3-D Ultrafast Shear Wave Absolute Vibro-Elastography Using a Matrix Array Transducer.

Real-time ultrasound imaging plays an important role in ultrasound-guided interventions. The 3-D imaging provides more spatial information compared to conventional 2-D frames by considering the volumes of data. One of the main bottlenecks of 3-D imaging is the long data acquisition time, which reduces practicality and can introduce artifacts from unwanted patient or sonographer motion. This article introduces the first shear wave absolute vibro-elastography (S-WAVE) method with real-time volumetric acquisition using a matrix array transducer. In S-WAVE, an external vibration source generates mechanical vibrations inside the tissue. The tissue motion is then estimated and used in solving a wave equation inverse problem to provide the tissue elasticity. A matrix array transducer is used with a Verasonics ultrasound machine and a frame rate of 2000 volumes/s to acquire 100 radio frequency (RF) volumes in 0.05 s. Using plane wave (PW) and compounded diverging wave (CDW) imaging methods, we estimate axial, lateral, and elevational displacements over 3-D volumes. The curl of the displacements is used with local frequency estimation to estimate elasticity in the acquired volumes. Ultrafast acquisition extends substantially the possible S-WAVE excitation frequency range, now up to 800 Hz, enabling new tissue modeling and characterization. The method was validated on three homogeneous liver fibrosis phantoms and on four different inclusions within a heterogeneous phantom. The homogeneous phantom results show less than 8% (PW) and 5% (CDW) difference between the manufacturer values and the corresponding estimated values over a frequency range of 80-800 Hz. The estimated elasticity values for the heterogeneous phantom at 400-Hz excitation frequency show the average errors of 9% (PW) and 6% (CDW) compared to the provided average values by magnetic resonance elastography (MRE). Furthermore, both imaging methods were able to detect the inclusions within the elasticity volumes. An ex vivo study on a bovine liver sample shows less than 11% (PW) and 9% (CDW) difference between the estimated elasticity ranges by the proposed method and the elasticity ranges provided by MRE and acoustic radiation force impulse (ARFI).

Utility of prepuncture ultrasound for localization of the thoracic epidural space.

BACKGROUND: Ultrasound has been shown to facilitate accurate identification of the intervertebral level and to predict skin-to-epidural depth in the lumbar epidural space with reliable precision. We hypothesized that we could accurately predict the skin-to-epidural depth and the intervertebral level in the thoracic spine with the use of ultrasound. METHODS: Twenty patients presenting for thoracic surgery were included in a feasibility study. The skin-to-epidural depth was measured using prepuncture ultrasound in the paramedian window, and the predicted depth was compared with the actual needle depth and the depth as measured by computed tomography. In addition, the intervertebral levels were identified by ultrasound using the "counting up" method, and the results were compared with the levels identified by anesthesiologists. RESULTS: The ultrasound-based depth measurements displayed a bias of 3.21 mm with 95% limits of agreement from -7.47 to 13.9 mm compared with the clinically determined needle depth. The intervertebral levels identified by the anesthesiologists and the sonographer matched in only 40% of cases. CONCLUSION: Ultrasound-based measurements of skin-to-epidural depth show acceptable agreement with the actual depth observed during epidural catheterization; however, the limits of agreement are wide, which restricts the predictive value of ultrasound-based measurements. Further study is required to delineate the role of ultrasound in thoracic epidural catheterizations.

Single-operator real-time ultrasound-guidance to aim and insert a lumbar epidural needle.

PURPOSE: In conventional practice of epidural needle placement, determining the interspinous level and choosing the puncture site are based on palpation of anatomical landmarks, which can be difficult with some subjects. Thereafter, the correct passage of the needle towards the epidural space is a blind "feel as you go" method. An aim-and-insert single-operator ultrasound-guided epidural needle placement is described and demonstrated. METHOD: Nineteen subjects undergoing elective Cesarean delivery consented to undergo both a pre-puncture ultrasound scan and real-time paramedian ultrasound-guidance for needle insertion. Following were the study objectives: to measure the success of a combined spinal-epidural needle insertion under real-time guidance, to compare the locations of the chosen interspinous levels as determined by both ultrasound and palpation, to measure the change in depth of the epidural space from the skin surface as pressure is applied to the ultrasound transducer, and to investigate the geometric limitations of using a fixed needle guide. RESULTS: One subject did not participate in the study because pre-puncture ultrasound examination showed unrecognizable bony landmarks. In 18 of 19 subjects, the epidural needle entered the epidural space successfully, as defined by a loss-of-resistance. In two subjects, entry into the epidural space was not achieved despite ultrasound guidance.Eighteen of the 19 interspinous spaces that were identified using palpation were consistent with those determined by ultrasound. The transducer pressure changed the depth of the epidural space by 2.8 mm. The measurements of the insertion lengths corresponded with the geometrical model of the needle guide, but the needle required a larger insertion angle than would be needed without the guide. CONCLUSION: This small study demonstrates the feasibility of the ultrasound-guidance technique. Areas for further development are identified for both ultrasound software and physical design.

Hand-eye coordination-based implicit re-calibration method for gaze tracking on ultrasound machines: a statistical approach.

PURPOSE: Eye gaze tracking is proving to be beneficial in many biomedical applications. The performance of systems based on eye gaze tracking is very much dependent on how accurate their calibration is. It has been reported that the gaze tracking accuracy deteriorates cumulatively and significantly with usage time. This impedes the wide use of gaze tracking in user interfaces. METHODS: Explicit re-calibration, typically requiring the user's active attention, is time-consuming and can interfere with the user's main activity. Therefore, we propose an implicit re-calibration method, which can rectify the deterioration of the gaze tracking accuracy without bringing about the user's deliberate attention. We make use of hand-eye coordination, with the reasonable assumption that the eye gaze follows the pointer during a selection task, to acquire additional calibration points during normal usage of a gaze-contingent system. We construct a statistical model for the calibration and the hand-eye coordination and apply the Gaussian process regression framework to perform the re-calibration. RESULTS: To validate our model and method, we performed a user study on ultrasonography tasks on a gaze-contingent interface for ultrasound machines. Results suggest that our method can rectify the tracking accuracy deterioration for [Formula: see text] of all cases where deterioration occurs in our user study. With another benchmark dataset, our method can redress tracking accuracy to a level comparable to the initial calibration in more than [Formula: see text] of the cases. CONCLUSIONS: Our implicit re-calibration method is a practical and convenient fix for tracking accuracy deterioration in gaze-contingent user interfaces, and in particular for gaze-contingent ultrasound machines.

Preinsertion paramedian ultrasound guidance for epidural anesthesia.

BACKGROUND: Ultrasound is receiving growing interest for improving the guidance of needle insertion in epidural anesthesia. Defining a paramedian ultrasound scanning technique would be helpful for correctly identifying the vertebral level. Finding surrogate measures of the depth of the epidural space may also improve the ease of scanning. METHODS: We examined 20 parturients with pre-epidural ultrasound in the paramedian plane, and the predicted depth was compared with the actual midline depth. The actual depth was also compared with subject biometrics, depth of transverse process, and thickness of lumbar fat. RESULTS: The scanning technique allowed the depth of the epidural space to be measured in all subjects. The depth measured in ultrasound was strongly correlated to the actual depth (R(2) = 0.8 and 95% limits of agreement of -14.8 to 5.2 mm), unlike patient biometrics (R(2) < 0.25), the depth of the neighboring transverse processes (R(2) = 0.35 and 95% limits of agreement of -13.8 to 19.1 mm), or the thickness of overlying fat (R(2) = 0.66). The duration of the ultrasound scan was 10 min at the beginning of the trial and 3 min for the last subjects. CONCLUSIONS: Paramedian ultrasound can be used to estimate the midline depth to the epidural space. The surrogate measures are not sufficiently correlated with the depth to the epidural space to recommend them as a replacement for the actual depth to the epidural space measurement.

Adaptive Augmentation of Medical Data Using Independently Conditional Variational Auto-Encoders.

Current deep supervised learning methods typically require large amounts of labeled data for training. Since there is a significant cost associated with clinical data acquisition and labeling, medical datasets used for training these models are relatively small in size. In this paper, we aim to alleviate this limitation by proposing a variational generative model along with an effective data augmentation approach that utilizes the generative model to synthesize data. In our approach, the model learns the probability distribution of image data conditioned on a latent variable and the corresponding labels. The trained model can then be used to synthesize new images for data augmentation. We demonstrate the effectiveness of the approach on two independent clinical datasets consisting of ultrasound images of the spine and magnetic resonance images of the brain. For the spine dataset, a baseline and a residual model achieve an accuracy of 85% and 92%, respectively, using our method compared to 78% and 83% using a conventional training approach for image classification task. For the brain dataset, a baseline and a U-net network achieve an accuracy of 84% and 88%, respectively, in Dice coefficient in tumor segmentation compared to 80% and 83% for the convention training approach.

A novel gaze-supported multimodal human-computer interaction for ultrasound machines.

PURPOSE: Conventional ultrasound (US) machines employ a physical control panel (PCP) as the primary user interface for machine control. This panel is adjacent to the main machine display that requires the operator's constant attention. The switch of attention to the control panel can lead to interruptions in the flow of the medical examination. Some ultraportable machines also lack many physical controls. Furthermore, the need to both control the US machine and observe the US image may lead the practitioners to adopt unergonomic postures and repetitive motions that can lead to work-related injuries. Therefore, there is a need for a more efficient human-computer interaction method on US machines. METHODS: To tackle some of the limitations with the PCP, we propose to merge the PCP into the main screen of the US machines. We propose to use gaze tracking and a handheld controller so that machine control can be achieved via a multimodal human-computer interaction (HCI) method that does not require one to touch the screen or look away from the US image. As a first step, a pop-up menu and measurement tool were designed on top of the US image based on gaze position for efficient machine control. RESULTS: A comparative study was performed on the BK Medical SonixTOUCH US machine. Participants were asked to complete the task of measuring the area of an ellipse-shaped tumor in a phantom using our gaze-supported HCI method as well as the traditional method. The user study indicates that the task completion time can be reduced by [Formula: see text] when using our gaze-supported HCI, while no extra workload is imposed on the operators. CONCLUSIONS: Our preliminary study suggests that, when combined with a simple handheld controller, eye gaze tracking can be integrated into the US machine HCI for more efficient machine control.

Acoustic Shadow Detection: Study and Statistics of B-Mode and Radiofrequency Data.

An acoustic shadow is an ultrasound artifact occurring at boundaries between significantly different tissue impedances, resulting in signal loss and a dark appearance. Shadow detection is important as shadows can identify anatomical features or obscure regions of interest. A study was performed to scan human participants (N = 37) specifically to explore the statistical characteristics of various shadows from different anatomy and with different transducers. Differences in shadow statistics were observed and used for shadow detection algorithms with a fitted Nakagami distribution on radiofrequency (RF) speckle or cumulative entropy on brightness-mode (B-mode) data. The fitted Nakagami parameter and entropy values in shadows were consistent across different transducers and anatomy. Both algorithms utilized adaptive thresholding, needing only the transducer pulse length as an input parameter for easy utilization by different operators or equipment. Mean Dice coefficients (± standard deviation) of 0.90 ± 0.07 and 0.87 ± 0.08 were obtained for the RF and B-mode algorithms, which is within the range of manual annotators. The high accuracy in different imaging scenarios indicates that the shadows can be detected with high versatility and without expert configuration. The understanding of shadow statistics can be used for more specialized techniques to be developed for specific applications in the future, including pre-processing for machine learning and automatic interpretation.

Automated Placenta Segmentation with a Convolutional Neural Network Weighted by Acoustic Shadow Detection.

Placental assessment through routine obstetrical ultrasound is often limited to documenting its location and ruling out placenta previa. However, many obstetrical complications originate from abnormal focal or global placental development. Technical difficulties in assessing the placenta as well as a lack of established objective criteria to classify echotexture are barriers to diagnosis of pathology by ultrasound imaging. As a first step towards the development of a computer aided placental assessment tool, we developed a fully automated method for placental segmentation using a convolutional neural network. The network contains a novel layer weighted by automated acoustic shadow detection to recognize artifacts specific to ultrasound. In order to develop a detection algorithm usable in different imaging scenarios, we acquired a dataset containing 1364 fetal ultrasound images from 247 patients acquired over 47 months was taken with different machines, operators, and at a range of gestational ages. Mean Dice coefficients for automated segmentation on the full dataset with and without the acoustic shadow detection layer were 0.92±0.04 and 0.91±0.03 when comparing to manual segmentation. Mean Dice coefficients on the subset of images containing acoustic shadows with and without acoustic shadow detection were 0.87±0.04 and 0.75±0.05. The method requires no user input to tune the detection. The automated placenta segmentation method can serve as a preprocessing step for further image analysis in artificial intelligence methods requiring large scale data processing of placental images.

Automatic Localization of the Needle Target for Ultrasound-Guided Epidural Injections.

Accurate identification of the needle target is crucial for effective epidural anesthesia. Currently, epidural needle placement is administered by a manual technique, relying on the sense of feel, which has a significant failure rate. Moreover, misleading the needle may lead to inadequate anesthesia, post dural puncture headaches, and other potential complications. Ultrasound offers guidance to the physician for identification of the needle target, but accurate interpretation and localization remain challenges. A hybrid machine learning system is proposed to automatically localize the needle target for epidural needle placement in ultrasound images of the spine. In particular, a deep network architecture along with a feature augmentation technique is proposed for automatic identification of the anatomical landmarks of the epidural space in ultrasound images. Experimental results of the target localization on planes of 3-D as well as 2-D images have been compared against an expert sonographer. When compared with the expert annotations, the average lateral and vertical errors on the planes of 3-D test data were 1 and 0.4 mm, respectively. On 2-D test data set, an average lateral error of 1.7 mm and vertical error of 0.8 mm were acquired.

Tracking a 3-D ultrasound probe with constantly visible fiducials.

A new method is presented for tracking a 3-D ultrasound (US) probe in space. The key is to use small fiducials that create point features in the US volume near the probe face and which are connected rigidly to the tracker on the probe. In this way, fiducials appear in every US volume and are used to calculate the position and orientation of the volume with respect to a fixed base. The main novelty is the elimination of a separate calibration device because calibration can be considered to be performed on every volume. After acquisition, the user simply marks the locations of the fiducials in the volume and solves a single equation to convert volume coordinates to the base. The point accuracy of the new method is slightly lower than those of conventional methods mainly because of the suboptimal appearance of the fiducials near the top of the image and little data averaging, but ease of use is improved.

Three-dimensional extended field-of-view ultrasound.

Three-dimensional (3-D) extended field-of-view ultrasound creates a mosaic view from a set of volumes acquired from a dedicated 3-D ultrasound machine combined with a position tracker. A simple compounding technique can be used to combine the volumes together using only the position measurements, but some misalignment remains. Two different registration methods were developed to correct these errors in the overlapping regions. The first method divides the overlap into smaller blocks and warps the blocks to best align the features. The second method is similar, but uses rigid body registration of the blocks. Experiments in vitro and in vivo showed that block-based registration with warping produced the most reproducible results and the greatest increase in similarity among the overlapping regions. It also produced the best reconstruction accuracy, with a mean distance error of 0.4 mm measured across 101.78 mm in a phantom, representing 0.4% error.

Needle tip localization using stylet vibration.

Power Doppler ultrasound is used to localize the tip of a needle by detecting physical vibrations. Two types of vibrations are investigated, lateral and axial. The lateral vibrations are created by rotating a stylet, whose tip is slightly bent, inside a stationary cannula while the stylet is completely within the cannula. The minute deflection at the needle tip when rotated causes tissue motion. The axial vibration is induced by extending and retracting a straight stylet inside a stationary cannula. The stylet's tip makes contact with the tissue and causes it to move. The lateral vibration method was found to perform approximately the same under a variety of configurations (e.g., different insertion angles and depths) and better than the axial vibration method. Tissue stiffness affects the performance of the lateral vibration method, but good images can be obtained through proper tuning of the ultrasound machine.

Methods for segmenting curved needles in ultrasound images.

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.

Ultrasound-Guided Spine Anesthesia: Feasibility Study of a Guidance System.

Spinal needle injections are guided by fluoroscopy or palpation, resulting in radiation exposure and/or multiple needle re-insertions. Consequently, guiding these procedures with live ultrasound has become more popular, but images are still challenging to interpret. We introduce a guidance system based on augmentation of ultrasound images with a patient-specific 3-D surface model of the lumbar spine. We assessed the feasibility of the system in a study on 12 patients. The system could accurately provide augmentations of the epidural space and the facet joint for all subjects. Following conventional, fluoroscopy-guided needle placement, augmentation accuracy was determined according to the electromagnetically tracked final position of the needle. In 9 of 12 cases, the accuracy was considered sufficient for successfully delivering anesthesia. The unsuccessful cases can be attributed to errors in the electromagnetic tracking reference, which can be avoided by a setup reducing the influence of the metal C-arm.

Comparison of calibration methods for spatial tracking of a 3-D ultrasound probe.

Real-time 3-D ultrasound (US) is a new-generation US system that uses a dedicated probe to create volume data sets instead of standard 2-D cross-sectional images. For applications in image-guided surgery and radiation therapy, a position tracker is added to the probe so that the volumes can be located in space. Calibration plays a critical role in determining the overall accuracy of an US volume-tracking system. In this paper, three calibration methods are developed specifically for 3-D probes. The three methods are based on a IXI-shaped wire phantom, a cube phantom and a stylus. The performance of each method was evaluated in terms of calibration reproducibility, point accuracy and reconstruction accuracy by distance measurement. The mean errors in the reproducibility tests were 1.50 mm (IXI-wire), 1.16 mm (cube) and 5.13 mm (stylus). The root mean square errors of the point accuracy measure were 2.15 mm (IXI-wire), 4.91 mm (cube) and 2.36 mm (stylus). The root mean square errors of the reconstruction accuracy by distance measure were 1.52 mm (IXI-wire), 1.59 mm (cube) and 1.85 mm (stylus). Overall, the IXI-wire phantom achieved the best results.

Needle detection in curvilinear ultrasound images based on the reflection pattern of circular ultrasound waves.

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.

Ultrasound RF time series for classification of breast lesions.

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.

Towards real-time, tracker-less 3D ultrasound guidance for spine anaesthesia.

PURPOSE: Epidural needle insertions and facet joint injections play an important role in spine anaesthesia. The main challenge of safe needle insertion is the deep location of the target, resulting in a narrow and small insertion channel close to sensitive anatomy. Recent approaches utilizing ultrasound (US) as a low-cost and widely available guiding modality are promising but have yet to become routinely used in clinical practice due to the difficulty in interpreting US images, their limited view of the internal anatomy of the spine, and/or inclusion of cost-intensive tracking hardware which impacts the clinical workflow. METHODS: We propose a novel guidance system for spine anaesthesia. An efficient implementation allows us to continuously align and overlay a statistical model of the lumbar spine on the live 3D US stream without making use of additional tracking hardware. The system is evaluated in vivo on 12 volunteers. RESULTS: The in vivo study showed that the anatomical features of the epidural space and the facet joints could be continuously located, at a volume rate of 0.5 Hz, within an accuracy of 3 and 7 mm, respectively. CONCLUSIONS: A novel guidance system for spine anaesthesia has been presented which augments a live 3D US stream with detailed anatomical information of the spine. Results from an in vivo study indicate that the proposed system has potential for assisting the physician in quickly finding the target structure and planning a safe insertion trajectory in the spine.

Real-time ultrasound image classification for spine anesthesia using local directional Hadamard features.

PURPOSE: Injection therapy is a commonly used solution for back pain management. This procedure typically involves percutaneous insertion of a needle between or around the vertebrae, to deliver anesthetics near nerve bundles. Most frequently, spinal injections are performed either blindly using palpation or under the guidance of fluoroscopy or computed tomography. Recently, due to the drawbacks of the ionizing radiation of such imaging modalities, there has been a growing interest in using ultrasound imaging as an alternative. However, the complex spinal anatomy with different wave-like structures, affected by speckle noise, makes the accurate identification of the appropriate injection plane difficult. The aim of this study was to propose an automated system that can identify the optimal plane for epidural steroid injections and facet joint injections. METHODS: A multi-scale and multi-directional feature extraction system to provide automated identification of the appropriate plane is proposed. Local Hadamard coefficients are obtained using the sequency-ordered Hadamard transform at multiple scales. Directional features are extracted from local coefficients which correspond to different regions in the ultrasound images. An artificial neural network is trained based on the local directional Hadamard features for classification. RESULTS: The proposed method yields distinctive features for classification which successfully classified 1032 images out of 1090 for epidural steroid injection and 990 images out of 1052 for facet joint injection. In order to validate the proposed method, a leave-one-out cross-validation was performed. The average classification accuracy for leave-one-out validation was 94 % for epidural and 90 % for facet joint targets. Also, the feature extraction time for the proposed method was 20 ms for a native 2D ultrasound image. CONCLUSION: A real-time machine learning system based on the local directional Hadamard features extracted by the sequency-ordered Hadamard transform for detecting the laminae and facet joints in ultrasound images has been proposed. The system has the potential to assist the anesthesiologists in quickly finding the target plane for epidural steroid injections and facet joint injections.