Shape estimation of flexible ultrasound arrays using spatial coherence: A preliminary study

A flexible ultrasound array can potentially provide a larger field-of-view, enhanced imaging resolution, and less operator dependency compared to conventional rigid transducer arrays. However, such transducer arrays require information about relative element positions for beamforming and reconstructing geometrically accurate sonograms. In this study, we assess the potential utility of using spatial coherence of backscattered radiofrequency data to estimate transducer array shape (inverse problem). The methodology is evaluated through 1) simulation of flexible arrays and 2) blinded in vivo experiments using commercial rigid transducer arrays on various anatomical targets (shoulder, forearm, scapular, posterior calf muscles, and abdomen) and multi-purpose ultrasound phantoms. The average Euclidean error of shape estimation is below 0.1 wavelengths for simulated arrays and below 1.4 wavelengths (median: 0.58 wavelengths) for real arrays. The complex wavelet structural similarity index between the B-mode images reconstructed with estimated and ground truth array shapes is above 99 % and 96 %, for simulations and experiments, respectively. These findings suggest that optimizing for spatial coherence may be an effective way to estimate the unknown shape of conformal ultrasound arrays.

Multi-Frequency 3D Shear Wave Absolute Vibro-Elastography (S-WAVE) System for the Prostate

This article describes a novel system for quantitative and volumetric measurement of tissue elasticity in the prostate using simultaneous multi-frequency tissue excitation. Elasticity is computed by using a local frequency estimator to measure the three-dimensional local wavelengths of steady-state shear waves within the prostate gland. The shear wave is created using a mechanical voice coil shaker which transmits simultaneous multi-frequency vibrations transperineally. Radio frequency data is streamed directly from a BK Medical 8848 transrectal ultrasound transducer to an external computer where tissue displacement due to the excitation is measured using a speckle tracking algorithm. Bandpass sampling is used that eliminates the need for an ultra-fast frame rate to track the tissue motion and allows for accurate reconstruction at a sampling frequency that is below the Nyquist rate. A roll motor with computer control is used to rotate the transducer and obtain 3D data. Two commercially available phantoms were used to validate both the accuracy of the elasticity measurements as well as the functional feasibility of using the system for in vivo prostate imaging. The phantom measurements were compared with 3D Magnetic Resonance Elastography (MRE), where a high correlation of 96% was achieved. In addition, the system has been used in two separate clinical studies as a method for cancer identification. Qualitative and quantitative results of 11 patients from these clinical studies are presented here. Furthermore, an AUC of 0.87±0.12 was achieved for malignant vs. benign classification using a binary support vector machine classifier trained with data from the latest clinical study with leave one patient out cross-validation.

3-D Transducer Mounted Shear Wave Absolute Vibro-Elastography: Proof of Concept

Quantitative tissue stiffness characterization using ultrasound (US) has been shown to improve prostate cancer (PCa) detection in multiple studies. Shear wave absolute vibro-elastography (SWAVE) allows quantitative and volumetric assessment of tissue stiffness using external multifrequency excitation. This article presents a proof of concept of a first-of-a-kind 3-D hand-operated endorectal SWAVE system designed to be used during systematic prostate biopsy. The system is developed with a clinical US machine, requiring only an external exciter that can be mounted directly to the transducer. Subsector acquisition of radio frequency (RF) data allows imaging of shear waves with a high effective frame rate (up to 250 Hz). The system was characterized using eight different quality assurance phantoms. Due to the invasive nature of prostate imaging, at this early stage of development, validation of in vivo human tissue was instead carried out by intercostally scanning the livers of n = 7 healthy volunteers. The results are compared with 3-D magnetic resonance elastography (MRE) and an existing 3-D SWAVE system with a matrix array transducer (M-SWAVE). High correlations were found with MRE (99% in phantoms, 94% in liver data) and with M-SWAVE (99% in phantoms, 98% in liver data).

Automatic measurement of kidney dimensions in two-dimensional ultrasonography is comparable to expert sonographers

Purpose

Length and width measurements of the kidneys aid in the detection and monitoring of structural abnormalities and organ disease. Manual measurement results in intra- and inter-rater variability, is complex and time-consuming, and is fraught with error. We propose an automated approach based on machine learning for quantifying kidney dimensions from two-dimensional (2D) ultrasound images in both native and transplanted kidneys.

Approach

An nnU-net machine learning model was trained on 514 images to segment the kidney capsule in standard longitudinal and transverse views. Two expert sonographers and three medical students manually measured the maximal kidney length and width in 132 ultrasound cines. The segmentation algorithm was then applied to the same cines, region fitting was performed, and the maximum kidney length and width were measured. Additionally, single kidney volume for 16 patients was estimated using either manual or automatic measurements.

Results

The experts resulted in length of 84.8±26.4  mm [95% CI: 80.0, 89.6] and a width of 51.8±10.5  mm [49.9, 53.7]. The algorithm resulted a length of 86.3±24.4 [81.5, 91.1] and a width of 47.1±12.8 [43.6, 50.6]. Experts, novices, and the algorithm did not statistically significant differ from one another (p>0.05). Bland-Altman analysis showed the algorithm produced a mean difference of 2.6 mm (SD = 1.2) from experts, compared to novices who had a mean difference of 3.7 mm (SD = 2.9 mm). For volumes, mean absolute difference was 47 mL (31%) consistent with ∼1  mm error in all three dimensions.

Conclusions

This pilot study demonstrates the feasibility of an automatic tool to measure in vivo kidney biometrics of length, width, and volume from standard 2D ultrasound views with comparable accuracy and reproducibility to expert sonographers. Such a tool may enhance workplace efficiency, assist novices, and aid in tracking disease progression.

The Kidneys Are Not All Normal: Transplanted Kidneys and Their Speckle Distributions

OBJECTIVE

Modelling ultrasound speckle to characterise tissue properties has generated considerable interest. As speckle is dependent on the underlying tissue architecture, modelling it may aid in tasks such as segmentation or disease detection. For the transplanted kidney, where ultrasound is used to investigate dysfunction, it is unknown which statistical distribution best characterises such speckle. This applies to the regions of the transplanted kidney: the cortex, the medulla and the central echogenic complex. Furthermore, it is unclear how these distributions vary by patient variables such as age, sex, body mass index, primary disease or donor type. These traits may influence speckle modelling given their influence on kidney anatomy. We investigate these two aims.

METHODS

B-mode images from n = 821 kidney transplant recipients (one image per recipient) were automatically segmented into the cortex, medulla and central echogenic complex using a neural network. Seven distinct probability distributions were fitted to each region's histogram, and statistical analysis was performed.

DISCUSSION

The Rayleigh and Nakagami distributions had model parameters that differed significantly between the three regions (p ≤ 0.05). Although both had excellent goodness of fit, the Nakagami had higher Kullbeck-Leibler divergence. Recipient age correlated weakly with scale in the cortex (Ω: ρ = 0.11, p = 0.004), while body mass index correlated weakly with shape in the medulla (m: ρ = 0.08, p = 0.04). Neither sex, primary disease nor donor type exhibited any correlation.

CONCLUSION

We propose the Nakagami distribution be used to characterize transplanted kidneys regionally independent of disease etiology and most patient characteristics.

SWAVE 2.0 Imaging of Placental Elasticity and Viscosity: Potential Biomarkers for Placenta-Mediated Disease Detection

Pregnancy complications such as pre-eclampsia (PE) and intrauterine growth restriction (IUGR) are associated with structural and functional changes in the placenta. Different elastography techniques with an ability to assess the mechanical properties of tissue can identify and monitor the pathological state of the placenta. Currently available elastography techniques have been used with promising results to detect placenta abnormalities; however, limitations include inadequate measurement depth and safety concerns from high negative pressure pulses. Previously, we described a shear wave absolute vibro-elastography (SWAVE) method by applying external low-frequency mechanical vibrations to generate shear waves and studied 61 post-delivery clinically normal placentas to explore the feasibility of SWAVE for placental assessment and establish a measurement baseline. This next phase of the study, namely, SWAVE 2.0, improves the previous system and elasticity reconstruction by incorporating a multi-frequency acquisition system and using a 3-D local frequency estimation (LFE) method. Compared with its 2-D counterpart, the proposed system using 3-D LFE was found to reduce the bias and variance in elasticity measurements in tissue-mimicking phantoms. In the aim of investigating the potential of improved SWAVE 2.0 measurements to identify placental abnormalities, we studied 46 post-delivery placentas, including 26 diseased (16 IUGR and 10 PE) and 20 normal control placentas. By use of a 3.33-MHz motorized curved-array transducer, multi-frequency (80,100 and 120 Hz) elasticity measures were obtained with 3-D LFE, and both IUGR (15.30 ± 2.96 kPa, p = 3.35e^-5) and PE (12.33 ± 4.88 kPa, p = 0.017) placentas were found to be significantly stiffer compared with the control placentas (8.32 ± 3.67 kPa). A linear discriminant analysis (LDA) classifier was able to classify between healthy and diseased placentas with a sensitivity, specificity and accuracy of 87%, 78% and 83% and an area under the receiver operating curve of 0.90 (95% confidence interval: 0.8-0.99). Further, the pregnancy outcome in terms of neonatal intensive care unit admission was predicted with a sensitivity, specificity and accuracy of 70%, 71%, 71%, respectively, and area under the receiver operating curve of 0.78 (confidence interval: 0.62-0.93). A viscoelastic characterization of placentas using a fractional rheological model revealed that the viscosity measures in terms of viscosity parameter n were significantly higher in IUGR (2.3 ± 0.21) and PE (2.11 ± 0.52) placentas than in normal placentas (1.45 ± 0.65). This work illustrates the potential relevance of elasticity and viscosity imaging using SWAVE 2.0 as a non-invasive technology for detection of placental abnormalities and the prediction of pregnancy outcomes.

Model-Based Quantitative Elasticity Reconstruction Using ADMM

We introduce two model-based iterative methods to obtain shear modulus images of tissue using magnetic resonance elastography. The first method jointly finds the displacement field that best fits tissue displacement data and the corresponding shear modulus. The displacement satisfies a viscoelastic wave equation constraint, discretized using the finite element method. Sparsifying regularization terms in both shear modulus and displacement are used in the cost function minimized for the best fit. The second method extends the first method for multifrequency tissue displacement data. The formulated problems are bi-convex. Their solution can be obtained iteratively by using the alternating direction method of multipliers. Sparsifying regularizations and the wave equation constraint filter out sensor noise and compressional waves. Our methods do not require bandpass filtering as a preprocessing step and converge fast irrespective of the initialization. We evaluate our new methods in multiple in silico and phantom experiments, with comparisons with existing methods, and we show improvements in contrast to noise and signal-to-noise ratios. Results from an in vivo liver imaging study show elastograms with mean elasticity comparable to other values reported in the literature.

Project SWAVE 2.0: An overview of the study design for multimodal placental image acquisition and alignment

Development of non-invasive and in utero placenta imaging techniques can potentially identify biomarkers of placental health. Correlative imaging using multiple multiscale modalities is particularly important to advance the understanding of placenta structure, function and their relationship. The objective of the project SWAVE 2.0 was to understand human placental structure and function and thereby identify quantifiable measures of placental health using a multimodal correlative approach. In this paper, we present a multimodal image acquisition protocol designed to acquire and align data from ex vivo placenta specimens derived from both healthy and complicated pregnancies. Qualitative and quantitative validation of the alignment method were performed. The qualitative analysis showed good correlation between findings in the MRI, ultrasound and histopathology images. The proposed protocol would enable future studies on comprehensive analysis of placental anatomy, function and their relationship.

● An overview of a novel multimodal placental image acquisition protocol is presented.

● A co-registration method using surface markers and external fiducials is described.

● A preliminary correlative imaging analysis for a placenta specimen is presented.

U-LanD: Uncertainty-Driven Video Landmark Detection

This paper presents U-LanD, a framework for automatic detection of landmarks on key frames of the video by leveraging the uncertainty of landmark prediction. We tackle a specifically challenging problem, where training labels are noisy and highly sparse. U-LanD builds upon a pivotal observation: a deep Bayesian landmark detector solely trained on key video frames, has significantly lower predictive uncertainty on those frames vs. other frames in videos. We use this observation as an unsupervised signal to automatically recognize key frames on which we detect landmarks. As a test-bed for our framework, we use ultrasound imaging videos of the heart, where sparse and noisy clinical labels are only available for a single frame in each video. Using data from 4,493 patients, we demonstrate that U-LanD can exceedingly outperform the state-of-the-art non-Bayesian counterpart by a noticeable absolute margin of 42% in R² score, with almost no overhead imposed on the model size.

Kidney Ultrasound for the Nephrologist: A Review

Ultrasound imaging is a key investigatory step in the evaluation of chronic kidney disease and kidney transplantation. It uses nonionizing radiation, is noninvasive, and generates real-time images, making it the ideal initial radiographic test for patients with abnormal kidney function. Ultrasound enables the assessment of both structural (form and size) and functional (perfusion and patency) aspects of kidneys, both of which are especially important as the disease progresses. Ultrasound and its derivatives have been studied for their diagnostic and prognostic significance in chronic kidney disease and kidney transplantation. Ultrasound is rapidly growing more widely accessible and is now available even in handheld formats that allow for bedside ultrasound examinations. Given the trend toward ubiquity, the current use of kidney ultrasound demands a full understanding of its breadth as it and its variants become available. We described the current applications and future directions of ultrasound imaging and its variants in the context of chronic kidney disease and transplantation in this review.

A unified representation of control logic in human-ultrasound machine interaction

Advances in human-computer interaction (HCI) technologies have granted sonographers and radiologists a much improved user experience when operating different ultrasound (US) machines. Continued HCI improvements in US would benefit from a systematic study of the HCI control logic used in this domain. Such a study has not been presented previously and is the subject of this paper. We surveyed sonographers to determine the most frequently used controls in US machines. We standardized the representation of the US machine HCI control logic by using the unified modelling language (UML). We used UML diagrams to analyze the HCI control logic of 10 different cart-based US machines from several major manufacturers, and we discovered that the control logic for the most frequently used functions are identical. While this control logic does not follow an established standard, it has been commonly adopted. Using the UML for the visualization and formulation of control logic, we can target logically optimal interactions (whose operation steps cannot be further reduced), e.g., adjustment of B-mode gain, frequency and depth, and can derive methods to simplify logically sub-optimal interactions, e.g., the pointing and selecting operation, as well as image measurements. Our study provides insights into existing HCI approaches used in US machines and establishes a rigorous UML-based framework for future US machine design to improve interoperability, efficiency and ease-of-use.

A multiparametric volumetric quantitative ultrasound imaging technique for soft tissue characterization

Quantitative ultrasound (QUS) offers a non-invasive and objective way to quantify tissue health. We recently presented a spatially adaptive regularization method for reconstruction of a single QUS parameter, limited to a two dimensional region. That proof-of-concept study showed that regularization using homogeneity prior improves the fundamental precision-resolution trade-off in QUS estimation. Based on the weighted regularization scheme, we now present a multiparametric 3D weighted QUS (3D QUS) method, involving the reconstruction of three QUS parameters: attenuation coefficient estimate (ACE), integrated backscatter coefficient (IBC) and effective scatterer diameter (ESD). With the phantom studies, we demonstrate that our proposed method accurately reconstructs QUS parameters, resulting in high reconstruction contrast and therefore improved diagnostic utility. Additionally, the proposed method offers the ability to analyze the spatial distribution of QUS parameters in 3D, which allows for superior tissue characterization. We apply a three-dimensional total variation regularization method for the volumetric QUS reconstruction. The 3D regularization involving N planes results in a high QUS estimation precision, with an improvement of standard deviation over the theoretical 1/N rate achievable by compounding N independent realizations. In the in vivo liver study, we demonstrate the advantage of adopting a multiparametric approach over the single parametric counterpart, where a simple quadratic discriminant classifier using feature combination of three QUS parameters was able to attain a perfect classification performance to distinguish between normal and fatty liver cases.

Investigation of photoacoustic tomography reconstruction with a limited view from linear array

SIGNIFICANCE

As linear array transducers are widely used in clinical ultrasound imaging, photoacoustic tomography (PAT) with linear arrays is similarly suitable for clinical applications. However, due to the limited-view problem, a linear array has limited performance and leads to artifacts and blurring, which has hindered its broader application. There is a need to address the limited-view problem in PAT imaging with linear arrays.

AIM

We investigate potential approaches for improving PAT reconstruction from linear array, by optimizing the detection geometry and implementing iterative reconstruction.

APPROACH

PAT imaging with a single-array, dual-probe configurations in parallel-shape and L-shape, and square-shape configuration are compared in simulations and phantom experiments. An iterative model-based algorithm based on the variance-reduced stochastic gradient descent (VR-SGD) method is implemented. The optimum configuration found in simulation is validated on phantom experiments.

RESULTS

PAT imaging with dual-probe detection and VR-SGD algorithm is found to improve the limited-view problem compared to a single probe and provide comparable performance as full-view geometry in simulation. This configuration is validated in experiments where more complete structure is obtained with reduced artifacts compared with a single array.

CONCLUSIONS

PAT with dual-probe detection and iterative reconstruction is a promising solution to the limited-view problem of linear arrays.

Breast Cancer Detection using Multimodal Time Series Features from Ultrasound Shear Wave Absolute Vibro-Elastography

In shear wave absolute vibro-elastography (S-WAVE), a steady-state multi-frequency external mechanical excitation is applied to tissue, while a time-series of ultrasound radio-frequency (RF) data are acquired. Our objective is to determine the potential of S-WAVE to classify breast tissue lesions as malignant or benign. We present a new processing pipeline for feature-based classification of breast cancer using S-WAVE data, and we evaluate it on a new data set collected from 40 patients. Novel bi-spectral and Wigner spectrum features are computed directly from the RF time series and are combined with textural and spectral features from B-mode and elasticity images. The Random Forest permutation importance ranking and the Quadratic Mutual Information methods are used to reduce the number of features from 377 to 20. Support Vector Machines and Random Forest classifiers are used with leave-one-patient-out and Monte Carlo cross-validations. Classification results obtained for different feature sets are presented. Our best results (95% confidence interval, Area Under Curve = 95%1.45%, sensitivity = 95%, and specificity = 93%) outperform the state-of-the-art reported S-WAVE breast cancer classification performance. The effect of feature selection and the sensitivity of the above classification results to changes in breast lesion contours is also studied. We demonstrate that time-series analysis of externally vibrated tissue as an elastography technique, even if the elasticity is not explicitly computed, has promise and should be pursued with larger patient datasets. Our study proposes novel directions in the field of elasticity imaging for tissue classification.

Echo-SyncNet: Self-Supervised Cardiac View Synchronization in Echocardiography

In echocardiography (echo), an electrocardiogram (ECG) is conventionally used to temporally align different cardiac views for assessing critical measurements. However, in emergencies or point-of-care situations, acquiring an ECG is often not an option, hence motivating the need for alternative temporal synchronization methods. Here, we propose Echo-SyncNet, a self-supervised learning framework to synchronize various cross-sectional 2D echo series without any human supervision or external inputs. The proposed framework takes advantage of two types of supervisory signals derived from the input data: spatiotemporal patterns found between the frames of a single cine (intra-view self-supervision) and interdependencies between multiple cines (inter-view self-supervision). The combined supervisory signals are used to learn a feature-rich and low dimensional embedding space where multiple echo cines can be temporally synchronized. Two intra-view self-supervisions are used, the first is based on the information encoded by the temporal ordering of a cine (temporal intra-view) and the second on the spatial similarities between nearby frames (spatial intra-view). The inter-view self-supervision is used to promote the learning of similar embeddings for frames captured from the same cardiac phase in different echo views. We evaluate the framework with multiple experiments: 1) Using data from 998 patients, Echo-SyncNet shows promising results for synchronizing Apical 2 chamber and Apical 4 chamber cardiac views, which are acquired spatially perpendicular to each other; 2) Using data from 3070 patients, our experiments reveal that the learned representations of Echo-SyncNet outperform a supervised deep learning method that is optimized for automatic detection of fine-grained cardiac cycle phase; 3) We go one step further and show the usefulness of the learned representations in a one-shot learning scenario of cardiac key-frame detection. Without any fine-tuning, key frames in 1188 validation patient studies are identified by synchronizing them with only one labeled reference cine. We do not make any prior assumption about what specific cardiac views are used for training, and hence we show that Echo-SyncNet can accurately generalize to views not present in its training set. Project repository: github.com/fatemehtd/Echo-SyncNet>.

Three-Dimensional Multi-Frequency Shear Wave Absolute Vibro-Elastography (3D S-WAVE) With a Matrix Array Transducer: Implementation and Preliminary In Vivo Study of the Liver

Magnetic resonance elastography (MRE) is commonly regarded as the imaging-based gold-standard for liver fibrosis staging, comparable to biopsy. While ultrasound-based elastography methods for liver fibrosis staging have been developed, they are confined to a 1D or a 2D region of interest and to a limited depth. 3D Shear Wave Absolute Vibro-Elastography (S-WAVE) is a steady-state, external excitation, volumetric elastography technique that is similar to MRE, but has the additional advantage of multi-frequency excitation. We present a novel ultrasound matrix array implementation of S-WAVE that takes advantage of 3D imaging. We use a matrix array transducer to sample axial multi-frequency steady-state tissue motion over a volume, using a Color Power Angiography sequence. Tissue motion with the frequency components {40,50,60} and {45,55,65} Hz are acquired over a (90° lateral) × (40° elevational) × (16 cm depth) sector with an acquisition time of 12 seconds. We compute the elasticity map in 3D using local spatial frequency estimation. We characterize this new approach in tissue phantoms against measurements obtained with transient elastography and MRE. Six healthy volunteers and eight patients with chronic liver disease were imaged. Their MRE and S-WAVE volumes were aligned using T1 to B-mode registration for direct comparison in common regions of interest. S-WAVE and MRE results are correlated with R² = 0.92, while MRE and TE results are correlated with R² = 0.71. Our findings show that S-WAVE with matrix array has the potential to deliver a similar assessment of liver fibrosis as MRE in a more accessible, inexpensive way, to a broader set of patients.

3D Global Time-Delay Estimation for Shear-Wave Absolute Vibro-Elastography of the Placenta

The placenta is a vital organ for growth and development of the fetus. Shear Wave Absolute Vibro-Elastography (SWAVE) is a new elastography technique proposed to detect placenta disorders. Elastography involves applying a force on the tissue and measuring the resulting tissue deformation. All types of compression cause the tissue to expand in three directions given the biological tissues are nearly incompressible. Hence, 3D displacement estimation should lead to the most accurate elasticity reconstruction compared to the traditional 1D methods. Previous studies estimated 3D displacements over ultrasound volumes mostly for quasi-static compression to generate strain images. However, accurate displacement tracking of dynamic motion continues to be a challenge. In this work, a novel volumetric regularized algorithm, 3D GLobal Ultrasound Elastography (GLUE3D), is presented to estimate the 3D displacement over a volume of ultrasound data, following by a 3D Young's modulus reconstruction. The proposed method outperforms the previous 2D method over a volume and is compared with a 3D technique using phantom data for which the elasticity are provided by the values from magnetic resonance elastography on the same phantom and also the manufacturer reference numbers. We then present Young's modulus reconstruction results obtained from clinical data of placenta which shows more uniform elasticity maps compared to the traditional 1D displacement measurements over a volume of ultrasound data. Furthermore, the dependency of the elasticity values to the frequency is investigated in this study.

Automatic Midline Identification in Transverse 2-D Ultrasound Images of the Spine

Effective epidural needle placement and injection involves accurate identification of the midline of the spine. Ultrasound, as a safe pre-procedural imaging modality, is suitable for epidural guidance because it offers adequate visibility of the vertebral anatomy. However, image interpretation remains a key challenge, especially for novices. A deep neural network is proposed to automatically classify the transverse ultrasound images of the vertebrae and identify the midline. To distinguish midline images from off-center frames, the proposed network detects the left-right symmetric anatomic landmarks. To assess the feasibility of the proposed method for midline detection, a data set of ultrasound images was collected from 20 volunteers, whose body mass indices were less than 30. The data were split into two segments, for training and test. The performance of the proposed method was further evaluated using fourfold cross validation. Moreover, it was compared against a state-of-the-art deep neural network. Compared with the gold standard provided by an expert sonographer, the proposed trained network correctly classified 88% of the transverse planes from unseen test patients. This capability supports the first step of guiding the placement of an epidural needle.

Enhancement of needle visualization and localization in ultrasound

PURPOSE

This scoping review covers needle visualization and localization techniques in ultrasound, where localization-based approaches mostly aim to compute the needle shaft (and tip) location while potentially enhancing its visibility too.

METHODS

A literature review is conducted on the state-of-the-art techniques, which could be divided into five categories: (1) signal and image processing-based techniques to augment the needle, (2) modifications to the needle and insertion to help with needle-transducer alignment and visibility, (3) changes to ultrasound image formation, (4) motion-based analysis and (5) machine learning.

RESULTS

Advantages, limitations and challenges of representative examples in each of the categories are discussed. Evaluation techniques performed in ex vivo, phantom and in vivo studies are discussed and summarized.

CONCLUSION

Greatest limitation of the majority of the literature is that they rely on original visibility of the needle in the static image. Need for additional/improved apparatus is the greatest limitation toward clinical utility in practice.

SIGNIFICANCE

Ultrasound-guided needle placement is performed in many clinical applications, including biopsies, treatment injections and anesthesia. Despite the wide range and long history of this technique, an ongoing challenge is needle visibility in ultrasound. A robust technique to enhance ultrasonic needle visibility, especially for steeply inserted hand-held needles, and while maintaining clinical utility requirements is needed.

A comparative study on position and paramedian neuraxial access on healthy volunteers using three-dimensional models registered to lumbar spine ultrasound

PURPOSE

Optimizing patient position and needle puncture site are important factors for successful neuraxial anesthesia. Two paramedian approaches are commonly utilized and we sought to determine whether variations of the seated position would increase the chance of puncture success.

METHODS

We simulated paramedian needle passes on three-dimensional lumbar spine models registered to volumetric ultrasound data acquired from ten healthy volunteers in three different positions: 1) prone; 2) seated with thoracic and lumbar flexion; and 3) seated as in position 2, but with a 10° dorsal tilt. Simulated paramedian needle passes from the right side performed on validated models were used to determine L2-3 and L3-4 neuraxial target size and success. We selected two paramedian puncture sites according to standard anesthesia textbook descriptions: 10 mm lateral and 10 mm caudal from inferior edge of the superior spinous process as described by Miller, and 10 mm lateral from the superior edge of the inferior spinous process as described by Barash.

RESULTS

A significant increase in the area available for dural puncture was found in the L2-3 (61-62 mm²) and L3-4 (76-79 mm²) vertebral levels for all seated positions relative to the prone position (P < 0.001). Similarly, a significant increase in the total number of successful punctures was found in the L2-3 (77-79) and L3-4 (119-120) vertebral levels for all seated positions relative to the prone position (P < 0.001). No differences were found between seated positions. The Barash puncture site achieved a higher number of successful punctures than the Miller puncture site in both the L2-3 (19) and L3-4 (84) vertebral levels (P < 0.001).

CONCLUSION

An added dorsal table tilt did not increase puncture success in the seated position. The landmarks for puncture site described by Barash resulted in significantly more successful punctures compared with those described by Miller in all positions.

On Modelling Label Uncertainty in Deep Neural Networks: Automatic Estimation of Intra- Observer Variability in 2D Echocardiography Quality Assessment

Uncertainty of labels in clinical data resulting from intra-observer variability can have direct impact on the reliability of assessments made by deep neural networks. In this paper, we propose a method for modelling such uncertainty in the context of 2D echocardiography (echo), which is a routine procedure for detecting cardiovascular disease at point-of-care. Echo imaging quality and acquisition time is highly dependent on the operator's experience level. Recent developments have shown the possibility of automating echo image quality quantification by mapping an expert's assessment of quality to the echo image via deep learning techniques. Nevertheless, the observer variability in the expert's assessment can impact the quality quantification accuracy. Here, we aim to model the intra-observer variability in echo quality assessment as an aleatoric uncertainty modelling regression problem with the introduction of a novel method that handles the regression problem with categorical labels. A key feature of our design is that only a single forward pass is sufficient to estimate the level of uncertainty for the network output. Compared to the 0.11 ± 0.09 absolute error (in a scale from 0 to 1) archived by the conventional regression method, the proposed method brings the error down to 0.09 ± 0.08, where the improvement is statistically significant and equivalents to 5.7% test accuracy improvement. The simplicity of the proposed approach means that it could be generalized to other applications of deep learning in medical imaging, where there is often uncertainty in clinical labels.

Cardiac point-of-care to cart-based ultrasound translation using constrained CycleGAN

PURPOSE

 The emerging market of cardiac handheld ultrasound (US) is on the rise. Despite the advantages in ease of access and the lower cost, a gap in image quality can still be observed between the echocardiography (echo) data captured by point-of-care ultrasound (POCUS) compared to conventional cart-based US, which limits the further adaptation of POCUS. In this work, we aim to present a machine learning solution based on recent advances in adversarial training to investigate the feasibility of translating POCUS echo images to the quality level of high-end cart-based US systems.

METHODS

 We propose a constrained cycle-consistent generative adversarial architecture for unpaired translation of cardiac POCUS to cart-based US data. We impose a structured shape-wise regularization via a critic segmentation network to preserve the underlying shape of the heart during quality translation. The proposed deep transfer model is constrained to the anatomy of the left ventricle (LV) in apical two-chamber (AP2) echo views.

RESULTS

 A total of 1089 echo studies from 841 patients are used in this study. The AP2 frames are captured by POCUS (Philips Lumify and Clarius) and cart-based (Philips iE33 and Vivid E9) US machines. The dataset of quality translation comprises a total of 441 echo studies from 395 patients. Data from both POCUS and cart-based systems of the same patient were available in 122 cases. The deep-quality transfer model is integrated into a pipeline for an automated cardiac evaluation task, namely segmentation of LV in AP2 view. By transferring the low-quality POCUS data to the cart-based US, a significant average improvement of 30% and 34 mm is obtained in the LV segmentation Dice score and Hausdorff distance metrics, respectively.

CONCLUSION

 This paper presents the feasibility of a machine learning solution to transform the image quality of POCUS data to that of high-quality high-end cart-based systems. The experiments show that by leveraging the quality translation through the proposed constrained adversarial training, the accuracy of automatic segmentation with POCUS data could be improved.

Cardiac Phase Detection in Echocardiograms With Densely Gated Recurrent Neural Networks and Global Extrema Loss

Accurate detection of end-systolic (ES) and end-diastolic (ED) frames in an echocardiographic cine series can be difficult but necessary pre-processing step for the development of automatic systems to measure cardiac parameters. The detection task is challenging due to variations in cardiac anatomy and heart rate often associated with pathological conditions. We formulate this problem as a regression problem and propose several deep learning-based architectures that minimize a novel global extrema structured loss function to localize the ED and ES frames. The proposed architectures integrate convolution neural networks (CNNs)-based image feature extraction model and recurrent neural networks (RNNs) to model temporal dependencies between each frame in a sequence. We explore two CNN architectures: DenseNet and ResNet, and four RNN architectures: long short-term memory, bi-directional LSTM, gated recurrent unit (GRU), and Bi-GRU, and compare the performance of these models. The optimal deep learning model consists of a DenseNet and GRU trained with the proposed loss function. On average, we achieved 0.20 and 1.43 frame mismatch for the ED and ES frames, respectively, which are within reported inter-observer variability for the manual detection of these frames.

Region-of-Interest-Based Closed-Loop Beamforming for Spinal Ultrasound Imaging

Clear visualization of spine structures in ultrasound imaging is difficult due to factors such as specular reflection, off-axis energy, and reverberation artifacts. The received channel data from the spine are often tilted even after delay correction, resulting in signal cancellation during the beamforming process. Conventional beamformers are not designed to tackle this issue. This paper proposes a closed-loop beamforming method which feeds back the location of the spine to the beamforming process so that backscattered bone signals can be aligned prior to the beamforming. To suppress the weak soft tissue and reverberation artifacts and increase the contrast of bones, a tensor-based filtering is employed prior to the cross-correlation-based alignment. Directional filtering is also employed to improve the bone surface detection. Phantom studies show improvement on the sharpness of the spine without shape distortion. In vivo results confirm significant contrast improvement of spinal structures. Compared with the conventional delay-and-sum beamforming, the proposed method improves the contrast ratio (CR) of the spine from 0.56 to 0.96. The 6-dB width of bone surfaces is also reduced by 51%.

Photoacoustic tomography for imaging the prostate: a transurethral illumination probe design and application

In vivo imaging of prostate cancer with photoacoustic tomography is currently limited by the lack of sufficient local fluence for deep tissue penetration and the risk of over-irradiation near the laser-tissue contact surface. We propose the design of a transurethral illumination probe that addresses those limitations. A high energy of 50 mJ/pulse is coupled into a 1000-µm-core diameter multimode fiber. A 2 cm diffusing end is fabricated, which delivers light in radial illumination. The radial illumination is then reflected and reshaped by a parabolic cylindrical mirror to obtain nearly parallel side illumination with a doubled fluence. The fiber assembly is housed in a 25 Fr cystoscope sheath to provide protection of the fiber and maintain a minimal laser-tissue contact distance of 5 mm. A large laser-tissue contact surface area of 4 cm² is obtained and the fluence on the tissue surface is kept below the maximum permissible exposure. By imaging a prostate mimicking phantom, a penetration depth of 3.5 cm at 10 mJ/cm² fluence and 700 nm wavelength is demonstrated. The results indicate that photoacoustic tomography with the proposed transurethral probe has the potential to image the entire prostate while satisfying the fluence maximum permissible exposure and delivering a high power to the tissue.

Attenuation Coefficient Estimation of Normal Placentas

Attenuation coefficient estimation has the potential to be a useful tool for placental tissue characterization. A current challenge is the presence of inhomogeneities in biological tissue that result in a large variance in the attenuation coefficient estimate (ACE), restricting its clinical utility. In this work, we propose a new Attenuation Estimation Region Of Interest (AEROI) selection method for computing the ACE based on the (i) envelope signal-to-noise ratio deviation and (ii) coefficient of variation of the transmit pulse bandwidth. The method was first validated on a tissue-mimicking phantom, for which an 18%-21% reduction in the standard deviation of ACE and a 14%-24% reduction in the ACE error, expressed as a percentage of reported ACE, were obtained. A study on 59 post-delivery clinically normal placentas was then performed. The proposed AEROI selection method reduced the intra-subject standard deviation of ACE from 0.72 to 0.39 dB/cm/MHz. The measured ACE of 59 placentas was 0.77 ± 0.37 dB/cm/MHz, which establishes a baseline for future studies on placental tissue characterization.

Automatic biplane left ventricular ejection fraction estimation with mobile point-of-care ultrasound using multi-task learning and adversarial training

PURPOSE

Left ventricular ejection fraction (LVEF) is one of the key metrics to assess the heart functionality, and cardiac ultrasound (echo) is a standard imaging modality for EF measurement. There is an emerging interest to exploit the point-of-care ultrasound (POCUS) usability due to low cost and ease of access. In this work, we aim to present a computationally efficient mobile application for accurate LVEF estimation.

METHODS

Our proposed mobile application for LVEF estimation runs in real time on Android mobile devices that have either a wired or wireless connection to a cardiac POCUS device. We propose a pipeline for biplane ejection fraction estimation using apical two-chamber (AP2) and apical four-chamber (AP4) echo views. A computationally efficient multi-task deep fully convolutional network is proposed for simultaneous LV segmentation and landmark detection in these views, which is integrated into the LVEF estimation pipeline. An adversarial critic model is used in the training phase to impose a shape prior on the LV segmentation output.

RESULTS

The system is evaluated on a dataset of 427 patients. Each patient has a pair of captured AP2 and AP4 echo studies, resulting in a total of more than 40,000 echo frames. The mobile system reaches a noticeably high average Dice score of 92% for LV segmentation, an average Euclidean distance error of 2.85 pixels for the detection of anatomical landmarks used in LVEF calculation, and a median absolute error of 6.2% for LVEF estimation compared to the expert cardiologist's annotations and measurements.

CONCLUSION

The proposed system runs in real time on mobile devices. The experiments show the effectiveness of the proposed system for automatic LVEF estimation by demonstrating an adequate correlation with the cardiologist's examination.

Comparison of Patient Position and Midline Lumbar Neuraxial Access Via Statistical Model Registration to Ultrasound

Patient positioning and needle puncture site are important for lumbar neuraxial anesthesia. We sought to identify optimal patient positioning and puncture sites with a novel ultrasound registration. We registered a statistical model to volumetric ultrasound data acquired from volunteers (n = 10) in three positions: (i) prone; (ii) seated with thoracic and lumbar flexion; and (iii) seated as in position ii, with a 10° dorsal tilt. We determined injection target size and penetration success by simulating lumbar injections on validated registered models. Injection window and target area sizes in seated positions were significantly larger than those in prone positions by 65% in L2-3 and 130% in L3-4; a 10° tilt had no significant effect on target sizes between seated positions. In agreement with computed tomography studies, simulated L2-3 and L3-4 injections had the highest success at the 50% and 75% midline puncture sites, respectively, measured from superior to inferior spinous process. We conclude that our registration to ultrasound technique is a potential tool for tolerable determination of puncture site success in vivo.

Multiparametric QUS Analysis for Placental Tissue Characterization

Multiparametric Quantitative Ultrasound (QUS) holds promise for characterizing placental tissue and detecting placental disorders. In this study, we simultaneously extract two qualitatively different QUS parameters, namely attenuation coefficient estimate (ACE) and shear wave speed from ultrasound radio frequency data acquired using a shear wave vibro elastography (SWAVE) method. The study comprised data from 59 post-delivery clinically normal placentas. The shear wave speed was found to be equal to 1.74 ± 0.13 m/s whereas the attenuation coefficient estimate was 0.57 ± 0.48 dB/cm-MHz. This provides a baseline for future studies of placental disorders.

Real-Time FEM-Based Registration of 3-D to 2.5-D Transrectal Ultrasound Images

We present a novel technique for real-time deformable registration of 3-D to 2.5-D transrectal ultrasound (TRUS) images for image-guided, robot-assisted laparoscopic radical prostatectomy (RALRP). For RALRP, a pre-operatively acquired 3-D TRUS image is registered to thin-volumes comprised of consecutive intra-operative 2-D TRUS images, where the optimal transformation is found using a gradient descent method based on analytical first and second order derivatives. Our method relies on an efficient algorithm for real-time extraction of arbitrary slices from a 3-D image deformed given a discrete mesh representation. We also propose and demonstrate an evaluation method that generates simulated models and images for RALRP by modeling tissue deformation through patient-specific finite-element models (FEM). We evaluated our method on in-vivo data from 11 patients collected during RALRP and focal therapy interventions. In the presence of an average landmark deformation of 3.89 and 4.62 mm, we achieved accuracies of 1.15 and 0.72 mm, respectively, on the synthetic and in-vivo data sets, with an average registration computation time of 264 ms, using MATLAB on a conventional PC. The results show that the real-time tracking of the prostate motion and deformation is feasible, enabling a real-time augmented reality-based guidance system for RALRP.].

Follow the light: projector-based augmented reality intracorporeal system for laparoscopic surgery

A projector-based augmented reality intracorporeal system (PARIS) is presented that includes a miniature tracked projector, tracked marker, and laparoscopic ultrasound (LUS) transducer. PARIS was developed to improve the efficacy and safety of laparoscopic partial nephrectomy (LPN). In particular, it has been demonstrated to effectively assist in the identification of tumor boundaries during surgery and to improve the surgeon's understanding of the underlying anatomy. PARIS achieves this by displaying the orthographic projection of the cancerous tumor on the kidney's surface. The performance of PARIS was evaluated in a user study with two surgeons who performed 32 simulated robot-assisted partial nephrectomies. They performed 16 simulated partial nephrectomies with PARIS for guidance and 16 simulated partial nephrectomies with only an LUS transducer for guidance. With PARIS, there was a significant reduction [30% ([Formula: see text])] in the amount of healthy tissue excised and a trend toward a more accurate dissection around the tumor and more negative margins. The combined point tracking and reprojection root-mean-square error of PARIS was 0.8 mm. PARIS' proven ability to improve key metrics of LPN surgery and qualitative feedback from surgeons about PARIS supports the hypothesis that it is an effective surgical navigation tool.

Accumulated Angle Factor-Based Beamforming to Improve the Visualization of Spinal Structures in Ultrasound Images

In recent years, ultrasound has been increasingly used to guide needle insertion procedures for spinal anesthesia. The primary anatomical targets are facet joints and epidural spaces. For these procedures, accurate visualization of the spine anatomy is of critical importance. Challenges arising from the interactions between the ultrasound beam and spinal structures including tilt caused by specular reflections, off-axis interference, and reverberations often result in weakened and blurred vertebra surfaces. Previously, adaptive beamforming methods have been proposed to improve the resolution and contrast. However, most of these methods are not specialized for improving the contrast of specular targets like bones. In this paper, we propose an accumulated angle factor (AAF)-based beamforming method customized for bone surface enhancement. This approach applies a Hilbert transform on delay compensated channel data across the receive aperture. The accumulated phase change across the receive aperture is then calculated and utilized as the weight in the beamforming output. We compared our method with classical delay and sum (DAS) beamforming method and adaptive beamforming methods such as Wiener, phase coherence factor (PCF), CF, and generalized CF (GCF) beamforming. In 12 volunteer data sets, the mean contrast ratio between the vertebrae surface and the surrounding tissue for DAS, Wiener, PCF, CF, GCF, and the proposed AAF methods are 0.49, 0.64, 0.82, 0.77, 0.76, and 0.91, respectively. The contrast is significantly improved in the proposed method.

Fabrication and testing of polymer-based capacitive micromachined ultrasound transducers for medical imaging

The ultrasonic transducer industry is dominated by piezoelectric materials. As an emerging alternative, capacitive micromachined ultrasound transducers (CMUTs) offer wider bandwidth, better integration with electronics, and ease of fabricating large arrays. CMUTs have a sealed cavity between a fixed electrode and a suspended metalized membrane. Manufacturing cost and sensitivity are limiting factors in current CMUTs that depend on the fabrication equipment and, especially, on the materials used. For widespread use of CMUTs, a much lower fabrication cost that uses inexpensive materials, which maintain or improve upon existing sensitivity, is needed. Herein, a new fabrication process is described for polymer-based CMUTs (polyCMUTs) using the photopolymer SU-8 and Omnicoat. The first ultrasound B-mode image of a wire phantom created with a 64-element linear array using synthetic aperture beamforming techniques is presented. A 12 V _AC signal superimposed on a 10 V_DC signal was used on the transmission side, and only a bias-tee, with no amplifiers, was used on the receiving side. The low operational voltage and high sensitivity of this device can be partially attributed to a pre-biasing condition on the membrane. By using a novel sacrificial layer combined with a top electrode embedded inside the membrane, we demonstrated that SU-8 can be used to manufacture CMUTs inexpensively. Moreover, the fabrication used relatively simple equipment, and the number of fabrication steps was reduced compared to traditional CMUT fabrication. This new fabrication process has the potential to increase the use of CMUTs in the ultrasound market, including the market for wearable transducers.

Fast elastic registration of soft tissues under large deformations

A fast and accurate fusion of intra-operative images with a pre-operative data is a key component of computer-aided interventions which aim at improving the outcomes of the intervention while reducing the patient's discomfort. In this paper, we focus on the problematic of the intra-operative navigation during abdominal surgery, which requires an accurate registration of tissues undergoing large deformations. Such a scenario occurs in the case of partial hepatectomy: to facilitate the access to the pathology, e.g. a tumor located in the posterior part of the right lobe, the surgery is performed on a patient in lateral position. Due to the change in patient's position, the resection plan based on the pre-operative CT scan acquired in the supine position must be updated to account for the deformations. We suppose that an imaging modality, such as the cone-beam CT, provides the information about the intra-operative shape of an organ, however, due to the reduced radiation dose and contrast, the actual locations of the internal structures necessary to update the planning are not available. To this end, we propose a method allowing for fast registration of the pre-operative data represented by a detailed 3D model of the liver and its internal structure and the actual configuration given by the organ surface extracted from the intra-operative image. The algorithm behind the method combines the iterative closest point technique with a biomechanical model based on a co-rotational formulation of linear elasticity which accounts for large deformations of the tissue. The performance, robustness and accuracy of the method is quantitatively assessed on a control semi-synthetic dataset with known ground truth and a real dataset composed of nine pairs of abdominal CT scans acquired in supine and flank positions. It is shown that the proposed surface-matching method is capable of reducing the target registration error evaluated of the internal structures of the organ from more than 40 mm to less then 10 mm. Moreover, the control data is used to demonstrate the compatibility of the method with intra-operative clinical scenario, while the real datasets are utilized to study the impact of parametrization on the accuracy of the method. The method is also compared to a state-of-the art intensity-based registration technique in terms of accuracy and performance.

Intra-operative ultrasound-based augmented reality guidance for laparoscopic surgery

In laparoscopic surgery, the surgeon must operate with a limited field of view and reduced depth perception. This makes spatial understanding of critical structures difficult, such as an endophytic tumour in a partial nephrectomy. Such tumours yield a high complication rate of 47%, and excising them increases the risk of cutting into the kidney's collecting system. To overcome these challenges, an augmented reality guidance system is proposed. Using intra-operative ultrasound, a single navigation aid, and surgical instrument tracking, four augmentations of guidance information are provided during tumour excision. Qualitative and quantitative system benefits are measured in simulated robot-assisted partial nephrectomies. Robot-to-camera calibration achieved a total registration error of 1.0 ± 0.4 mm while the total system error is 2.5 ± 0.5 mm. The system significantly reduced healthy tissue excised from an average (±standard deviation) of 30.6 ± 5.5 to 17.5 ± 2.4 cm³ (p < 0.05) and reduced the depth from the tumor underside to cut from an average (±standard deviation) of 10.2 ± 4.1 to 3.3 ± 2.3 mm (p < 0.05). Further evaluation is required in vivo, but the system has promising potential to reduce the amount of healthy parenchymal tissue excised.

Correction to "Automatic Quality Assessment of Echocardiograms Using Convolutional Neural Networks: Feasibility on the Apical Four-Chamber View"

In the above paper [1], the first footnote should have indicated the following information: A. H. Abdi and C. Luong are joint first authors.

A Comparison of Finite Element-Based Inversion Algorithms, Local Frequency Estimation, and Direct Inversion Approach Used in MRE

In quantitative elastography, maps of the mechanical properties of soft tissue, or elastograms, are calculated from the measured displacement data by solving an inverse problem. The model assumptions have a significant effect on elastograms. Motivated by the high sensitivity of imaging results to the model assumptions for in vivo magnetic resonance elastography of the prostate, we compared elastograms obtained with four different methods. Two finite-element method (FEM)-based methods developed by our group were compared with two other commonly used methods, local frequency estimator (LFE) and curl-based direct inversion (c-DI). All the methods assume a linear isotropic elastic model, but the methods vary in their assumptions, such as local homogeneity or incompressibility, and in the specific approach used. We report results using simulations, phantom, and ex vivo and in vivo data. The simulation and phantom studies show, for regions with an inclusion, that the contrast to noise ratio (CNR) for the FEM methods is about three to five times higher than the CNR for the LFE and c-DI and the rms error is about half. The LFE method produces very smooth results (i.e., low CNR) and is fast. c-DI is faster than the FEM methods but it is only accurate in areas where elasticity variations are small. The artifacts resulting from the homogeneity assumption in c-DI is detrimental in regions with large variations. The ex vivo and in vivo results also show similar trends as the simulation and phantom studies. The c-FEM method is more sensitive to noise compared with the mixed-FEM due to higher orders derivatives. This is especially evident at lower frequencies, where the wave curvature is smaller and it is more prone to such error, causing a discrepancy in the absolute values between the mixed-FEM and c-FEM in our in vivo results. In general, the proposed FEMs use fewer simplifying assumptions and outperform the other methods but they are computationally more expensive.

Design of high energy laser pulse delivery in a multimode fiber for photoacoustic tomography

In photoacoustic tomography (PAT), delivering high energy pulses through optical fiber is critical for achieving high quality imaging. A fiber coupling scheme with a beam homogenizer is demonstrated for coupling high energy pulses in a single multimode fiber. This scheme can benefit PAT applications that require miniaturized illumination or internal illumination with a small fiber. The beam homogenizer is achieved by using a cross cylindrical lens array, which provides a periodic spatial modulation on the phase of the input light. Thus the lens array acts as a phase grating which diffracts the beam into a 2D diffraction pattern. Both theoretical analysis and experiments demonstrate that the focused beam can be split into a 2D spot array that can reduce the peak power on the fiber tip surface and thus enhance the coupling performance. The theoretical analysis of the intensity distribution of the focused beam is carried out by Fourier optics. In experiments, coupled energy at 48 mJ/pulse and 60 mJ/pulse have been achieved and the corresponding coupling efficiency is 70% and 90% in a 1000-μm and a 1500-μm-core-diameter fiber, respectively. The high energy pulses delivered by the multimode fiber are further tested for PAT imaging in phantoms. PAT imaging of a printed dot array shows a large illumination area of 7 cm² under 5 mm thick chicken breast tissue. In vivo imaging is also demonstrated on the human forearm. The large improvement in coupling energy can potentially benefit PAT with single fiber delivery to achieve large area imaging and deep penetration detection.

Novel 3D ultrasound system for midline single-operator epidurals: a feasibility study on a porcine model

BACKGROUND

We developed a real-time 3D ultrasound thick slice rendering technique and innovative Epiguide needle-guide as an adjunct to single-operator midline epidural needle insertions. Study goals were to determine feasibility of the technique in a porcine model and compare the visibility of standard and echogenic needles.

METHODS

Thirty-four lumbar needle insertions were performed on six intact porcine spines ex vivo. Ultrasound scanning identified the insertion site and, using an Epiguide, the needle was guided into the epidural space through the ligamentum flavum in the midline plane, watched in real-time on the 3D ultrasound. Entry into the epidural space was judged by a loss-of-resistance technique. Needle visibility was rated by the anesthesiologist performing the technique using a 4-point scale; (0=cannot see, 1=poor, 2=satisfactory, 3=excellent), and later by an independent assessor viewing screenshots. The procedure was repeated at all lumbar levels using either the standard or echogenic needle.

RESULTS

Successful loss-of-resistance to fluid was achieved in 76% of needle insertions; needle visibility with echogenic needles (94.2% rated satisfactory/excellent) was significantly better than with standard needles (29.4% satisfactory/excellent, P<0.0001). Successful loss-of-resistance was 93% when mean needle visibility was rated as 'excellent'. Inter-observer agreement between assessors was 'near-perfect' (weighted kappa=0.83).

CONCLUSION

It is feasible to perform 3D ultrasound-guided real-time single-operator midline epidural insertions, in a porcine model. Echogenic needles were found to consistently improve needle visibility; and improved needle visibility tended to increase successful entry into epidural space.

Detection of an invisible needle in ultrasound using a probabilistic SVM and time-domain features

We propose a novel learning-based approach to detect an imperceptible hand-held needle in ultrasound images using the natural tremor motion. The minute tremor induced on the needle however is also transferred to the tissue in contact with the needle, making the accurate needle detection a challenging task. The proposed learning-based framework is based on temporal analysis of the phase variations of pixels to classify them according to the motion characteristics. In addition to the classification, we also obtain a probability map of the segmented pixels by cross-validation. A Hough transform is then used on the probability map to localize the needle using the segmented needle and posterior probability estimate. The two-step probability-weighted localization on the segmented needle in a learning framework is the key innovation which results in localization improvement and adaptability to specific clinical applications. The method was tested in vivo for a standard 17 gauge needle inserted at 50-80° insertion angles and 40-60mm depths. The results showed an average accuracy of (2.12°, 1.69mm) and 81%±4% for localization and classification, respectively.

CASPER: computer-aided segmentation of imperceptible motion-a learning-based tracking of an invisible needle in ultrasound

PURPOSE

This paper presents a new micro-motion-based approach to track a needle in ultrasound images captured by a handheld transducer.

METHODS

We propose a novel learning-based framework to track a handheld needle by detecting microscale variations of motion dynamics over time. The current state of the art on using motion analysis for needle detection uses absolute motion and hence work well only when the transducer is static. We have introduced and evaluated novel spatiotemporal and spectral features, obtained from the phase image, in a self-supervised tracking framework to improve the detection accuracy in the subsequent frames using incremental training. Our proposed tracking method involves volumetric feature selection and differential flow analysis to incorporate the neighboring pixels and mitigate the effects of the subtle tremor motion of a handheld transducer. To evaluate the detection accuracy, the method is tested on porcine tissue in-vivo, during the needle insertion in the biceps femoris muscle.

RESULTS

Experimental results show the mean, standard deviation and root-mean-square errors of [Formula: see text], [Formula: see text] and [Formula: see text] in the insertion angle, and 0.82, 1.21, 1.47 mm, in the needle tip, respectively.

CONCLUSIONS

Compared to the appearance-based detection approaches, the proposed method is especially suitable for needles with ultrasonic characteristics that are imperceptible in the static image and to the naked eye.

Automatic Quality Assessment of Echocardiograms Using Convolutional Neural Networks: Feasibility on the Apical Four-Chamber View

Echocardiography (echo) is a skilled technical procedure that depends on the experience of the operator. The aim of this paper is to reduce user variability in data acquisition by automatically computing a score of echo quality for operator feedback. To do this, a deep convolutional neural network model, trained on a large set of samples, was developed for scoring apical four-chamber (A4C) echo. In this paper, 6,916 end-systolic echo images were manually studied by an expert cardiologist and were assigned a score between 0 (not acceptable) and 5 (excellent). The images were divided into two independent training-validation and test sets. The network architecture and its parameters were based on the stochastic approach of the particle swarm optimization on the training-validation data. The mean absolute error between the scores from the ultimately trained model and the expert's manual scores was 0.71 ± 0.58. The reported error was comparable to the measured intra-rater reliability. The learned features of the network were visually interpretable and could be mapped to the anatomy of the heart in the A4C echo, giving confidence in the training result. The computation time for the proposed network architecture, running on a graphics processing unit, was less than 10 ms per frame, sufficient for real-time deployment. The proposed approach has the potential to facilitate the widespread use of echo at the point-of-care and enable early and timely diagnosis and treatment. Finally, the approach did not use any specific assumptions about the A4C echo, so it could be generalizable to other standard echo views.

SWAVE Imaging of Placental Elasticity and Viscosity: Proof of Concept

The placenta is the interface between the fetus and the mother and is vital for fetal development. Ultrasound elastography provides a non-invasive way to examine in vivo the stiffness of the placenta; increased stiffness has previously been linked to fetal growth restriction. This study used a previously developed dynamic elastography method, called shear wave absolute vibro-elastography, to study 61 post-delivery clinically normal placentas. The shear wave speeds in the placenta were recorded under five different low-frequency mechanical excitations. The elasticity and viscosity were estimated through rheological modeling. The shear wave speeds at excitation frequencies of 60, 80, 90, 100 and 120 Hz were measured to be 1.23 ± 0.44, 1.67 ± 0.76, 1.74 ± 0.72, 1.80 ± 0.78 and 2.25 ± 0.80 m/s. The shear wave speed values we obtained are consistent with previous studies. In addition, our multi-frequency acquisition approach enables us to provide viscosity estimates that have not been previously reported.

DeepInfer: Open-Source Deep Learning Deployment Toolkit for Image-Guided Therapy

Deep learning models have outperformed some of the previous state-of-the-art approaches in medical image analysis. Instead of using hand-engineered features, deep models attempt to automatically extract hierarchical representations at multiple levels of abstraction from the data. Therefore, deep models are usually considered to be more flexible and robust solutions for image analysis problems compared to conventional computer vision models. They have demonstrated significant improvements in computer-aided diagnosis and automatic medical image analysis applied to such tasks as image segmentation, classification and registration. However, deploying deep learning models often has a steep learning curve and requires detailed knowledge of various software packages. Thus, many deep models have not been integrated into the clinical research workflows causing a gap between the state-of-the-art machine learning in medical applications and evaluation in clinical research procedures. In this paper, we propose "DeepInfer" - an open-source toolkit for developing and deploying deep learning models within the 3D Slicer medical image analysis platform. Utilizing a repository of task-specific models, DeepInfer allows clinical researchers and biomedical engineers to deploy a trained model selected from the public registry, and apply it to new data without the need for software development or configuration. As two practical use cases, we demonstrate the application of DeepInfer in prostate segmentation for targeted MRI-guided biopsy and identification of the target plane in 3D ultrasound for spinal injections.

Three-Dimensional Ultrasound-Guided Real-Time Midline Epidural Needle Placement with Epiguide: A Prospective Feasibility Study

Current 2-D ultrasound technology is unable to perform a midline neuraxial needle insertion under real-time ultrasound guidance using a standard needle and without an assistant. The aim of the work described here was to determine the feasibility of a new technology providing such capability, starting with a study evaluating the selected puncture site. A novel 3-D ultrasound imaging technique was designed using thick-slice rendering in conjunction with a custom needle guide (3DUS + Epiguide). A clinical feasibility study evaluated the ability of 3DUS + Epiguide to identify the epidural needle puncture site for a midline insertion in the lumbar spine. We hypothesized that (i) the puncture site identified by 3DUS + Epiguide was within a 5-mm radius from the site chosen by standard palpation, and (ii) the difference between the two puncture sites was not correlated to the patient characteristics age, weight, height, body mass index and gestational age. The mean (±standard deviation) distances between puncture sites determined by 3DUS + Epiguide and palpation were 3.1 (±1.7) mm and 2.8 (±1.3) mm, for the L2-3 and L3-4 interspaces of 20 patients, respectively. Distances were comparable to intra-observer variability, indicating the potential for a thick-slice rendering of 3-D ultrasound along the Epiguide trajectory to select the puncture site of a midline neuraxial needle insertion. The long-term potential benefits of this system include increased efficiency and use of anesthesia, and a reduction in the frequency and severity of the complications from incorrect needle insertions. Epidural success in the most difficult cases (e.g., the obese) will be the focus of future work.