Synthetic Elastography Using B-Mode Ultrasound Through a Deep Fully Convolutional Neural Network

B-mode ultrasound to elastography synthesis using multiscale learning

Elastography is a promising diagnostic tool that measures the hardness of tissues, and it has been used in clinics for detecting lesion progress, such as benign and malignant tumors. However, due to the high cost of examination and limited availability of elastic ultrasound devices, elastography is not widely used in primary medical facilities in rural areas. To address this issue, a deep learning approach called the multiscale elastic image synthesis network (MEIS-Net) was proposed, which utilized the multiscale learning to synthesize elastic images from ultrasound data instead of traditional ultrasound elastography in virtue of elastic deformation. The method integrates multi-scale features of the prostate in an innovative way and enhances the elastic synthesis effect through a fusion module. The module obtains B-mode ultrasound and elastography feature maps, which are used to generate local and global elastic ultrasound images through their correspondence. Finally, the two-channel images are synthesized into output elastic images. To evaluate the approach, quantitative assessments and diagnostic tests were conducted, comparing the results of MEIS-Net with several deep learning-based methods. The experiments showed that MEIS-Net was effective in synthesizing elastic images from B-mode ultrasound data acquired from two different devices, with a structural similarity index of 0.74 ± 0.04. This outperformed other methods such as Pix2Pix (0.69 ± 0.09), CycleGAN (0.11 ± 0.27), and StarGANv2 (0.02 ± 0.01). Furthermore, the diagnostic tests demonstrated that the classification performance of the synthetic elastic image was comparable to that of real elastic images, with only a 3 % decrease in the area under the curve (AUC), indicating the clinical effectiveness of the proposed method.

TSE-GAN: strain elastography using generative adversarial network for thyroid disease diagnosis

Over the past 35 years, studies conducted worldwide have revealed a threefold increase in the incidence of thyroid cancer. Strain elastography is a new imaging technique to identify benign and malignant thyroid nodules due to its sensitivity to tissue stiffness. However, there are certain limitations of this technique, particularly in terms of standardization of the compression process, evaluation of results and several assumptions used in commercial strain elastography modes for the purpose of simplifying imaging analysis. In this work, we propose a novel conditional generative adversarial network (TSE-GAN) for automatically generating thyroid strain elastograms, which adopts a global-to-local architecture to improve the ability of extracting multi-scale features and develops an adaptive deformable U-net structure in the sub-generator to apply effective deformation. Furthermore, we introduce a Lab-based loss function to induce the networks to generate realistic thyroid elastograms that conform to the probability distribution of the target domain. Qualitative and quantitative assessments are conducted on a clinical dataset provided by Shanghai Sixth People's Hospital. Experimental results demonstrate that thyroid elastograms generated by the proposed TSE-GAN outperform state-of-the-art image translation methods in meeting the needs of clinical diagnostic applications and providing practical value.

Deep learning in ultrasound elastography imaging: A review

It is known that changes in the mechanical properties of tissues are associated with the onset and progression of certain diseases. Ultrasound elastography is a technique to characterize tissue stiffness using ultrasound imaging either by measuring tissue strain using quasi-static elastography or natural organ pulsation elastography, or by tracing a propagated shear wave induced by a source or a natural vibration using dynamic elastography. In recent years, deep learning has begun to emerge in ultrasound elastography research. In this review, several common deep learning frameworks in the computer vision community, such as multilayer perceptron, convolutional neural network, and recurrent neural network are described. Then, recent advances in ultrasound elastography using such deep learning techniques are revisited in terms of algorithm development and clinical diagnosis. Finally, the current challenges and future developments of deep learning in ultrasound elastography are prospected. This article is protected by copyright. All rights reserved.

Feasibility of a Deep Learning approach to estimate Shear Wave Speed using the framework of Reverberant Shear Wave Elastography: A numerical simulation study

Reverberant Shear Wave Elastography (RSWE) is an ultrasound elastography technique that offers great advantages, however, current estimators generate underestimations and time-consuming issues. As well, the involvement of Deep Learning into the medical imaging field with new tools to assess complex problems, makes it a great candidate to serve as a new approach for a RSWE estimator. This work addresses the application of a Deep Neural Network (DNN) for the estimation of Shear Wave Speed (SWS) maps from particle velocity using numerically simulated data. The architecture of the proposed network is based on a U-Net, which works with a custom loss function specifically adopted for the reconstruction task. Four DNNs were trained using four different databases: clean, noisy, acquired at variable frequency, and noisy and acquired at variable frequency data. After the training of the DNNs, the predicted SWS maps were evaluated based on different metrics related to segmentation, regression and similarity of images. The model for clean data showed better results with a Mean Absolute Error (MAE) of 0.011, Mean Square Error(MSE) of 0.001, modified Intersection over Union (mIoU) of 98.4%, Peak Signal to Noise Ratio (PSNR) of 32.925 and a Structural Similarity Index Measure (SSIM) of 0.99, for 250 (size of Testing Sets); while the other models delivered SSIM in the range of 0.87 to 0.96. It was concluded that noisy and clean data could be effectively handled by the model, while the other ones still need enhancement. Clinical Relevance- This work is focused on the application of a Deep Learning approach to accurately asses the Shear Wave Speed in numerical simulations of Reverberant Shear Wave Elastography approach. This novel estimator could be useful for future clinical experiments specially with real time applications to determine the status of living tissue such as detection of malignant or benign tumors located in breast cervix prostate or skin and in the diagnosis of other pathologies such us liver fibrosis.

AUE-Net: Automated Generation of Ultrasound Elastography Using Generative Adversarial Network

Problem: Ultrasonography is recommended as the first choice for evaluation of thyroid nodules, however, conventional ultrasound features may not be able to adequately predict malignancy. Ultrasound elastography, adjunct to conventional B-mode ultrasound, can effectively improve the diagnostic accuracy of thyroid nodules. However, this technology requires professional elastography equipment and experienced physicians. Aim: in the field of computational medicine, Generative Adversarial Networks (GANs) were proven to be a powerful tool for generating high-quality images. This work therefore utilizes GANs to generate ultrasound elastography images. Methods: this paper proposes a new automated generation method of ultrasound elastography (AUE-net) to generate elastography images from conventional ultrasound images. The AUE-net was based on the U-Net architecture and optimized by attention modules and feature residual blocks, which could improve the adaptability of feature extraction for nodules of different sizes. The additional color loss function was used to balance color distribution. In this network, we first attempted to extract the tissue features of the ultrasound image in the latent space, then converted the attributes by modeling the strain, and finally reconstructed them into the corresponding elastography image. Results: a total of 726 thyroid ultrasound elastography images with corresponding conventional images from 397 patients were obtained between 2019 and 2021 as the dataset (646 in training set and 80 in testing set). The mean rating accuracy of the AUE-net generated elastography images by ultrasound specialists was 84.38%. Compared with that of the existing models in the visual aspect, the presented model generated relatively higher quality elastography images. Conclusion: the AUE-net generated ultrasound elastography images showed natural appearance and retained tissue information. Accordingly, it seems that B-mode ultrasound harbors information that can link to tissue elasticity. This study may pave the way to generate ultrasound elastography images readily without the need for professional equipment.

ApodNet: Learning for High Frame Rate Synthetic Transmit Aperture Ultrasound Imaging

Two-way dynamic focusing in synthetic transmit aperture (STA) beamforming can benefit high-quality ultrasound imaging with higher lateral spatial resolution and contrast resolution. However, STA requires the complete dataset for beamforming in a relatively low frame rate and transmit power. This paper proposes a deep-learning architecture to achieve high frame rate STA imaging with two-way dynamic focusing. The network consists of an encoder and a joint decoder. The encoder trains a set of binary weights as the apodizations of the high-frame-rate plane wave transmissions. In this respect, we term our network ApodNet. The decoder can recover the complete dataset from the acquired channel data to achieve dynamic transmit focusing. We evaluate the proposed method by simulations at different levels of noise and in-vivo experiments on the human biceps brachii and common carotid artery. The experimental results demonstrate that ApodNet provides a promising strategy for high frame rate STA imaging, obtaining comparable lateral resolution and contrast resolution with four-times higher frame rate than conventional STA imaging in the in-vivo experiments. Particularly, ApodNet improves contrast resolution of the hypoechoic targets with much shorter computational time when compared with other high-frame-rate methods in both simulations and in-vivo experiments.

Enhanced complex local frequency elastography method for tumor viscoelastic shear modulus reconstruction

BACKGROUND AND OBJECTIVES

The Mayo Clinic provides a magnetic resonance (MR) elastography software named MRE Wave, which uses the conventional local frequency elastography (LFE) method. However, MRE Wave is unable to supply complex viscoelasticity maps for elastography. We sought to improve the local frequency estimation algorithm used in LFE, which we refer to as the Enhanced Complex Local Frequency Elastography (EC-LFE) algorithm.

METHODS

The proposed algorithm uses wave equations under the hypotheses of being linear, isotropic, and locally homogeneous. Two 2D simulation models were used to investigate the accuracy and sensitivity of the EC-LFE algorithm for detecting small tumors. The corresponding statistical parameters were the relative root mean square (RMS) error and contrast-to-noise ratio (CNR). EC-LFE was investigated with two different parameter sets, one with an optimally chosen parameter ξ (EC-LFE Adj, for short) and the other with ξ = 0 (EC-LFE0). We compared the MRE Wave and the EC-LFE using series signal-to-noise (SNR) wave data.

RESULTS

The elasticity RMS error of the MRE Wave software was about 1%, and that of the EC-LFE0 and EC-LFE Adj were about 0.2%. The elasticity standard deviation of the MRE Wave software was about 3% of the mean value, and those of the EC-LFE0 and EC-LFE Adj were about 1% of the mean value. The elasticity CNR value of EC-LFE0 reached 1.93 times that of the MRE Wave in the region of small tumors (less than 10-point sampling). The viscosity RMS errors of the EC-LFE0 could be less than 5%.

CONCLUSION

Compared to conventional methods, the EC-LFE was more accurate and sensitive for small tumor detection and exhibited higher noise immunity. The improved algorithm output more parameters and outperformed than the MRE Wave, thereby rendering them more suitable for clinical applications.

Technology trends and applications of deep learning in ultrasonography: image quality enhancement, diagnostic support, and improving workflow efficiency

In this review of the most recent applications of deep learning to ultrasound imaging, the architectures of deep learning networks are briefly explained for the medical imaging applications of classification, detection, segmentation, and generation. Ultrasonography applications for image processing and diagnosis are then reviewed and summarized, along with some representative imaging studies of the breast, thyroid, heart, kidney, liver, and fetal head. Efforts towards workflow enhancement are also reviewed, with an emphasis on view recognition, scanning guide, image quality assessment, and quantification and measurement. Finally some future prospects are presented regarding image quality enhancement, diagnostic support, and improvements in workflow efficiency, along with remarks on hurdles, benefits, and necessary collaborations.

Simultaneous Evalulation of Contrast Pulse Sequences for Super-Resolution Ultrasound Imaging - Preliminary In Vitro and In Vivo Results

Super-resolution ultrasound imaging (SR-US) has enabled a tenfold improvement in resolution of the microvasculature with clinical application in many disease processes such as cancer, diabetes and cardiovascular disease. Plane wave ultrasound (US) platforms in turn are capable of the very high frame rates needed to track microbubble (MB) contrast agents used in SR-US. Both B-mode US imaging and contrast enhanced US imaging (CEUS) have been effectively used in SR-US, with B-mode US having higher signal-to-noise ratio (SNR) and CEUS providing higher contrast-to-tissue ratio (CTR). Lengthy imaging time needed for SR-US to allow perfusion and MB detection is an impediment to clinical adoption. Both SNR and CTR improvements can enhance SR-US imaging by enhancing the detection of MBs thus reducing imaging time. This study simultaneously evaluated nonlinear contrast pulse sequences (CPS) employing different amplitude modulation (AM) and pulse inversion (PI) nonlinear CEUS imaging techniques as well as combinations of the two, (AMPI) with B-mode US imaging. The objective was to improve the detection rate of MB during SR-US. Imaging was performed in vitro and in vivo in the rat hind limb using a Vantage 256 research scanner (Verasonics Inc.). Comparisons of four CPS compositions with B-mode US imaging was made based on the number of MB detected and localized in SR-US images. The use of a PI nonlinear CEUS imaging strategy improved SR-US imaging by increasing the number of MB detected in a sequence of frames by an average of 28.3% and up to 52.6% over a B-mode US imaging strategy, which would decrease imaging time accordingly.