SIMUS: An open-source simulator for medical ultrasound imaging. Part II: Comparison with four simulators

A deep learning phase-based solution in 2D echocardiography motion estimation

In this paper, we propose a new deep learning method based on Quaternion Wavelet Transform (QWT) phases of 2D echocardiographic sequences to estimate the motion and strain of myocardium. The proposed method considers intensity and phases gained from QWT as the inputs of customized PWC-Net structure, a high-performance deep network in motion estimation. We have trained and tested our proposed method performance using two realistic simulated B-mode echocardiographic sequences. We have evaluated our proposed method in terms of both geometrical and clinical indices. Our method achieved an average endpoint error of 0.06 mm per frame and 0.59 mm between End Diastole and End Systole on a simulated dataset. Correlation analysis between ground truth and the computed strain shows a correlation coefficient of 0.89, much better than the most efficient methods in the state-of-the-art 2D echocardiography motion estimation. The results show the superiority of our proposed method in both geometrical and clinical indices.

Dynamic Ultrasound Localization Microscopy Without ECG-Gating

OBJECTIVE

Dynamic Ultrasound Localization Microscopy (DULM) has first been developed for non-invasive Pulsatility measurements in the rodent brain. DULM relies on the localization and tracking of microbubbles (MBs) injected into the bloodstream, to obtain highly resolved velocity and density cine-loops. Previous DULM techniques required ECG-gating, limiting its application to specific datasets, and increasing acquisition time. The objective of this study is to eliminate the need for ECG-gating in DULM experiments by introducing a motion-matching method for time registration.

METHODS

We developed a motion-matching algorithm based on tissue Doppler that leverages the cyclic tissue motion within the brain. Tissue Doppler was estimated for each group of frames in the acquisitions, at multiple locations identified as local maxima in the skin above the skull. Subsequently, each group of frames was time-registered to a reference group by delaying it based on the maximum correlation value between their respective tissue Doppler signals. This synchronization ensured that each group of frames aligned with the brain tissue motion of the reference group, and consequently, with its cardiac cycle. As a result, velocities of MBs could be averaged to retrieve flow velocity variations over time.

RESULTS

Initially validated in ECG-gated acquisitions in a rat model (n = 1), the proposed method was successfully applied in a mice model in 2D (n = 3) and in a feline model in 3D (n = 1). Performing time-registration with the proposed motion-matching method or by using ECG-gating leads to similar results. For the first time, dynamic velocity and density cine-loops were extracted without the need for any information on the animal ECG, and complex dynamic markers such as the Pulsatility index were estimated.

CONCLUSION

Results suggest that DULM can be performed without external gating, enabling the use of DULM on any ULM dataset where enough MBs are detectable. Time registration by motion-matching represents a significant advancement in DULM techniques, making DULM more accessible by simplifying its experimental complexity.

Complex Residual Attention U-Net for Fast Ultrasound Imaging from a Single Plane-Wave Equivalent to Diverging Wave Imaging

Plane wave imaging persists as a focal point of research due to its high frame rate and low complexity. However, in spite of these advantages, its performance can be compromised by several factors such as noise, speckle, and artifacts that affect the image quality and resolution. In this paper, we propose an attention-based complex convolutional residual U-Net to reconstruct improved in-phase/quadrature complex data from a single insonification acquisition that matches diverging wave imaging. Our approach introduces an attention mechanism to the complex domain in conjunction with complex convolution to incorporate phase information and improve the image quality matching images obtained using coherent compounding imaging. To validate the effectiveness of this method, we trained our network on a simulated phased array dataset and evaluated it using in vitro and in vivo data. The experimental results show that our approach improved the ultrasound image quality by focusing the network's attention on critical aspects of the complex data to identify and separate different regions of interest from background noise.

SIMUS3: An open-source simulator for 3-D ultrasound imaging

BACKGROUND AND OBJECTIVE

Computational Ultrasound Imaging (CUI) has become increasingly popular in the medical ultrasound community, facilitated by free simulation software. These tools enable the design and exploration of transmit sequences, transducer arrays, and signal processing. We recently introduced SIMUS, a frequency-based ultrasound simulator within the open-source MUST toolbox, which offers numerical advantages and allows easy consideration of frequency-dependent factors. In response to the growing interest in simulating ultrasound imaging with 2-D matrix arrays, we present 3-D versions, PFIELD3 and SIMUS3.

METHOD

The linear acoustic equations driving these functions are described, with theoretical assumptions reviewed for user guidance.

RESULTS

Comparative analyses with Field II, using a 32×32 element 3-MHz matrix array, highlight the performance of PFIELD3 and SIMUS3 under various transmission conditions.

CONCLUSIONS

This work extends the capabilities of existing CUI tools and provides researchers with valuable resources for advanced ultrasound simulations.

Bioresorbable shape-adaptive structures for ultrasonic monitoring of deep-tissue homeostasis

Monitoring homeostasis is an essential aspect of obtaining pathophysiological insights for treating patients. Accurate, timely assessments of homeostatic dysregulation in deep tissues typically require expensive imaging techniques or invasive biopsies. We introduce a bioresorbable shape-adaptive materials structure that enables real-time monitoring of deep-tissue homeostasis using conventional ultrasound instruments. Collections of small bioresorbable metal disks distributed within thin, pH-responsive hydrogels, deployed by surgical implantation or syringe injection, allow ultrasound-based measurements of spatiotemporal changes in pH for early assessments of anastomotic leaks after gastrointestinal surgeries, and their bioresorption after a recovery period eliminates the need for surgical extraction. Demonstrations in small and large animal models illustrate capabilities in monitoring leakage from the small intestine, the stomach, and the pancreas.

Ultrasound image super-resolution reconstruction based on semi-supervised CycleGAN

In ultrasonic testing, diffraction artifacts generated around defects increase the challenge of quantitatively characterizing defects. In this paper, we propose a label-enhanced semi-supervised CycleGAN network model, referred to as LESS-CycleGAN, which is a conditional cycle generative adversarial network designed for accurately characterizing defect morphology in ultrasonic testing images. The proposed method introduces paired cross-domain image samples during model training to achieve a defect transformation between the ultrasound image domain and the morphology image domain, thereby eliminating artifacts. Furthermore, the method incorporates a novel authenticity loss function to ensure high-precision defect reconstruction capability. To validate the effectiveness and robustness of the model, we use simulated 2D images of defects and corresponding ultrasonic detection images as training and test sets, and an actual ultrasonic phased array image of a test block as the validation set to evaluate the model's application performance. The experimental results demonstrate that the proposed method is convenient and effective, achieving subwavelength-scale defect reconstruction with good robustness.

Efficient Stratified 3-D Scatterer Sampling for Freehand Ultrasound Simulation

Ultrasound image simulation is a well-explored field with the main objective of generating realistic synthetic images, further used as ground truth for computational imaging algorithms or for radiologists' training. Several ultrasound simulators are already available, most of them consisting in similar steps: 1) generate a collection of tissue mimicking individual scatterers with random spatial positions and random amplitudes; 2) model the ultrasound probe and the emission and reception schemes; and 3) generate the radio frequency (RF) signals resulting from the interaction between the scatterers and the propagating ultrasound waves. This article is focused on the first step. To ensure fully developed speckle, a few tens of scatterers by resolution cell are needed, demanding to handle high amounts of data (especially in 3-D) and resulting into important computational time. The objective of this work is to explore new scatterer spatial distributions, with application to multiple coherent 2-D slice simulations from 3-D volumes. More precisely, lazy evaluation of pseudorandom schemes proves them to be highly computationally efficient compared with uniform random distribution commonly used. We also propose an end-to-end method from the 3-D tissue volume to resulting ultrasound images using coherent and 3-D-aware scatterer generation and usage in a real-time context.

Think twice before f-numbering

In a 2021 paper, we delved into the details of delay-sum beamforming (DAS) in high-frame-rate ultrasound for medical imaging [1]. We also proposed a simple and fast method of determining an f-number, which is based on the directivity of the transducer elements. In their comment, Martin F. Schiffner and Georg Schmitz argue that we mistakenly link image quality enhancement to the reduction of measurement noise. They disapprove our proposed f-number, claiming it deteriorates the signal-to-noise ratio (SNR). Based on their previous work [2], they also highlight that the f-number should be derived from the grating lobe angles. In this reply, we explain their error in the SNR argument. We also illustrate the potential drawbacks of exclusively relying on grating lobes to establish an f-number with a DAS, suggesting that alternative approaches might be worthy of consideration.

Enabling strain imaging in realistic Eulerian ultrasound simulation methods

Cardiovascular strain imaging is continually improving due to ongoing advances in ultrasound acquisition and data processing techniques. The phantoms used for validation of new methods are often burdensome to make and lack flexibility to vary mechanical and acoustic properties. Simulations of US imaging provide an alternative with the required flexibility and ground truth strain data. However, the current Lagrangian US strain imaging models cannot simulate heterogeneous speed of sound distributions and higher-order scattering, which limits the realism of the simulations. More realistic Eulerian modelling techniques exist but have so far not been used for strain imaging. In this research, a novel sampling scheme was developed based on a band-limited interpolation of the medium, which enables accurate strain simulation in Eulerian methods. The scheme was validated in k-Wave using various numerical phantoms and by a comparison with Field II. The method allows for simulations with a large range in strain values and was accurate with errors smaller than -60 dB. Furthermore, an excellent agreement with the Fourier theory of US scattering was found. The ability to perform simulations with heterogeneous speed of sound distributions was demonstrated using a pulsating artery model. The developed sampling scheme contributes to more realistic strain imaging simulations, in which the effect of heterogenous acoustic properties can be taken into account.

Ultrafast Cardiac Imaging Using Deep Learning for Speckle-Tracking Echocardiography

High-quality ultrafast ultrasound imaging is based on coherent compounding from multiple transmissions of plane waves (PW) or diverging waves (DW). However, compounding results in reduced frame rate, as well as destructive interferences from high-velocity tissue motion if motion compensation (MoCo) is not considered. While many studies have recently shown the interest of deep learning for the reconstruction of high-quality static images from PW or DW, its ability to achieve such performance while maintaining the capability of tracking cardiac motion has yet to be assessed. In this article, we addressed such issue by deploying a complex-weighted convolutional neural network (CNN) for image reconstruction and a state-of-the-art speckle-tracking method. The evaluation of this approach was first performed by designing an adapted simulation framework, which provides specific reference data, i.e., high-quality, motion artifact-free cardiac images. The obtained results showed that, while using only three DWs as input, the CNN-based approach yielded an image quality and a motion accuracy equivalent to those obtained by compounding 31 DWs free of motion artifacts. The performance was then further evaluated on nonsimulated, experimental in vitro data, using a spinning disk phantom. This experiment demonstrated that our approach yielded high-quality image reconstruction and motion estimation, under a large range of velocities and outperforms a state-of-the-art MoCo-based approach at high velocities. Our method was finally assessed on in vivo datasets and showed consistent improvement in image quality and motion estimation compared to standard compounding. This demonstrates the feasibility and effectiveness of deep learning reconstruction for ultrafast speckle-tracking echocardiography.

A New Estimation Scheme for Improving the Performance of Shear Wave Elasticity Imaging

Shear wave velocity (SWV) reconstruction based on time-of-flight (TOF) is widely adopted to realize shear wave elasticity imaging (SWEI). It typically breaks down the reconstruction of a SWV image into many kernels and treats them independently. We hypothesized that information exchange among kernels improves the performance of SWEI. Therefore, we propose the approach of iterative re-weighted least squares based on inter-kernel communication (IKC-IRLS). We also hypothesized that time-to-peak (TTP) is superior to cross-correlation (CC) in visualizing small targets because TTP uses higher shear wave frequencies than CC. To examine the hypotheses, IKC-IRLS was combined with TTP data and compared with four established methods. The five methods were tested by imaging several small-size stiff targets (2.5, 4.0 and 6.4 mm in diameter) using different kernel sizes in the simulation and real experiments. The results indicate that the IKC-IRLS approach can mitigate speckle noise and is robust to TTP outliers. Consequently, the proposed method achieves the highest contrast-to-noise ratio and the lowest mean absolute percentage error of target in almost all tested cases.

Unsupervised domain adaptation method for segmenting cross-sectional CCA images

BACKGROUND AND OBJECTIVES

Automatic vessel segmentation in ultrasound is challenging due to the quality of the ultrasound images, which is affected by attenuation, high level of speckle noise and acoustic shadowing. Recently, deep convolutional neural networks are increasing in popularity due to their great performance on image segmentation problems, including vessel segmentation. Traditionally, large labeled datasets are required to train a network that achieves high performance, and is able to generalize well to different orientations, transducers and ultrasound scanners. However, these large datasets are rare, given that it is challenging and time-consuming to acquire and manually annotate in-vivo data.

METHODS

In this work, we present a model-based, unsupervised domain adaptation method that consists of two stages. In the first stage, the network is trained on simulated ultrasound images, which have an accurate ground truth. In the second stage, the network continues training on in-vivo data in an unsupervised way, therefore not requiring the data to be labelled. Rather than using an adversarial neural network, prior knowledge on the elliptical shape of the segmentation mask is used to detect unexpected outputs.

RESULTS

The segmentation performance was quantified using manually segmented images as ground truth. Due to the proposed domain adaptation method, the median Dice similarity coefficient increased from 0 to 0.951, outperforming a domain adversarial neural network (median Dice 0.922) and a state-of-the-art Star-Kalman algorithm that was specifically designed for this dataset (median Dice 0.942).

CONCLUSIONS

The results show that it is feasible to first train a neural network on simulated data, and then apply model-based domain adaptation to further improve segmentation performance by training on unlabeled in-vivo data. This overcomes the limitation of conventional deep learning approaches to require large amounts of manually labeled in-vivo data. Since the proposed domain adaptation method only requires prior knowledge on the shape of the segmentation mask, performance can be explored in various domains and applications in future research.

Full-volume three-component intraventricular vector flow mapping by triplane color Doppler

Objective. Intraventricular vector flow mapping (iVFM) is a velocimetric technique for retrieving two-dimensional velocity vector fields of blood flow in the left ventricular cavity. This method is based on conventional color Doppler imaging, which makes iVFM compatible with the clinical setting. We have generalized the iVFM for a three-dimensional reconstruction (3D-iVFM). Approach. 3D-iVFM is able to recover three-component velocity vector fields in a full intraventricular volume by using a clinical echocardiographic triplane mode. The 3D-iVFM problem was written in the spherical (radial, polar, azimuthal) coordinate system associated to the six half-planes produced by the triplane mode. As with the 2D version, the method is based on the mass conservation, and free-slip boundary conditions on the endocardial wall. These mechanical constraints were imposed in a least-squares minimization problem that was solved through the method of Lagrange multipliers. We validated 3D-iVFM in silico in a patient-specific CFD (computational fluid dynamics) model of cardiac flow and tested its clinical feasibility in vivo in patients and in one volunteer. Main results. The radial and polar components of the velocity were recovered satisfactorily in the CFD setup (correlation coefficients, r  = 0.99 and 0.78). The azimuthal components were estimated with larger errors ( r  = 0.57) as only six samples were available in this direction. In both in silico and in vivo investigations, the dynamics of the intraventricular vortex that forms during diastole was deciphered by 3D-iVFM. In particular, the CFD results showed that the mean vorticity can be estimated accurately by 3D-iVFM. Significance. Our results tend to indicate that 3D-iVFM could provide full-volume echocardiographic information on left intraventricular hemodynamics from the clinical modality of triplane color Doppler.