IEEE transactions on ultrasonics, ferroelectrics, and frequency control最新文献

Color Doppler echocardiography enables visualization of blood flow within the heart. However, the limited frame rate impedes the quantitative assessment of blood velocity throughout the cardiac cycle, thereby compromising a comprehensive analysis of ventricular filling. Concurrently, deep learning is demonstrating promising outcomes in post-processing of echocardiographic data for various applications. This work explores the use of deep learning models for intracardiac Doppler velocity estimation from a reduced number of filtered I/Q signals. We used a supervised learning approach by simulating patient-based cardiac color Doppler acquisitions and proposed data augmentation strategies to enlarge the training dataset. We implemented architectures based on convolutional neural networks. In particular, we focused on comparing the U-Net model and the recent ConvNeXt models, alongside assessing real-valued versus complex-valued representations. We found that both models outperformed the state-of-the-art autocorrelator method, effectively mitigating aliasing and noise. We did not observe significant differences between the use of real and complex data. Finally, we validated the models on in vitro and in vivo experiments. All models produced quantitatively comparable results to the baseline and were more robust to noise. ConvNeXt emerged as the sole model to achieve high-quality results on in vivo aliased samples. These results demonstrate the interest of supervised deep learning methods for Doppler velocity estimation from a reduced number of acquisitions.

Ultrasound Localization Microscopy (ULM), an emerging medical imaging technique, effectively resolves the classical trade-off between resolution and penetration inherent in traditional ultrasound imaging, opening up new avenues for noninvasive observation of the microvascular system. However, traditional microbubble tracking methods encounter various practical challenges. These methods typically entail multiple processing stages, including intricate steps like pairwise correlation and trajectory optimization, rendering real-time applications unfeasible. Furthermore, existing deep learning-based tracking techniques neglect the temporal aspects of microbubble motion, leading to ineffective modeling of their dynamic behavior. To address these limitations, this study introduces a novel approach called the Gated Recurrent Unit (GRU)-based Multitasking Temporal Neural Network (GRU-MT). GRU-MT is designed to simultaneously handle microbubble trajectory tracking and trajectory optimization tasks. Additionally, we enhance the nonlinear motion model initially proposed by Piepenbrock et al. to better encapsulate the nonlinear motion characteristics of microbubbles, thereby improving trajectory tracking accuracy. In this study, we perform a series of experiments involving network layer substitutions to systematically evaluate the performance of various temporal neural networks, including Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), GRU, Transformer, and its bidirectional counterparts, on the microbubble trajectory tracking task. Concurrently, the proposed method undergoes qualitative and quantitative comparisons with traditional microbubble tracking techniques. The experimental results demonstrate that GRU-MT exhibits superior nonlinear modeling capabilities and robustness, both in simulation and in vivo dataset. Additionally, it achieves reduced trajectory tracking errors in shorter time intervals, underscoring its potential for efficient microbubble trajectory tracking. Model code is open-sourced at https://github.com/zyt-Lib/GRU-MT.

Ultrasound elastography images which enable quantitative visualization of tissue stiffness can be reconstructed by solving an inverse problem. Classical model-based methods are usually formulated in terms of constrained optimization problems. To stabilize the elasticity reconstructions, regularization techniques such as Tikhonov method are used with the cost of promoting smoothness and blurriness in the reconstructed images. Thus, incorporating a suitable regularizer is essential for reducing the elasticity reconstruction artifacts while finding the most suitable one is challenging. In this work, we present a new statistical representation of the physical imaging model which incorporates effective signal-dependent colored noise modeling. Moreover, we develop a learning-based integrated statistical framework which combines a physical model with learning-based priors. We use a dataset of simulated phantoms with various elasticity distributions and geometric patterns to train a denoising regularizer as the learning-based prior. We use fixed-point approaches and variants of gradient descent for solving the integrated optimization task following learning-based plug-and-play (PnP) prior and regularization by denoising (RED) paradigms. Finally, we evaluate the performance of the proposed approaches in terms of relative mean square error (RMSE) with nearly 20% improvement for both piece-wise smooth simulated phantoms and experimental phantoms compared to the classical model-based methods and 12% improvement for both spatially-varying breast-mimicking simulated phantoms and an experimental breast phantom, demonstrating the potential clinical relevance of our work. Moreover, the qualitative comparisons of reconstructed images demonstrate the robust performance of the proposed methods even for complex elasticity structures that might be encountered in clinical settings.

Left ventricle (LV) segmentation of 2D echocardiography images is an essential step in the analysis of cardiac morphology and function and - more generally - diagnosis of cardiovascular diseases. Several deep learning (DL) algorithms have recently been proposed for the automatic segmentation of the LV, showing significant performance improvement over the traditional segmentation algorithms. However, unlike the traditional methods, prior information about the segmentation problem, e.g. anatomical shape information, is not usually incorporated for training the DL algorithms. This can degrade the generalization performance of the DL models on unseen images if their characteristics are somewhat different from those of the training images, e.g. low-quality testing images. In this study, a new shape-constrained deep convolutional neural network (CNN) - called BEAS-Net - is introduced for automatic LV segmentation. The BEAS-Net learns how to associate the image features, encoded by its convolutional layers, with anatomical shape-prior information derived by the B-spline explicit active surface (BEAS) algorithm to generate physiologically meaningful segmentation contours when dealing with artifactual or low-quality images. The performance of the proposed network was evaluated using three different in-vivo datasets and was compared a deep segmentation algorithm based on the U-Net model. Both networks yielded comparable results when tested on images of acceptable quality, but the BEAS-Net outperformed the benchmark DL model on artifactual and low-quality images.