Ultrasound Imaging Artifacts Research Articles

SPReCHD: Four-Chamber Semantic Parsing Network for Recognizing Fetal Congenital Heart Disease in Medical Metaverse.

Echocardiography is essential for evaluating cardiac anatomy and function during early recognition and screening for congenital heart disease (CHD), a widespread and complex congenital malformation. However, fetal CHD recognition still faces many difficulties due to instinctive fetal movements, artifacts in ultrasound images, and distinctive fetal cardiac structures. These factors hinder capturing robust and discriminative representations from ultrasound images, resulting in CHD's low prenatal detection rate. Hence, we propose a multi-scale gated axial-transformer network (MSGATNet) to capture fetal four-chamber semantic information. Then, we propose a SPReCHD: four-chamber semantic parsing network for recognizing fetal CHD in the clinical treatment of the medical metaverse, integrating MSGATNet to segment and locate four-chamber arbitrary contours, further capturing distinguished representations for the fetal heart. Comprehensive experiments indicate that our SPReCHD is sufficient in recognizing fetal CHD, achieving a precision of 95.92%, a recall of 94%, an accuracy of 95%, and a F1 score of 94.95% on the test set, dramatically improving the fetal CHD's prenatal detection rate.

A target region extraction method for ultrasound medical images based on improvedPRIDNetandUCTransNet

AbstractComputer‐aided diagnosis is pivotal in augmenting the diagnostic efficiency of ultrasound images. Nonetheless, the substantial presence of noise and artifacts in ultrasound images presents a challenge to the precise segmentation of the target region. To highlight and analyze the diagnostic information such as tissues, organs, and lesions in ultrasound medical images more accurately, a target region extraction method combining the improved PRIDNet and UCTransNet for ultrasound medical images is proposed. The method sequentially enhances and segments the target region of the image, thereby solving the problem of inconspicuous target region caused by noise and artifacts in ultrasound images. There are three key characteristics: (i) The feature extraction part of the enhancement network (improved PRIDNet) is redesigned for speckle noise to improve the network's ability to extract information and highlight the feature information of the target region in ultrasound images. (ii) The segmentation network with the addition of the underlying information on UCTransNet would effectively improves Channel‐wise Cross fusion Transformer (CCT) and decoder feature fusion capability. (iii) By combining the enhancement network with the segmentation network, we can further improve the segmentation accuracy of the target region in the presence of noise interference. The experiments conducted on both UFSU that we prepared and on some public datasets including BUSI, FHC, and CT2US have demonstrated that The proposed method attains MIoU, DSC, Acc, and HD of 96.34%, 98.12%, 99.35%, and 8.64 in CT2US, respectively. The method significantly surpasses those certain state‐of‐the‐art methods, demonstrating its potential to offer valuable guidance for clinical treatment. The code will be publicly released athttps://github.com/425877/Target-Region-Extraction-Method-for-Ultrasound-Medical-Images.

Development of an Automated Ultrasound Signal Indicator of Lung Interstitial Syndrome.

The number and distribution of lung ultrasound (LUS) imaging artifacts termed B-lines correlate with the presence of acute lung disease such as infection, acute respiratory distress syndrome (ARDS), and pulmonary edema. Detection and interpretation of B-lines require dedicated training and is machine and operator-dependent. The goal of this study was to identify radio frequency (RF) signal features associated with B-lines in a cohort of patients with cardiogenic pulmonary edema. A quantitative signal indicator could then be used in a single-element, non-imaging, wearable, automated lung ultrasound sensor (LUSS) for continuous hands-free monitoring of lung fluid. In this prospective study a 10-zone LUS exam was performed in 16 participants, including 12 patients admitted with acute cardiogenic pulmonary edema (mean age 60 ± 12 years) and 4 healthy controls (mean age 44 ± 21). Overall,160 individual LUS video clips were recorded. The LUS exams were performed with a phased array probe driven by an open-platform ultrasound system with simultaneous RF signal collection. RF data were analyzed offline for candidate B-line indicators based on signal amplitude, temporal variability, and frequency spectrum; blinded independent review of LUS images for the presence or absence of B-lines served as ground truth. Predictive performance of the signal indicators was determined with receiving operator characteristic (ROC) analysis with k-fold cross-validation. Two RF signal features-temporal variability of signal amplitude at large depths and at the pleural line-were strongly associated with B-line presence. The sensitivity and specificity of a combinatorial indicator were 93.2 and 58.5%, respectively, with cross-validated area under the ROC curve (AUC) of 0.91 (95% CI = 0.80-0.94). A combinatorial signal indicator for use with single-element non-imaging LUSS was developed to facilitate continuous monitoring of lung fluid in patients with respiratory illness.

Cross-image Dependency Modelling for Breast Ultrasound Segmentation.

We present a novel deep network (namely BUSSeg) equipped with both within- and cross-image long-range dependency modeling for automated lesions segmentation from breast ultrasound images, which is a quite daunting task due to (1) the large variation of breast lesions, (2) the ambiguous lesion boundaries, and (3) the existence of speckle noise and artifacts in ultrasound images. Our work is motivated by the fact that most existing methods only focus on modeling the within-image dependencies while neglecting the cross-image dependencies, which are essential for this task under limited training data and noise. We first propose a novel cross-image dependency module (CDM) with a cross-image contextual modeling scheme and a cross-image dependency loss (CDL) to capture more consistent feature expression and alleviate noise interference. Compared with existing cross-image methods, the proposed CDM has two merits. First, we utilize more complete spatial features instead of commonly used discrete pixel vectors to capture the semantic dependencies between images, mitigating the negative effects of speckle noise and making the acquired features more representative. Second, the proposed CDM includes both intra- and inter-class contextual modeling rather than just extracting homogeneous contextual dependencies. Furthermore, we develop a parallel bi-encoder architecture (PBA) to tame a Transformer and a convolutional neural network to enhance BUSSeg's capability in capturing within-image long-range dependencies and hence offer richer features for CDM. We conducted extensive experiments on two representative public breast ultrasound datasets, and the results demonstrate that the proposed BUSSeg consistently outperforms state-of-the-art approaches in most metrics.

Hybrid Techniques with Support Vector Machine for Improving Artifact Ultrasound Images

The most common artifacts in ultrasound (US) imaging are reverberation and comet-tail. These are multiple reflection echoing the interface that causing them, and result in ghost echoes in the ultrasound image. A method to reduce these unwanted artifacts using a Otsu thresholding to find region of interest (reflection echoes) and output applied to median filter to remove noise. The developed method significantly reduced the magnitude of the reverberation and comet-tail artifacts. Support Vector Machine (SVM) algorithm is most suitable for hyperplane differentiate. For that, we use image enhancement, extraction of feature, region of interest, Otsu thresholding, and finally classification image datasets to normal or abnormal image. Because of the machine’s training for both types of images, the machine can now predict whether a new image is an abnormal image or a normal image. As a result, it reduced medical work for many checkups and other things. Our proposed method shows the correct classification result by more than 89%.

Improved breast ultrasound tumor classification using dual-input CNN with GAP-guided attention loss.

Ultrasonography is a widely used medical imaging technique for detecting breast cancer. While manual diagnostic methods are subject to variability and time-consuming, computer-aided diagnostic (CAD) methods have proven to be more efficient. However, current CAD approaches neglect the impact of noise and artifacts on the accuracy of image analysis. To enhance the precision of breast ultrasound image analysis for identifying tissues, organs and lesions, we propose a novel approach for improved tumor classification through a dual-input model and global average pooling (GAP)-guided attention loss function. Our approach leverages a convolutional neural network with transformer architecture and modifies the single-input model for dual-input. This technique employs a fusion module and GAP operation-guided attention loss function simultaneously to supervise the extraction of effective features from the target region and mitigate the effect of information loss or redundancy on misclassification. Our proposed method has three key features: (i) ResNet and MobileViT are combined to enhance local and global information extraction. In addition, a dual-input channel is designed to include both attention images and original breast ultrasound images, mitigating the impact of noise and artifacts in ultrasound images. (ii) A fusion module and GAP operation-guided attention loss function are proposed to improve the fusion of dual-channel feature information, as well as supervise and constrain the weight of the attention mechanism on the fused focus region. (iii) Using the collected uterine fibroid ultrasound dataset to train ResNet18 and load the pre-trained weights, our experiments on the BUSI and BUSC public datasets demonstrate that the proposed method outperforms some state-of-the-art methods. The code will be publicly released at https://github.com/425877/Improved-Breast-Ultrasound-Tumor-Classification.

Evaluation of Fetal Head Circumference (HC) and Biparietal Diameter (BPD (Biparietal Diameter)) in Ultrasound Images Using Multi-Task Deep Convolutional Neural Network

Introduction: Ultrasound imaging is a standard examination during pregnancy that can measure specific biometric parameters towards prenatal diagnosis and estimating gestational age. Fetal head circumference (HC) is a significant factor in determining fetus growth and health. Methods: This paper proposes a multi-task deep convolutional neural network for automatic segmentation and estimation of HC (Fetal head circumference) ellipse by minimizing a compound cost function composed of segmentation dice score and MSE of ellipse parameters. Ultrasound-based fetal biometric measurements, such as head circumference (HC) and biparietal diameter (BPD (BIPARIETAL DIAMETER)), are commonly used to evaluate the gestational age and diagnose fetal central nervous system (CNS) pathology. Since manual measurements are operator-dependent and time-consuming, there have been numerous researches on automated methods. However, existing computerized methods still are not satisfactory in terms of accuracy and reliability, owing to difficulties in dealing with various artefacts in ultrasound images. Results: This paper focuses on fetal head biometry and develops a deep-learning-based method for estimating HC (Fetal head circumference) and BPD (BIPARIETAL DIAMETER) with a high degree of accuracy and reliability. Conclusion: The proposed method effectively identifies the head boundary by differentiating tissue image patterns concerning the ultrasound propagation direction. The proposed method was trained with 102 labelled data set and tested to 70 ultrasound images. We achieved a success rate of 92.31% for HC (Fetal head circumference) and BPD (BIPARIETAL DIAMETER) estimations and an accuracy of 87.14% for the plane acceptance check.

Annotation-guided encoder-decoder network for bone extraction in ultrasound-assisted orthopedic surgery

The patients and surgeons are usually exposed in massive ionizing radiation during fluoroscopy-based navigation orthopedic surgery. Comparatively, ultrasound-assisted orthopedic surgery could not only decrease the risk of radiation but also provide rich navigation information. However, due to the artifacts in ultrasound images, the extraction of bone structure from ultrasound sequences can be a particularly difficult task, which leads to some major challenges in ultrasound-assisted orthopedic navigation. In this paper, we propose an annotation-guided encoder-decoder network (AGN) to extract bone structure from the radiation-free ultrasound sequences. Specifically, the variability of the ultrasound probe's pose leads to the change of the ultrasound frame during the acquisition of ultrasound sequences. Therefore, a feature alignment module deployed in the AGN model is used to achieve reliable matching across ultrasound frames. Moreover, inspired by the interactive ultrasound analysis, where user annotated foreground information can help target extraction, our AGN model incorporates the annotation information obtained by Siamese networks. Experimental results validated that the AGN model not only produced better bone surface extraction than state-of-the-art methods (IOU: 0.92 versus. 0.88), but also achieved almost real-time extraction with the speed about 15 frames per second. In addition, the acquired bone surface further provided radiation-free 3D intraoperative bone structure for the intuitive navigation of orthopedic surgery.

Focal U-Net: A Focal Self-attention based U-Net for Breast Lesion Segmentation in Ultrasound Images.

Accurate breast lesion segmentation in ultrasound images helps radiologists to make exact diagnoses and treatments, which is important to increase the survival rate of breast cancer patients. Recently, deep learning-based methods have demonstrated remarkable results in breast lesion segmentation. However, the blurry breast lesion boundaries and noise artifacts in ultrasound images still limit the performance of the deep learning-based methods. In this paper, we propose a novel segmentation network equipped with a focal self-attention block for improving the performance of breast lesion segmentation. The focal self-attention block can incorporate fine-grained local and coarse-grained global information. The fine-grained local information is useful to enhance features of breast lesion boundaries, while the coarse-grained global information effectively reduces noise interference. To verify the performance of our network, we implement breast lesion segmentation on our collected dataset of 9836 ultrasound images. The results demonstrate that the focal self-attention block enhances features of breast lesion boundaries and improves the accuracy of breast lesion segmentation.

Mechanistic analysis of B-line formation in lung ultrasound

The number and distribution of lung ultrasound (LUS) imaging artifacts—B-lines—is correlated with the presence of lung interstitial syndrome such as viral infection and pulmonary edema. The detection and quantification of B-lines is machine and operator dependent, and the mechanisms for B-line formation are not fully understood. The goals of this work were to collect RF data during LUS exams in patients with pulmonary edema and to compare to the signals and corresponding images simulated numerically to elucidate the B-line formation process. Verasonics ultrasound engine (VUE) with a phased array probe (4.5 MHz) was used to perform standard 10-zone LUS in ten patients with confirmed pulmonary edema. The RF data corresponding to each B-mode image and a series of 35 plane wave acquisitions were collected for off-line analyses. Finite element modeling of LUS pulse propagation was performed in COMSOL with fluid-filled inclusions of variable sizes and shapes in air-like medium simulating edematous lung areas. The B-mode image resulting from the simulated RF signals was reconstructed using VUE beamforming. The B-lines similar to those observed experimentally formed in simulated images only under specific conditions of sizes and shapes of water-filled areas relatively to LUS imaging wavelength. [Work supported by NIH R01EB023910.]

Segmentation atrioventricular septal defect by using convolutional neural networks based on U-NET architecture

Congenital heart disease often occurs, especially in infants and fetuses. Fetal image is one of the issues that can be related to the segmentation process. The fetal heart is an important indicator in the process of structural segmentation and functional assessment of congenital heart disease. This study is very challenging due to the fetal heart has a relatively unclear structural anatomical appearance, especially in the artifacts in ultrasound images. There are several types of congenital heart disease that often occurs namely in septal defects it consists of the atrial septal defect, ventricular septal defect, and atrioventricular septal defect. The process of identifying the standard of the heart, especially the fetus, can be identified with a 2D ultrasound video in the initial steps to diagnose congenital heart disease. The process of diagnosis of fetal heart standards can be seen from a variety of spaces, i.e., 4 chamber views. In this study, the standard semantic segmentation process of the fetal heart is abnormal and normal in terms of the perspective of 4 chamber views. The validation evaluation results obtained in this study amounted to 99.79% pixel accuracy, mean iou 96.10%, mean accuracy 97.82%, precision 96.41% recall 95.72% and F1 score 96.02%.

Effects of Artifacts on the Diagnosis of Ultrasound Image

In ultrasound imaging, the artifact is the term that can be used to describe various parts of an image that doesnot accurately represent the anatomic structure within the subject being evaluated. The current study aimsto explain the foundation of understanding the artifacts in conventional ultrasound and Doppler techniquesto highlight the effect which may occur as a result of these artifacts. Artifact in ultrasound imaging can beclassified into three categories according to its cause, artifacts caused by the patient, by instrument, and byan operator. Recognition of artifacts is important as they can be considered as tissue composition indicators.Therefore, it helps in the diagnosis. The ability to recognize and correct potential ultrasound artifacts issignificant for image quality improvement and optimal patient care. The most frequent artifact is acousticshadowing that had been seen in 11 from 54 cases and the less frequent is blooming artifact that occurred inonly 1 case from selected cases.

A Double-Envelope Mitral Inflow Spectral Doppler Profile After MitraClip

A Double-Envelope Mitral Inflow Spectral Doppler Profile After MitraClip

Needle Tip Tracking in 2D Ultrasound Based on Improved Compressive Tracking and Adaptive Kalman Filter

Ultrasound (US) is commonly used in percutaneous needle procedures for real-time guidance. Accurate and robust automatic needle tracking is highly desirable to address the influence of noise and artifacts in US images. This letter presents a tracking approach which combines an improved compressive tracking (ICT) algorithm and a modified Sage-Husa adaptive Kalman filter (SHAKF) to achieve real-time needle tip tracking under 2D US. Estimated needle insertion velocity is used to improve the tracking performance while the high US pixel intensity of the needle tip is used to correct drift. A simplified SHAKF is then implemented to adaptively estimate the statistical characteristics of the noise in the compressive tracking results. An innovation threshold is proposed to improve the response speed of the filter while a normalized cross correlation based method is used to improve the tracking robustness. The proposed tracking approach has been evaluated in in-plane and out-of-plane motions under different insertion speeds and angles in both phantom and tissue experiments. Compared with the original compressive tracking, ICT+Kalman filter, and the template matching algorithm, our proposed approach demonstrates highly accurate tracking performance and high robustness in all cases.

Shadow Estimation for Ultrasound Images Using Auto-Encoding Structures and Synthetic Shadows

Acoustic shadows are common artifacts in medical ultrasound imaging. The shadows are caused by objects that reflect ultrasound such as bones, and they are shown as dark areas in ultrasound images. Detecting such shadows is crucial for assessing the quality of images. This will be a pre-processing for further image processing or recognition aiming computer-aided diagnosis. In this paper, we propose an auto-encoding structure that estimates the shadowed areas and their intensities. The model once splits an input image into an estimated shadow image and an estimated shadow-free image through its encoder and decoder. Then, it combines them to reconstruct the input. By generating plausible synthetic shadows based on relatively coarse domain-specific knowledge on ultrasound images, we can train the model using unlabeled data. If pixel-level labels of the shadows are available, we also utilize them in a semi-supervised fashion. By experiments on ultrasound images for fetal heart diagnosis, we show that our method achieved 0.720 in the DICE score and outperformed conventional image processing methods and a segmentation method based on deep neural networks. The capability of the proposed method on estimating the intensities of shadows and the shadow-free images is also indicated through the experiments.

Removal of manually induced artifacts in ultrasound images of thyroid nodules based on edge-connection and Criminisi image restoration algorithm

Background and ObjectiveThere are various artificial markers in ultrasound images of thyroid nodules, which have impact on subsequent processing and computer-aided diagnosis. The purpose of this study was to develop an approach to automatically remove artifacts and restore ultrasound images of thyroid nodules. MethodsFifty ultrasound images with manually induced artifacts were selected from publicly available and self-collected datasets. A combined approach was developed which consisted of two steps, artifacts detection and removal of the detected artifacts. Specifically, a novel edge-connection algorithm was used for artifact detection, detection accuracy and false discovery rate were used to evaluate the performance of artifact detection approaches. Criminisi algorithm was used for image restoration with peak signal-to-noise ratio (PSNR) and mean gradient difference to evaluate its performance. In addition, computation complexity was evaluated by execution time of relevant algorithms. ResultsResults revealed that the proposed joint approach with edge-connection and Criminisi algorithm could achieve automatic artifacts removal. Mean detection accuracy and mean false discovery rate of the proposed edge-connection algorithm for the 50 ultrasound images were 0.86 and 1.50. Mean PSNR of the 50 restored images by Criminisi algorithm was 36.64 dB, and mean gradient difference of the restored images was -0.002 compared with the original images. ConclusionsThe proposed combined approach had a good detection accuracy for different types of manually induced artifacts, and could significantly improve PSNR of the ultrasound images. The proposed combined approach may have potential use for the repair of ultrasound images with artifacts.

Detection of Line Artifacts in Lung Ultrasound Images of COVID-19 Patients Via Nonconvex Regularization.

In this article, we present a novel method for line artifacts quantification in lung ultrasound (LUS) images of COVID-19 patients. We formulate this as a nonconvex regularization problem involving a sparsity-enforcing, Cauchy-based penalty function, and the inverse Radon transform. We employ a simple local maxima detection technique in the Radon transform domain, associated with known clinical definitions of line artifacts. Despite being nonconvex, the proposed technique is guaranteed to convergence through our proposed Cauchy proximal splitting (CPS) method, and accurately identifies both horizontal and vertical line artifacts in LUS images. To reduce the number of false and missed detection, our method includes a two-stage validation mechanism, which is performed in both Radon and image domains. We evaluate the performance of the proposed method in comparison to the current state-of-the-art B-line identification method, and show a considerable performance gain with 87% correctly detected B-lines in LUS images of nine COVID-19 patients.

Cascaded one-shot deformable convolutional neural networks: Developing a deep learning model for respiratory motion estimation in ultrasound sequences.

Improving the quality of image-guided radiation therapy requires the tracking of respiratory motion in ultrasound sequences. However, the low signal-to-noise ratio and the artifacts in ultrasound images make it difficult to track targets accurately and robustly. In this study, we propose a novel deep learning model, called a Cascaded One-shot Deformable Convolutional Neural Network (COSD-CNN), to track landmarks in real time in long ultrasound sequences. Specifically, we design a cascaded Siamese network structure to improve the tracking performance of CNN-based methods. We propose a one-shot deformable convolution module to enhance the robustness of the COSD-CNN to appearance variation in a meta-learning manner. Moreover, we design a simple and efficient unsupervised strategy to facilitate the network's training with a limited number of medical images, in which many corner points are selected from raw ultrasound images to learn network features with high generalizability. The proposed COSD-CNN has been extensively evaluated on the public Challenge on Liver UltraSound Tracking (CLUST) 2D dataset and on our own ultrasound image dataset from the First Affiliated Hospital of Sun Yat-sen University (FSYSU). Experiment results show that the proposed model can track a target through an ultrasound sequence with high accuracy and robustness. Our method achieves new state-of-the-art performance on the CLUST 2D benchmark set, indicating its strong potential for application in clinical practice.

A Deep Learning Approach to Resolve Aliasing Artifacts in Ultrasound Color Flow Imaging.

Despite being used clinically as a noninvasive flow visualization tool, color flow imaging (CFI) is known to be prone to aliasing artifacts that arise due to fast blood flow beyond the detectable limit. From a visualization standpoint, these aliasing artifacts obscure proper interpretation of flow patterns in the image view. Current solutions for resolving aliasing artifacts are typically not robust against issues such as double aliasing. In this article, we present a new dealiasing technique based on deep learning principles to resolve CFI aliasing artifacts that arise from single- and double-aliasing scenarios. It works by first using two convolutional neural networks (CNNs) to identify and segment CFI pixel positions with aliasing artifacts, and then it performs phase unwrapping at these aliased pixel positions. The CNN for aliasing identification was devised as a U-net architecture, and it was trained with in vivo CFI frames acquired from the femoral bifurcation that had known presence of single- and double-aliasing artifacts. Results show that the segmentation of aliased CFI pixels was achieved successfully with intersection over union approaching 90%. After resolving these artifacts, the dealiased CFI frames consistently rendered the femoral bifurcation's triphasic flow dynamics over a cardiac cycle. For dealiased CFI pixels, their root-mean-squared difference was 2.51% or less compared with manual dealiasing. Overall, the proposed dealiasing framework can extend the maximum flow detection limit by fivefold, thereby improving CFI's flow visualization performance.

Robust real-time bone surfaces segmentation from ultrasound using a local phase tensor-guided CNN.

Automatic bone surfaces segmentation is one of the fundamental tasks of ultrasound (US)-guided computer-assisted orthopedic surgery procedures. However, due to various US imaging artifacts, manual operation of the transducer during acquisition, and different machine settings, many existing methods cannot deal with the large variations of the bone surface responses, in the collected data, without manual parameter selection. Even for fully automatic methods, such as deep learning-based methods, the problem of dataset bias causes networks to perform poorly on the US data that are different from the training set. In this work, an intensity-invariant convolutional neural network (CNN) architecture is proposed for robust segmentation of bone surfaces from US data obtained from two different US machines with varying acquisition settings. The proposed CNN takes US image as input and simultaneously generates two intermediate output images, denoted as local phase tensor (LPT) and global context tensor (GCT), from two branches which are invariant to intensity variations. LPT and GCT are fused to generate the final segmentation map. In the training process, the LPT network branch is supervised by precalculated ground truth without manual annotation. The proposed method is evaluated on 1227 in vivo US scans collected using two US machines, including a portable handheld ultrasound scanner, by scanning various bone surfaces from 28 volunteers. Validation of proposed method on both US machines not only shows statistically significant improvements in cross-machine segmentation of bone surfaces compared to state-of-the-art methods but also achieves a computation time of 30 milliseconds per image, [Formula: see text] improvement over state-of-the-art. The encouraging results obtained in this initial study suggest that the proposed method is promising enough for further evaluation. Future work will include extensive validation of the method on new US data collected from various machines using different acquisition settings. We will also evaluate the potential of using the segmented bone surfaces as an input to a point set-based registration method.