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.

Mechano-driven intervertebral bone bridging via oriented mechanical stimulus in a twist metamaterial cage: An in silico study.

Stiffer cages provide sufficient mechanical support but fail to promote bone ingrowth due to stress shielding. It remains challenging for fusion cage to satisfy both bone bridging and mechanical stability. Here we designed a fusion cage based on twist metamaterial for improved bone ingrowth, and proved its superiority to the conventional diagonal-based cage in silico. The fusion process was numerically reproduced via an injury-induced osteogenesis model and the mechano-driven bone remodeling algorithm, and the outcomes fusion effects were evaluated by the morphological features of the newly-formed bone and the biomechanical behaviors of the bone-cage composite. The twist-based cages exhibited oriented bone formation in the depth direction, in comparison to the diagonal-based cages. The axial stiffness of the bone-cage composites with twist-based cages was notably higher than that with diagonal-based cages; meanwhile, the ranges of motion of the twist-based fusion segment were lower. It was concluded that the twist metamaterial cages led to oriented bone ingrowth, superior mechanical stability of the bone-cage composite, and less detrimental impacts on the adjacent bones. More generally, metamaterials with a tunable displacement mode of struts might provide more design freedom in implant designs to offer customized mechanical stimulus for osseointegration.

Tanshinone I attenuates estrogen-deficiency bone loss via inhibiting RANKL-induced MAPK and NF-κB signaling pathways.

AIM OF THE STUDY: This study aims to reveal the role of Tanshinone I (TI) in inhibiting osteoclast activity and bone loss in vitro and in vivo, as well as elucidate its underlying molecular mechanism. MATERIALS AND METHODS: A mouse model of estrogen deficiency was used to assess the inhibitory effect of TI on osteoclast activity and subsequent bone loss. To validate the impact of TI on osteoclast formation, TRAcP staining and pseudopodia belt staining were conducted. The expressions of osteoclast-specific genes and proteins were evaluated using RT-PCR and Western Blot analyses. Additionally, immunofluorescence staining was employed to examine the effect of TI on p65 nuclear translocation and the expression level of reactive oxygen species (ROS). RESULTS: TI demonstrated significant efficacy in alleviating bone mass loss and suppressing osteoclast activity and function in ovariectomized mice. This outcome was predominantly ascribed to a decrease in ROS levels, thereby impeding the NF-κB signaling pathway and the translocation of p65 to the nucleus. Additionally, TI hindered the RANKL-induced phosphorylation of the MAPK signaling pathway. Moreover, TI played a role in the reduction of osteoclast-specific genes and proteins. CONCLUSIONS: To summarize, this study sheds light on TI's capacity to modulate various signaling pathways triggered by RANKL, effectively impeding osteoclast formation and mitigating bone loss resulting from estrogen deficiency. Consequently, TI emerges as a promising therapeutic option for estrogen-deficiency bone loss.

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.

The correlations between kinematic profiles and cerebral hemodynamics suggest changes of motor coordination in single and bilateral finger movement.

Objective: The correlation between the performance of coordination movement and brain activity is still not fully understood. The current study aimed to identify activated brain regions and brain network connectivity changes for several coordinated finger movements with different difficulty levels and to correlate the brain hemodynamics and connectivity with kinematic performance. Methods: Twenty-one right-dominant-handed subjects were recruited and asked to complete circular motions of single and bilateral fingers in the same direction (in-phase, IP) and in opposite directions (anti-phase, AP) on a plane. Kinematic data including radius and angular velocity at each task and synchronized blood oxygen concentration data using functional near-infrared spectroscopy (fNIRS) were recorded covering six brain regions including the prefrontal cortex, motor cortex, and occipital lobes. A general linear model was used to locate activated brain regions, and changes compared with baseline in blood oxygen concentration were used to evaluate the degree of brain region activation. Small-world properties, clustering coefficients, and efficiency were used to measure information interaction in brain activity during the movement. Result: It was found that the radius error of the dominant hand was significantly lower than that of the non-dominant hand (p < 0.001) in both clockwise and counterclockwise movements. The fNIRS results confirmed that the contralateral brain region was activated during single finger movement and the dominant motor area was activated in IP movement, while both motor areas were activated simultaneously in AP movement. The Δhbo were weakly correlated with radius errors (p = 0.002). Brain information interaction in IP movement was significantly larger than that from AP movement in the brain network (p < 0.02) in the right prefrontal cortex. Brain activity in the right motor cortex reduces motor performance (p < 0.001), while the right prefrontal cortex region promotes it (p < 0.05). Conclusion: Our results suggest there was a significant correlation between motion performance and brain activation level, as well as between motion deviation and brain functional connectivity. The findings may provide a basis for further exploration of the operation of complex brain networks.

Pre-collapse femoral head necrosis treated by hip abduction: a computational biomechanical analysis.

Background and objective: Clinical studies indicated that femoral head collapse (FHC) occurs in 90% of patients without intervention within five years after the diagnosis of femoral head necrosis (FHN). The management of the FHN is still a great challenging task. Clinical studies indicated that hip abduction as physical therapy represents an effective hip preservation method. However, the mechanism is unclear. In this study, we use computational biomechanical technology to investigate mechanical response in FHN patients with hip abduction and establish guide protocols for FHN rehabilitation. Materials and methods: Thirty computational models were constructed for evaluating the safety of hip abduction and comparing the biomechanical performance of hip abduction for the treatment of different necrotic classifications. The distribution of principal compressive stress (PCS) and load share ratio (LSR) were computed and used for biomechanical evaluation. Results: Before the start of physical therapy, when the size of necrotic segment is increased and located more laterally, the damage area of PCS enlarged and LSR of subchondral cortical to trabecular bone increased. As the increase of hip abduction angle, PCS of Type B transformed into Type A, PCS of Type C1 transformed into Type B, PCS of Type C2 transformed into Type C1; Except Type C2, the LSR return to normal level. Discussion and conclusion: Stress transfer damaged pattern correlated significantly with necrotic classification. Hip abduction motions effectively enlarge the area of PCS and recover the LSR of different structures by altering motion posture during gait. The results indicated that hip abduction may be an effective physical therapy in improving hip function and interrupt the disease pathway of FHC and THA.

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.

Online Hard Patch Mining Using Shape Models and Bandit Algorithm for Multi-Organ Segmentation.

Hard sample selection can effectively improve model convergence by extracting the most representative samples from a training set. However, due to the large capacity of medical images, existing sampling strategies suffer from insufficient exploitation for hard samples or high time cost for sample selection when adopted by 3D patch-based models in the field of multi-organ segmentation. In this paper, we present a novel and effective online hard patch mining (OHPM) algorithm. In our method, an average shape model that can be mapped with all training images is constructed to guide the exploration of hard patches and aggregate feedback from predicted patches. The process of hard mining is formalized as a multi-armed bandit problem and solved with bandit algorithms. With the shape model, OHPM requires negligible time consumption and can intuitively locate difficult anatomical areas during training. The employment of bandit algorithms ensures online and sufficient hard mining. We integrate OHPM with advanced segmentation networks and evaluate them on two datasets containing different anatomical structures. Comparative experiments with other sampling strategies demonstrate the superiority of OHPM in boosting segmentation performance and improving model convergence. The results in each dataset with each network suggest that OHPM significantly outperforms other sampling strategies by nearly 2% average Dice score.

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.

AW3M: An auto-weighting and recovery framework for breast cancer diagnosis using multi-modal ultrasound.

Recently, more clinicians have realized the diagnostic value of multi-modal ultrasound in breast cancer identification and began to incorporate Doppler imaging and Elastography in the routine examination. However, accurately recognizing patterns of malignancy in different types of sonography requires expertise. Furthermore, an accurate and robust diagnosis requires proper weights of multi-modal information as well as the ability to process missing data in practice. These two aspects are often overlooked by existing computer-aided diagnosis (CAD) approaches. To overcome these challenges, we propose a novel framework (called AW3M) that utilizes four types of sonography (i.e. B-mode, Doppler, Shear-wave Elastography, and Strain Elastography) jointly to assist breast cancer diagnosis. It can extract both modality-specific and modality-invariant features using a multi-stream CNN model equipped with self-supervised consistency loss. Instead of assigning the weights of different streams empirically, AW3M automatically learns the optimal weights using reinforcement learning techniques. Furthermore, we design a light-weight recovery block that can be inserted to a trained model to handle different modality-missing scenarios. Experimental results on a large multi-modal dataset demonstrate that our method can achieve promising performance compared with state-of-the-art methods. The AW3M framework is also tested on another independent B-mode dataset to prove its efficacy in general settings. Results show that the proposed recovery block can learn from the joint distribution of multi-modal features to further boost the classification accuracy given single modality input during the test.