measures when implemented. The initial results for the system and its components are promising.

This paper presents a new algorithm for the semi-automatic segmentation of the prostate from B-mode trans-rectal ultrasound (TRUS) images. The segmentation algorithm first uses image warping to make the prostate shape elliptical. Measurement points along the prostate boundary, obtained from an edge-detector, are then used to find the best elliptical fit to the warped prostate. The final segmentation result is obtained by applying a reverse warping algorithm to the elliptical fit. This algorithm was validated using manual segmentation by an expert observer on 17 midgland, pre-operative, TRUS images. Distance-based metrics between the manual and semi-automatic contours showed a mean absolute difference of 0.67 +/- 0.18 mm, which is significantly lower than inter-observer variability. Area-based metrics showed an average sensitivity greater than 97% and average accuracy greater than 93%. The proposed algorithm was almost two times faster than manual segmentation and has potential for real-time applications.