Wavenumber Beamforming with Sub-Nyquist Sampling for Focus-Beam Ultrasound Imaging.

Conventional medical ultrasound systems utilizing focus-beam imaging generally acquire multi-channel echoes at frequencies in tens of megahertz after each transmission, resulting in significant data volumes for digital beamforming. Furthermore, integrating state-of-the-art beamformers with transmission compounding substantially increases the beamforming complexity. Except for upgrading the hardware system for better computing performance, an alternative strategy for accelerating ultrasound data processing is the wavenumber beamforming algorithm, which has not been effectively extended to synthetic focus-beam transmission imaging. In this study, we propose a novel wavenumber beamforming algorithm to efficiently reduce the computational complexity of traditional focus-beam ultrasound imaging. We further integrate the wavenumber beamformer with a sub-Nyquist sampling framework, enabling ultrasonic systems to acquire echoes within the active bandwidth at significantly reduced rates. Simulation and experimental results indicate that the proposed beamformer offers image quality comparable to the state-of-the-art spatiotemporal beamformer while reducing the sampling rate and runtime by nearly nine-fold and four-fold, respectively. The proposed approach would potentially help the development of low-power consumption and portable ultrasound systems.

SBCNet: Scale and Boundary Context Attention Dual-Branch Network for Liver Tumor Segmentation.

Automated segmentation of liver tumors in CT scans is pivotal for diagnosing and treating liver cancer, offering a valuable alternative to labor-intensive manual processes and ensuring the provision of accurate and reliable clinical assessment. However, the inherent variability of liver tumors, coupled with the challenges posed by blurred boundaries in imaging characteristics, presents a substantial obstacle to achieving their precise segmentation. In this paper, we propose a novel dual-branch liver tumor segmentation model, SBCNet, to address these challenges effectively. Specifically, our proposed method introduces a contextual encoding module, which enables a better identification of tumor variability using an advanced multi-scale adaptive kernel. Moreover, a boundary enhancement module is designed for the counterpart branch to enhance the perception of boundaries by incorporating contour learning with the Sobel operator. Finally, we propose a hybrid multi-task loss function, concurrently concerning tumors' scale and boundary features, to foster interaction across different tasks of dual branches, further improving tumor segmentation. Experimental validation on the publicly available LiTS dataset demonstrates the practical efficacy of each module, with SBCNet yielding competitive results compared to other state-of-the-art methods for liver tumor segmentation.

SC-SSL: Self-Correcting Collaborative and Contrastive Co-Training Model for Semi-Supervised Medical Image Segmentation.

Image segmentation achieves significant improvements with deep neural networks at the premise of a large scale of labeled training data, which is laborious to assure in medical image tasks. Recently, semi-supervised learning (SSL) has shown great potential in medical image segmentation. However, the influence of the learning target quality for unlabeled data is usually neglected in these SSL methods. Therefore, this study proposes a novel self-correcting co-training scheme to learn a better target that is more similar to ground-truth labels from collaborative network outputs. Our work has three-fold highlights. First, we advance the learning target generation as a learning task, improving the learning confidence for unannotated data with a self-correcting module. Second, we impose a structure constraint to encourage the shape similarity further between the improved learning target and the collaborative network outputs. Finally, we propose an innovative pixel-wise contrastive learning loss to boost the representation capacity under the guidance of an improved learning target, thus exploring unlabeled data more efficiently with the awareness of semantic context. We have extensively evaluated our method with the state-of-the-art semi-supervised approaches on four public-available datasets, including the ACDC dataset, M&Ms dataset, Pancreas-CT dataset, and Task_07 CT dataset. The experimental results with different labeled-data ratios show our proposed method's superiority over other existing methods, demonstrating its effectiveness in semi-supervised medical image segmentation.

An Automated Grading System Based on Topological Features for the Evaluation of Corneal Fluorescein Staining in Dry Eye Disease.

BACKGROUND: Corneal fluorescein staining is a key biomarker in evaluating dry eye disease. However, subjective scales of corneal fluorescein staining are lacking in consistency and increase the difficulties of an accurate diagnosis for clinicians. This study aimed to propose an automatic machine learning-based method for corneal fluorescein staining evaluation by utilizing prior information about the spatial connection and distribution of the staining region. METHODS: We proposed an end-to-end automatic machine learning-based classification model that consists of staining region identification, feature signature construction, and machine learning-based classification, which fully scrutinizes the multiscale topological features together with conventional texture and morphological features. The proposed model was evaluated using retrospective data from Beijing Tongren Hospital. Two masked ophthalmologists scored images independently using the Sjögren's International Collaborative Clinical Alliance Ocular Staining Score scale. RESULTS: A total of 382 images were enrolled in the study. A signature with six topological features, two textural features, and two morphological features was constructed after feature extraction and selection. Support vector machines showed the best classification performance (accuracy: 82.67%, area under the curve: 96.59%) with the designed signature. Meanwhile, topological features contributed more to the classification, compared with other features. According to the distribution and correlation with features and scores, topological features performed better than others. CONCLUSIONS: An automatic machine learning-based method was advanced for corneal fluorescein staining evaluation. The topological features in presenting the spatial connectivity and distribution of staining regions are essential for an efficient corneal fluorescein staining evaluation. This result implies the clinical application of topological features in dry-eye diagnosis and therapeutic effect evaluation.

Adaptive Frequency Learning Network With Anti-Aliasing Complex Convolutions for Colon Diseases Subtypes.

The automatic and dependable identification of colonic disease subtypes by colonoscopy is crucial. Once successful, it will facilitate clinically more in-depth disease staging analysis and the formulation of more tailored treatment plans. However, inter-class confusion and brightness imbalance are major obstacles to colon disease subtyping. Notably, the Fourier-based image spectrum, with its distinctive frequency features and brightness insensitivity, offers a potential solution. To effectively leverage its advantages to address the existing challenges, this article proposes a framework capable of thorough learning in the frequency domain based on four core designs: the position consistency module, the high-frequency self-supervised module, the complex number arithmetic model, and the feature anti-aliasing module. The position consistency module enables the generation of spectra that preserve local and positional information while compressing the spectral data range to improve training stability. Through band masking and supervision, the high-frequency autoencoder module guides the network to learn useful frequency features selectively. The proposed complex number arithmetic model allows direct spectral training while avoiding the loss of phase information caused by current general-purpose real-valued operations. The feature anti-aliasing module embeds filters in the model to prevent spectral aliasing caused by down-sampling and improve performance. Experiments are performed on the collected five-class dataset, which contains 4591 colorectal endoscopic images. The outcomes show that our proposed method produces state-of-the-art results with an accuracy rate of 89.82%.

DSANet: Dual-Branch Shape-Aware Network for Echocardiography Segmentation in Apical Views.

Echocardiography is an essential examination for cardiac disease diagnosis, from which anatomical structures segmentation is the key to assessing various cardiac functions. However, the obscure boundaries and large shape deformations due to cardiac motion make it challenging to accurately identify the anatomical structures in echocardiography, especially for automatic segmentation. In this study, we propose a dual-branch shape-aware network (DSANet) to segment the left ventricle, left atrium, and myocardium from the echocardiography. Specifically, the elaborate dual-branch architecture integrating shape-aware modules boosts the corresponding feature representation and segmentation performance, which guides the model to explore shape priors and anatomical dependence using an anisotropic strip attention mechanism and cross-branch skip connections. Moreover, we develop a boundary-aware rectification module together with a boundary loss to regulate boundary consistency, adaptively rectifying the estimation errors nearby the ambiguous pixels. We evaluate our proposed method on the publicly available and in-house echocardiography dataset. Comparative experiments with other state-of-the-art methods demonstrate the superiority of DSANet, which suggests its potential in advancing echocardiography segmentation.

BSMNet: Boundary-salience multi-branch network for intima-media identification in carotid ultrasound images.

Carotid artery intima-media thickness (CIMT) is an essential factor in signaling the risk of cardiovascular diseases, which is commonly evaluated using ultrasound imaging. However, automatic intima-media segmentation and thickness measurement are still challenging due to the boundary ambiguity of intima-media and inherent speckle noises in ultrasound images. In this work, we propose an end-to-end boundary-salience multi-branch network, BSMNet, to tackle the carotid intima-media identification from ultrasound images, where the prior shape knowledge and anatomical dependence are exploited using a parallel linear structure learning modules followed by a boundary refinement module. Moreover, we design a strip attention model to boost the thin strip region segmentation with shape priors, in which an anisotropic kernel shape captures long-range global relations and scrutinizes meaningful local salient contexts simultaneously. Extensive experimental results on an in-house carotid ultrasound (US) dataset demonstrate the promising performance of our method, which achieves about 0.02 improvement in Dice and HD95 than other state-of-the-art methods. Our method is promising in advancing the analysis of systemic arterial disease with ultrasound imaging.

DLGNet: A dual-branch lesion-aware network with the supervised Gaussian Mixture model for colon lesions classification in colonoscopy images.

Colorectal cancer is one of the malignant tumors with the highest mortality due to the lack of obvious early symptoms. It is usually in the advanced stage when it is discovered. Thus the automatic and accurate classification of early colon lesions is of great significance for clinically estimating the status of colon lesions and formulating appropriate diagnostic programs. However, it is challenging to classify full-stage colon lesions due to the large inter-class similarities and intra-class differences of the images. In this work, we propose a novel dual-branch lesion-aware neural network (DLGNet) to classify intestinal lesions by exploring the intrinsic relationship between diseases, composed of four modules: lesion location module, dual-branch classification module, attention guidance module, and inter-class Gaussian loss function. Specifically, the elaborate dual-branch module integrates the original image and the lesion patch obtained by the lesion localization module to explore and interact with lesion-specific features from a global and local perspective. Also, the feature-guided module guides the model to pay attention to the disease-specific features by learning remote dependencies through spatial and channel attention after network feature learning. Finally, the inter-class Gaussian loss function is proposed, which assumes that each feature extracted by the network is an independent Gaussian distribution, and the inter-class clustering is more compact, thereby improving the discriminative ability of the network. The extensive experiments on the collected 2568 colonoscopy images have an average accuracy of 91.50%, and the proposed method surpasses the state-of-the-art methods. This study is the first time that colon lesions are classified at each stage and achieves promising colon disease classification performance. To motivate the community, we have made our code publicly available via https://github.com/soleilssss/DLGNet.

Automatic 3-D spine curve measurement in freehand ultrasound via structure-aware reinforcement learning spinous process localization.

Freehand 3-D ultrasound systems have been advanced in scoliosis assessment to avoid radiation hazards, especially for teenagers. This novel 3-D imaging method also makes it possible to evaluate the spine curvature automatically from the corresponding 3-D projection images. However, most approaches neglect the three-dimensional spine deformity by only using the rendering images, thus limiting their usage in clinical applications. In this study, we proposed a structure-aware localization model to directly identify the spinous processes for automatic 3-D spine curve measurement using the images acquired with freehand 3-D ultrasound imaging. The pivot is to leverage a novel reinforcement learning (RL) framework to localize the landmarks, which adopts a multi-scale agent to boost structure representation with positional information. We also introduced a structure similarity prediction mechanism to perceive the targets with apparent spinous process structures. Finally, a two-fold filtering strategy was proposed to screen the detected spinous processes landmarks iteratively, followed by a three-dimensional spine curve fitting for the spine curvature assessments. We evaluated the proposed model on 3-D ultrasound images among subjects with different scoliotic angles. The results showed that the mean localization accuracy of the proposed landmark localization algorithm was 5.95 pixels. Also, the curvature angles on the coronal plane obtained by the new method had a high linear correlation with those by manual measurement (R = 0.86, p < 0.001). These results demonstrated the potential of our proposed method for facilitating the 3-D assessment of scoliosis, especially for 3-D spine deformity assessment.

Automatic Myotendinous Junction Identification In Ultrasound Images Based on Junction-based Template Measurements.

Tracking the myotendinous junction (MTJ) motion in consecutive ultrasound images is essential to assess muscle and tendon interaction and understand the mechanics' muscle-tendon unit and its pathological conditions during motion. However, the inherent speckle noises and ambiguous boundaries deter the reliable identification of MTJ, thus restricting their usage in human motion analysis. This study advances a fully automatic displacement measurement method for MTJ using prior shape knowledge on the Y-shape MTJ, precluding the influence of irregular and complicated hyperechoic structures in muscular ultrasound images. Our proposed method first adopts the junction candidate points using a combined measure of Hessian matrix and phase congruency, followed by a hierarchical clustering technique to refine the candidates approximating the position of the MTJ. Then, based on the prior knowledge of Y-shape MTJ, we finally identify the best matching junction points according to intensity distributions and directions of their branches using multiscale Gaussian templates and a Kalman filter. We evaluated our proposed method using the ultrasound scans of the gastrocnemius from 8 young, healthy volunteers. Our results present more consistent with the manual method in the MTJ tracking method than existing optical flow tracking methods, suggesting its potential in facilitating muscle and tendon function examinations with in vivo ultrasound imaging.

Pixel-based approach to delay multiply and sum beamforming in combination with Wiener filter for improving ultrasound image quality.

Unified pixel-based (PB) beamforming has been implemented for ultrasound imaging, offering significant enhancements in lateral resolution compared to the conventional dynamic focusing. However, it still suffers from clutter and off-axis artifacts, limiting the contrast resolution. This paper proposes an efficient method to improve image quality by integrating filtered delay multiply and sum (F-DMAS) into the framework. This hybrid strategy incorporates the spatial coherence of the received data into the beamforming process to improve contrast resolution and clutter rejection in the generated image. We also integrate a Wiener filter to suppress the spatiotemporal spreading using signals echoed from a single scatterer at the transmit focus as a kernel for the deconvolution. The Wiener filter is applied to the received waveforms before performing the hybrid strategy. The Wiener filter is shown to reduce interference due to the interaction between the excitation pulse and the transfer functions of the transducer elements, thus benefiting the axial resolution of the generated images. We validate the proposed method and compare it with other beamforming strategies through a series of experiments, including simulation, phantom, and in vivo studies. The results show that our approach can substantially improve both spatial resolution and contrast over the unified PB algorithm, while still maintaining the good features of this beamformer. The simplicity and good performance of our method show its potential for use in clinical applications.

AWSnet: An auto-weighted supervision attention network for myocardial scar and edema segmentation in multi-sequence cardiac magnetic resonance images.

Multi-sequence cardiac magnetic resonance (CMR) provides essential pathology information (scar and edema) to diagnose myocardial infarction. However, automatic pathology segmentation can be challenging due to the difficulty of effectively exploring the underlying information from the multi-sequence CMR data. This paper aims to tackle the scar and edema segmentation from multi-sequence CMR with a novel auto-weighted supervision framework, where the interactions among different supervised layers are explored under a task-specific objective using reinforcement learning. Furthermore, we design a coarse-to-fine framework to boost the small myocardial pathology region segmentation with shape prior knowledge. The coarse segmentation model identifies the left ventricle myocardial structure as a shape prior, while the fine segmentation model integrates a pixel-wise attention strategy with an auto-weighted supervision model to learn and extract salient pathological structures from the multi-sequence CMR data. Extensive experimental results on a publicly available dataset from Myocardial pathology segmentation combining multi-sequence CMR (MyoPS 2020) demonstrate our method can achieve promising performance compared with other state-of-the-art methods. Our method is promising in advancing the myocardial pathology assessment on multi-sequence CMR data. To motivate the community, we have made our code publicly available via https://github.com/soleilssss/AWSnet/tree/master.

Improved ultrasound image quality with pixel-based beamforming using a Wiener-filter and a SNR-dependent coherence factor.

Pixel-based beamforming generates focused data by assuming that the waveforms received on a linear transducer array are composed of spherical pulses. It does not take into account the spatiotemporal spread in the data from the length of the excitation pulse or from the transfer functions of the transducer elements. As a result, these beamformers primarily have impacts on lateral, rather than axial, resolution. This paper proposes an efficient method to improve the axial resolution for pixel-based beamforming. We extend our field pattern analysis and show that the received waveforms should be passed through a Wiener filter before being used in the coherent pixel-based beamformer. This filter is designed based on signals echoed from a single scatterer at the transmit focus. The beamformer output is then combined with a coherence factor, that is adaptive to the signal-to-noise ratio, to improve the image contrast and suppress artifacts that have arisen during the filtering process. We validate the proposed method and compare it with other beamforming strategies using a series of experiments, including simulation, phantom and in vivo studies. It is shown to offer significant improvements in axial resolution and contrast over coherent pixel-based beamforming, as well as other spatial filters derived from synthetic aperture imaging. The method also demonstrates robustness to modeling errors in the experimental data. Overall, the imaging results show that the proposed approach has the potential to be of value in clinical applications.

miR-137 Inhibition of the Invasion, Metastasis, and Epithelial-Mesenchymal Transition of Nasopharyngeal Cancer by Regulating KDM1A.

One of the most frequent malignancies in the head and neck is nasopharyngeal carcinoma (NPC). MicroRNAs, a kind of tiny noncoding RNA molecule, have been used as negative regulators in different types of cancer therapy in recent decades by downregulating their targets. Recent research suggests that microRNAs play an important role in cancer's epithelial-to-mesenchymal transition (EMT), supporting or inhibiting EMT development. The epithelial-to-mesenchymal transition (EMT) is linked to a variety of cancer-related activities, including growth, metastasis, and invasion. Previous research has linked EMT to cancer stem-like characteristics as well as treatment resistance. Moreover, since microRNAs (miRNAs) are important regulators of the EMT phenotype, certain miRNAs have an effect on cancer stemness and treatment resistance. As a result, both fundamental research and clinical therapy benefit from knowing the connection between EMT-associated miRNAs and cancer stemness/drug resistance. As a result, we looked at the different functions that EMT-associated miRNAs (miR-137) play in the stem-like characteristics of malignant cells in this article. Then we looked at how EMT-associated miRNAs interact with nasopharyngeal cancer's drug-resistant complex signaling pathways. Using qRT-PCR, we evaluated the performance of several micro RNAs with the proposed miR-137 for inhibiting invasion, metastasis, and the EMT process. In conclusion, our findings showed that miR-137 acted as a tumor suppressor gene in controlling NPC EMT and metastasis and that it may be a new therapeutic strategy and prognosis marker for the disease.

Learn Fine-Grained Adaptive Loss for Multiple Anatomical Landmark Detection in Medical Images.

Automatic and accurate detection of anatomical landmarks is an essential operation in medical image analysis with a multitude of applications. Recent deep learning methods have improved results by directly encoding the appearance of the captured anatomy with the likelihood maps (i.e., heatmaps). However, most current solutions overlook another essence of heatmap regression, the objective metric for regressing target heatmaps and rely on hand-crafted heuristics to set the target precision, thus being usually cumbersome and task-specific. In this paper, we propose a novel learning-to-learn framework for landmark detection to optimize the neural network and the target precision simultaneously. The pivot of this work is to leverage the reinforcement learning (RL) framework to search objective metrics for regressing multiple heatmaps dynamically during the training process, thus avoiding setting problem-specific target precision. We also introduce an early-stop strategy for active termination of the RL agent's interaction that adapts the optimal precision for separate targets considering exploration-exploitation tradeoffs. This approach shows better stability in training and improved localization accuracy in inference. Extensive experimental results on two different applications of landmark localization: 1) our in-house prenatal ultrasound (US) dataset and 2) the publicly available dataset of cephalometric X-Ray landmark detection, demonstrate the effectiveness of our proposed method. Our proposed framework is general and shows the potential to improve the efficiency of anatomical landmark detection.

A Single-Shot Region-Adaptive Network for Myotendinous Junction Segmentation in Muscular Ultrasound Images.

Tracking the myotendinous junction (MTJ) in consecutive ultrasound images is crucial for understanding the mechanics and pathological conditions of the muscle-tendon unit. However, the lack of reliable and efficient identification of MTJ due to poor image quality and boundary ambiguity restricts its application in motion analysis. In recent years, with the rapid development of deep learning, the region-based convolution neural network (RCNN) has shown great potential in the field of simultaneous objection detection and instance segmentation in medical images. This article proposes a region-adaptive network (RAN) to localize MTJ region and to segment it in a single shot. Our model learns about the salient information of MTJ with the help of a composite architecture. Herein, a region-based multitask learning network explores the region containing MTJ, while a parallel end-to-end U-shaped path extracts the MTJ structure from the adaptively selected region for combating data imbalance and boundary ambiguity. By demonstrating the ultrasound images of the gastrocnemius, we showed that the RAN achieves superior segmentation performance when compared with the state-of-the-art Mask RCNN method with an average Dice score of 80.1%. Our proposed method is robust and reliable for advanced muscle and tendon function examinations obtained by ultrasound imaging.

Automating Spine Curvature Measurement in Volumetric Ultrasound via Adaptive Phase Features.

Ultrasound volume projection imaging (VPI) has been recently suggested. This novel imaging method allows a non-radiation assessment of spine deformity with free-hand 3-D ultrasound imaging. This paper presents a fully automatic method to evaluate the spine curve in VPI images corresponding to different projection depth of the volumetric ultrasound, thus making it possible to analyze 3-D spine deformity. The new automatic method is based on prior knowledge about the geometric arrangement of the spinous processes. The frequency bandwidth of log-Gabor filters is adaptively adjusted to calculate the oriented phase congruency, facilitating the segmentation of the spinous column profile. And the spine curvature angle is finally calculated according to the inflection points of the curve over the segmented spinous column profile. The performance of the automatic method is evaluated on spine VPI images among patients with different scoliotic angles. The curvature angles obtained using the proposed method have a high linear correlation with those by the manual method (r = 0.90, p < 0.001) and X-ray Cobb's method (r = 0.87, p < 0.001). The feasibility of 3-D spine deformity assessment is also demonstrated using VPI images corresponding to various projection depth. The results suggest that this method can substantially improve the recognition of the spinous column profile, especially facilitating the applications of 3-D spine deformity assessment.

3D shape measurement based on structured light field imaging.

In this paper, a three-dimensional (3D) shape measurement method based on structured light field imaging is proposed, which contributes to the biomedical imaging. Generally, light field imaging is challenging to accomplish the 3D shape measurement accurately, as the slope estimation method based on radiance consistency is inaccurate. Taking into consideration the special modulation of structured light field, we utilize the phase information to substitute the phase consistency for the radiance consistency in epi-polar image (EPI) at first. Therefore, the 3D coordinates are derived after light field calibration, but the results are coarse due to slope estimation error and need to be corrected. Furthermore, the 3D coordinates refinement is performed based on relationship between the structured light field image and DMD image of the projector, which allows to improve the performance of the 3D shape measurement. The necessary light field camera calibration is described to generalize its application. Subsequently, the effectiveness of the proposed method is demonstrated with a sculpture and compared to the results of a conventional PMP system.

An automatic measurement method of spinal curvature on ultrasound coronal images in adolescent idiopathic scoliosis.

This study proposed a new automatic measurement method of spinal curvature on ultrasound coronal images in adolescent idiopathic scoliosis (AIS). After preprocessing of Gaussian enhancement, the symmetric information of the image was extracted using the phase congruency. Then bony features were segmented from the soft tissues and background using the greyscale polarity. The morphological methods of image erosion and top-bottom-hat transformation, and geometric moment were utilized to identify the spinous column profile from the transverse processes. Finally, the spine deformity curve was obtained using robust regression. In-vivo experiments based on AIS patients were performed to evaluate the performance of the developed method. The comparison results revealed there was a significant correlation (y=0.81x, r=0.86) and good agreement between the new automatic method and the manual measurement method. It can be expected that this novel method may help to provide effective and objective deformity assessment method during the ultrasound scanning for AIS patients.

A fast 3-D ultrasound projection imaging method for scoliosis assessment.

Applying ultrasound for scoliosis assessment has been an attractive topic over the past decade. This study proposed a new fast 3-D ultrasound projection imaging method to evaluate the spine deformity. A narrow-band rendering method was used to generate the coronal images based on B-mode images and their corresponding positional data. The non-planar reslicing method, which followed the natural spine curve, was used to project the complete spine data into the coronal image. The repeatability of the new method was tested. A comparison experiment on the reconstructed images and the processing time between the conventional 3-D rendering method and the developed projection imaging method was also performed among 70 patients with scoliosis. The intra- and inter-operator tests results demonstrated very good repeatability (ICC ≥ 0.90). The mean processing times for the developed projection method and conventional rendering method were 15.07 ± 0.03 s and 130.31 ± 35.07 s, respectively. The angle measurement results showed a high correlation (y = 0.984x, r = 0.954) between the images obtained using the two methods. The above results indicated that the developed projection imaging method could greatly decrease the processing time while preserving the comparative image quality. It can be expected that this novel method may help to provide fast 3-D ultrasound diagnosis of scoliosis in clinics.