Medical Ultrasound Imaging Research Articles

Target Classification in Synthetic Aperture Radar Images Using Quantized Wavelet Scattering Networks.

The need to classify targets and features in high-resolution imagery is of interest in applications such as detection of landmines in ground penetrating radar and tumors in medical ultrasound images. Convolutional neural networks (CNNs) trained using extensive datasets are being investigated recently. However, large CNNs and wavelet scattering networks (WSNs), which share similar properties, have extensive memory requirements and are not readily extendable to other datasets and architectures—and especially in the context of adaptive and online learning. In this paper, we quantitatively study several quantization schemes on WSNs designed for target classification using X-band synthetic aperture radar (SAR) data and investigate their robustness to low signal-to-noise ratio (SNR) levels. A detailed study was conducted on the tradeoffs involved between the various quantization schemes and the means of maximizing classification performance for each case. Thus, the WSN-based quantization studies performed in this investigation provide a good benchmark and important guidance for the design of quantized neural networks architectures for target classification.

Laplacian pyramid based non-linear coherence diffusion for real-time ultrasound image speckle reduction

The inherent speckle noise in medical ultrasound image degrades valuable clinical information and affects the diagnosis quality. Therefore, commercial ultrasound systems always face a big challenge to improve the visual quality of ultrasound images by reducing the speckle noise. A new hybrid algorithm is proposed in the present paper for speckle reduction by combining nonlinear coherence diffusion (NCD) with pyramid-transform-based multi-scale filters (named as Laplacian Pyramid Based Non-linear Coherence Diffusion; viz. LPNCD). The new approach exhibits good capability in preserving tissue features while enhancing the coherence. The theory and implementation of the approach are presented and verified based on phantom and clinical data. By comparing with previous techniques on quantified signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR), the results suggest that the LPNCD method may demonstrate superior performance than other commonly used AD-class filters. Meanwhile, the performance of GPU implementations of the current technique is also evaluated, and it is verified that the LPNCD approach may have good performance efficiency and wonderful visual effect as running on mainstream commercial ultrasound systems.

Broadband acoustic metamaterial for the design of an asymmetric focusing lens with single-mode output

Acoustic asymmetric focusing (AAF) can increase the intensity of acoustic energy in a region with one direction, which may greatly benefit medical ultrasound imaging. However, its shortcoming is the narrow bandwidth of the frequency, which severely constrains the application of the AAF lens. In this paper, we propose a broad bandwidth AAF lens based on an asymmetric transmission metamaterial supercell with single-mode output composed of three types of phased unit cells and a wave-guide material. The supercell can realize the asymmetric transmission and the conversion of even-mode to odd-mode simultaneously, due to the phase modulation offered by the phased unit cell and the even-mode band gap of the wave-guide. We design the AAF lens with high performance based on 14 supercells, which demonstrate a long diameter focusing region of 1.56 and short diameter of 0.27 and the broad bandwidth focusing from 3.1 kHz to 4.73 kHz. The proposed AAF lens based on the metamaterial supercells with single-mode output has broad application prospects in the design of asymmetric sound focusing devices with multi-functional capability.

Motion blur invariant for estimating motion parameters of medical ultrasound images

High-quality medical ultrasound imaging is definitely concerning motion blur, while medical image analysis requires motionless and accurate data acquired by sonographers. The main idea of this paper is to establish some motion blur invariant in both frequency and moment domain to estimate the motion parameters of ultrasound images. We propose a discrete model of point spread function of motion blur convolution based on the Dirac delta function to simplify the analysis of motion invariant in frequency and moment domain. This model paves the way for estimating the motion angle and length in terms of the proposed invariant features. In this research, the performance of the proposed schemes is compared with other state-of-the-art existing methods of image deblurring. The experimental study performs using fetal phantom images and clinical fetal ultrasound images as well as breast scans. Moreover, to validate the accuracy of the proposed experimental framework, we apply two image quality assessment methods as no-reference and full-reference to show the robustness of the proposed algorithms compared to the well-known approaches.

Fourier-based Synthetic-aperture Imaging for Arbitrary Transmissions by Cross-correlation of Transmitted and Received Wave-fields.

Investigations into Fourier beamforming for medical ultrasound imaging have largely been limited to plane-wave and single-element transmissions. The main aim of this work is to generalize Fourier beamforming to enable synthetic aperture imaging with arbitrary transmit sequences. When applied to focused transmit beams, the proposed approach yields a full-waveform-based alternative to virtual-source synthetic aperture, which has implications for both coherence imaging and sound speed estimation. When compared to virtual-source synthetic aperture and retrospective encoding for conventional ultrasound sequences (REFoCUS), the proposed imaging technique shows an 8.6 and 3.8 dB improvement in contrast over virtual source synthetic aperture and REFoCUS, respectively, and a 55% improvement in point target resolution over virtual source synthetic aperture. The proposed image reconstruction technique also demonstrates general imaging improvements in vivo, while avoiding limitations seen in prior techniques.

An efficient transfer learning-based Super-Resolution model for Medical Ultrasound Image

There are many imaging modalities for clinical diagnosis, but we heavily use ultrasound imaging; some of the ultrasound images are low resolution because of the body’s internal weakness. This paper presents a novel unsupervised super-resolution framework for ultrasound image enhancement without considering any large sets of training samples which is the major concern in many single image super-resolution techniques. Here, the most powerful nonlinear mapping is introduced within convolutional neural networks to restore potentially useful and prominent spatial information generated from the model sets considered for image enhancements. Here, two techniques are used: dilated convolution and residual learning to increase the convergence and reconstruction accuracy in terms of quality measures. The potential metrics of dilated convolution in extract spatial information and residual learning are used to narrow the convergence time by learning only the difference between the test input and distorted input image. By evaluating the proposed framework on real ultrasound image sets, the performance metrics are validated. The proposed model outperformed the other competitive image enhancement models in the USSR field.

CNN-Based Medical Ultrasound Image Quality Assessment

The quality of ultrasound image is a key information in medical related application. It is also an important index in evaluating the performance of ultrasonic imaging equipment and image processing algorithms. Yet, there is still no recognized quantitative standard about medical image quality assessment (IQA) due to the fact that IQA is traditionally regarded as a subjective issue, especially in case of the ultrasound medical images. As such, the medical ultrasound IQA on basis of convolutional neural network (CNN) is quantitatively studied in this paper. Firstly, a dataset with 1063 ultrasound images is established through degenerating a certain number of original high-quality images. Subsequently, some operations are performed for the dataset including scoring and abnormal value screening. Then, 478 ultrasonic images are selected as the training and testing examples. The label of each example is obtained by averaging the scores of different doctors. Afterwards, a deep CNN network and a residuals network are taken to establish the IQA models. Meanwhile, the transfer learning strategy is introduced here to accelerate the training and improve the robustness of the model considering the fact that the ultrasound image samples are not abundant. At last, some tests are taken to evaluate the IQA models. They show that the CNN-based IQA is feasible and effective.

Ultrasound Medical Images Classification Based on Deep Learning Algorithms: A Review

Ultrasound Medical Images Classification Based on Deep Learning Algorithms: A Review

Research on optimization sparse method for capacitive micromachined ultrasonic transducer array: heuristic algorithm

PurposeBecause of the small size and high integration of capacitive micromachined ultrasonic transducer (CMUT) component, it can be made into large-scale array, but this lead to high hardware complexity, so the purpose of this paper is to use less elements to achieve better imaging results. In this research, an optimized sparse array is studied, which can suppress the side lobe and reduce the imaging artifacts compared with the equispaced sparse array with the same number of elements.Design/methodology/approachGenetic algorithm is used to sparse the CMUT linear array, and Kaiser window apodization is added to reduce imaging artifacts, the beam pattern and peak-to-side lobe ratio are calculated, point targets imaging comparisons are performed. Furthermore, a 256-elements CMUT linear array is used to carry out the imaging experiment of embedded mass and forearm blood vessel, and the imaging results are compared quantitatively.FindingsThrough the imaging comparison of embedded mass and forearm blood vessel, the feasibility of optimized sparse array of CMUT is verified, and the purpose of reducing the hardware complexity is achieved.Originality/valueThis research provides a basis for the large-scale CMUT array to reduce the hardware complexity and the amount of calculation. At present, the CMUT array has been used in medical ultrasound imaging and has huge market potential.

Design of a 128‐channel transceiver hardware for medical ultrasound imaging systems

In this work, the design and development of a 128-channel transceiver hardware for medical ultrasound imaging systems and research is presented. The proposed hardware solution integrates the analog front-end (AFE) sections, high voltage transmit pulser sections, field programmable gate array (FPGA)-based transmit beamforming and control logic, time gain compensation (TGC) and continuous (CW) Doppler functional circuits, and the necessary power supplies (high voltage (HV) and low voltage (LV)) into a single board. In addition, it integrates pervasive segments like power, clock tree sections, and power management and debugger logic. The developed transceiver solution helps to advance the research in medical ultrasound imaging techniques and technologies. To prototype an ultrasound imaging system, the developed hardware can be interfaced with a 128-channel ultrasound transducer array and an FPGA-based signal processing module. As the transceiver hardware is designed with commercially available chipsets, it provides the flexibility to programme the ultrasound AFE signal chain, transmit beamforming and the arbitrary transmit wave pattern. Besides, compared to the commercial open ultrasound research scanners, the flexibility to interface FPGA-based signal processing module helps to investigate the performance of hardware realisation of various ultrasound signal processing algorithms. Moreover, the work realises a single-board transceiver solution for multichannel ultrasound system fulfilment.

Fusion of medical images based on salient features extraction by PSO optimized fuzzy logic in NSST domain

The aim of multimodal medical image fusion is to extract information from different modal images into a single one so that the single fusion image contains the salient features of the source images to the maximum extent. Different medical imaging modalities such as CT and MRI are presented as different visual morphology, which often show different complementary salient features in clinical diagnosis. According to this characteristic, in order to fuse different salient features of multimodal medical images into a single image and provide a new dimension of information for clinical diagnosis to improve the diagnosis accuracy, an improved image fusion algorithm based on visual salience detection is proposed in this paper. The visual salience of two registered source images is calculated by the GBVS algorithm, and the low-frequency and high-frequency sub-bands are obtained by decomposing the source images in NSST domain. For the low-frequency sub-bands, fuzzy logic system is used to obtain the respective weights of the fused low-frequency sub-band with the local energy and GBVS graph as input. For the high-frequency sub-bands, the NSML values of each sub-band are calculated and compared to obtain the fused high-frequency sub-band. The final fused image is obtained by the inverse NSST transformation. In addition, PSO algorithm is used to optimize the membership function of fuzzy logic system for better adaption to medical images and feature extraction. By applying this multimodal medical image fusion method, the visual quality of the image is effectively improved and the salient features of tissues are preserved well. Experiments on fusion of grayscale, color and ultrasound multimodal medical images show that the proposed method has advantages on retention of image salient features. Compared with other models, the fused image obtained by the proposed method has higher objective indexes with clearer edge contour, higher overall contrast, and no ringing effect and artifacts.

An Efficient Parallel Architecture for Sub Band Processor in Broad Band MVDR Beamformer for Medical Ultrasound Applications

Minimum Variance Distortion less Response (MVDR) algorithm is the key adaptive beamforming algorithm in high resolution Medical Ultrasound Imaging systems. MVDR Beamformer is a frequency domain beamformer, and each frequency sub band need to be processed to generate covariance matrix and the same is computationally costly. Though many VLSI architectures have been proposed for MVDR Beamformer, currently no Complex Correlation matrix generation architecture for frequency sub band has been devised which supports real time implementation of broad band MVDR Beamformer for Medical Ultrasound Imaging. In this paper we show real time MVDR sub array, sub band processor realization for an array with number of elements N=32 and sub array length L=8. To satisfy the narrow band condition of the array we employed 1K point FFT, with 12.5 % overlap. The entire design of MVDR Sub band processor is tested on the Field Programmable Gate Array (FPGA) platform. The implementation results show that the through put of the developed architecture is 600K Complex Correlation matrix generation per second which is equivalent to 65.57 fps to image a 20cm depth target at a Pulse Repetition Frequency (PRF) of 4 KHz, 600 Field of View and 10 lateral resolution and makes the MVDR a viable solution for practical systems.

Joint Detection of Tap and CEA Based on Deep Learning Medical Image Segmentation: Risk Prediction of Thyroid Cancer.

In recent years, the incidence of thyroid nodules has shown an increasing trend year by year and has become one of the important diseases that endanger human health. Ultrasound medical images based on deep learning are widely used in clinical diagnosis due to their cheapness, no radiation, and low cost. The use of image processing technology to accurately segment the nodule area provides important auxiliary information for the doctor's diagnosis, which is of great value for guiding clinical treatment. The purpose of this article is to explore the application value of combined detection of abnormal sugar-chain glycoprotein (TAP) and carcinoembryonic antigen (CEA) in the risk estimation of thyroid cancer in patients with thyroid nodules of type IV and above based on deep learning medical images. In this paper, ultrasound thyroid images are used as the research content, and the active contour level set method is used as the segmentation basis, and a segmentation algorithm for thyroid nodules is proposed. This paper takes ultrasound thyroid images as the research content, uses the active contour level set method as the basis of segmentation, and proposes an image segmentation algorithm Fast-SegNet based on deep learning, which extends the network model that was mainly used for thyroid medical image segmentation to more scenarios of the segmentation task. From January 2019 to October 2020, 400 patients with thyroid nodules of type IV and above were selected for physical examination and screening at the Health Management Center of our hospital, and they were diagnosed as thyroid cancer by pathological examination of thyroid nodules under B-ultrasound positioning. The detection rates of thyroid cancer in patients with thyroid nodules of type IV and above are compared; serum TAP and CEA levels are detected; PT-PCR is used to detect TTF-1, PTEN, and NIS expression; the detection, missed diagnosis, misdiagnosis rate, and diagnostic efficiency of the three detection methods are compared. This article uses the thyroid nodule region segmented based on deep learning medical images and compares experiments with CV model, LBF model, and DRLSE model. The experimental results show that the segmentation overlap rate of this method is as high as 98.4%, indicating that the algorithm proposed in this paper can more accurately extract the thyroid nodule area.

Medical Images Breast Cancer Segmentation Based on K-Means Clustering Algorithm: A Review

Early diagnosis is considered important for medical images of breast cancer, the rate of recovery and safety of affected women can be improved. It is also assisting doctors in their daily work by creating algorithms and software to analyze the medical images that can identify early signs of breast cancer. This review presents a comparison has been done in term of accuracy among many techniques used for detecting breast cancer in medical images. Furthermore, this work describes the imaging process, and analyze the advantages and disadvantages of the used techniques for mammography and ultrasound medical images. K-means clustering algorithm has been specifically used to analyze the medical image along with other techniques. The results of the K-means clustering algorithm are discussed and evaluated to show the capacity of this technique in the diagnosis of breast cancer and its reliability to identify a malignant from a benign tumor.

Optimized integrated design of a high-frequency medical ultrasound transducer with genetic algorithm

Designing efficient acoustic stack and elements for high-frequency (HF) medical ultrasound (US) transducers involves various interrelated parameters. So far, optimizing spatial resolution and acoustic field intensity simultaneously has been a daunting task in the area of HF medical US imaging. Here, we introduce optimized design for a 50-MHz US probe for skin tissue imaging. We have developed an efficient design and simulation approach using Krimholtz, Leedom and Matthaei (KLM) equivalent circuit model and spatial impulse response method by means of Field II software. These KLM model and Field II software are integrated, and a GA algorithm is used to optimize the design of the US transducer to obtain the best imaging performance. As a result, a 50-MHz single element probe is effectively optimized with 5 mm acoustic focal length, 72 upmu {text{m}} lateral, and 42 upmu {text{m}} axial imaging resolution, with an enhancement in imaging resolution over the conventionally designed and simulated probe by 10%. This work has the potential to benefit many applications that require a fast, high-resolution and strong US focus in skin imaging.

Selection on Golay complementary sequences in binary pulse compression for microbubble detection

In medical ultrasound imaging using microbubbles (MBs), the nonlinear echoes from the MBs are used for contrast-specific image construction. Techniques such as pulse inversion, amplitude modulation, and the combined method (PIAM) are employed to increase nonlinear components in the echoes. In addition, employment of pulse compression using binary-coded ultrasound can potentially increase the components. In the case of the nonlinear echo, however, a nonlinear sidelobe occurs around the compressed pulse (correlation peak), and nonlinear components for PIAM in the correlation peak are reduced. The shape of the nonlinear sidelobe and the nonlinear-component reduction in the correlation peak can be estimated from the binary codes used. In this study, the optimal binary codes for PIAM are determined from all patterns of 10, 16, and 20 bit Golay codes. Then, the performance of PIAM with pulse compression using each code is evaluated via computer simulations and experiments using the SonoVue MBs.

Noise level estimation for effective blind despeckling of medical ultrasound images

Despeckling of medical ultrasound images is an essential pre-processing step in automated diagnosis systems. The performance of certain image despeckling methods is dependent on the noise level of an input image. In the design of despeckling algorithms, the noise level is assumed to be known. Therefore, it is essential to estimate the noise level from input ultrasound image for effective blind despeckling. In this paper, a novel noise level estimation (NLE) technique is proposed to estimate the speckle (signal-dependent) noise level from the noisy ultrasound images. The presented NLE technique uses noise level aware features obtained from the high-pass filtered noisy image. The extracted features are then used to train the support vector regression (SVR) model. The proposed feature extraction technique followed by the SVR model results in accurate NLE. In order to ensure the effectiveness, the proposed NLE technique is incorporated and validated with the NLE-dependent state-of-the-art despeckling methods. The combination of state-of-the-art despeckling methods with the proposed NLE technique shows superior despeckling performance when compared to existing NLE techniques. In this work, block matching based despeckling method is recommended in combination with the proposed NLE technique for better despeckling performance in the ultrasound images. The experimental results demonstrate that the proposed NLE technique shows better performance than existing NLE techniques in terms of average absolute deviation and execution time.

Research on Ultrasonic Image Recognition Based on Optimization Immune Algorithm.

With the rapid development of science and technology, ultrasound has been paid more and more attention by people, and it is widely used in engineering, diagnosis, and detection. In this paper, an ultrasonic image recognition method based on immune algorithm is proposed for ultrasonic images, and its method is applied to medical ultrasound liver image recognition. Firstly, this paper grays out the ultrasound liver image and selects the region of interest of the image. Secondly, it extracts the feature based on spatial gray matrix independent matrix, spatial frequency decomposition, and fractal features. Then, the immune algorithm is used to classify and identify the normal liver, liver cirrhosis, and liver cancer ultrasound images. Finally, based on the deficiency of the immune algorithm, it is combined with the support vector machine to form an optimized immune algorithm, which improves the performance of ultrasonic liver image classification and recognition. The simulation shows that this paper can effectively classify the normal liver, liver cirrhosis, and liver cancer ultrasound images. Compared with the traditional immune algorithm, this paper combines the immune algorithm with the support vector machine, and the optimized immune algorithm can effectively improve the performance of ultrasonic liver image classification and recognition.

Experimental demonstration of a three-dimensional acoustic hyperlens for super-resolution imaging

Acoustic hyperlenses have recently attracted much attention for promising applications in various fields. Yet the experimental realization of an acoustic hyperlens working in a real three-dimensional (3D) world is still lacking. Here, we theoretically propose and experimentally demonstrate a 3D acoustic hyperlens capable of producing super-resolution imaging for broadband airborne sound. A simple nonresonant metamaterial is designed as a practical implementation that simultaneously ensures tessellation of the curved surface and deep-subwavelength resolution. We analyze the dispersion relationship of the designed metamaterial that converts the evanescent waves into radially propagating modes based on positive extreme anisotropy. The effectiveness of our mechanism is demonstrated both numerically and experimentally via the production of 3D magnifying super-resolution imaging of small objects containing subwavelength patterns within a broad frequency range. We envision the realization of a 3D acoustic hyperlens to offer possibilities for the design of acoustic super-resolution imaging devices and their application in diverse scenarios ranging from medical ultrasound imaging to noninvasive evaluation.

Acoustically-Stimulated Nanobubbles: Opportunities in Medical Ultrasound Imaging and Therapy

Medical ultrasound is one of the most widely used imaging modalities worldwide. Microbubbles, typically ~1–8 μm in diameter, are ultrasound contrast agents confined to the vasculature due to their size. Microbubbles have broadened the scope of medical ultrasound, permitting real-time imaging of the microvasculature for blood flow assessment, molecular imaging, and even non-invasive site-specific therapy. Recently, there has been increasing interest in developing submicron, “nanoscale” agents to extend the utility of medical ultrasound. In this review, we discuss the development of lipid-encapsulated, acoustically responsive, nanobubbles (~200–800 nm in diameter), a next-generation ultrasound contrast agent. First, medical ultrasound and bubble-based contrast agents are introduced, followed by the advantages of scaling down bubble size from an acoustic and biological viewpoint. Next, we present how lipid-encapsulated nanobubbles can be developed toward meeting clinically meaningful endpoints, from agent synthesis and characterization to in vivo considerations. Finally, future opportunities of nanobubbles for advanced applications in ultrasound diagnostic and therapeutic medicine are proposed.