A mechanism linking ferroptosis and ferritinophagy in melatonin-related improvement of diabetic brain injury.

Ferroptosis and ferritinophagy play critical roles in various disease contexts. Herein, we observed that ferroptosis and ferritinophagy were induced both in the brains of mice with diabetes mellitus (DM) and neuronal cells after high glucose (HG) treatment, as evidenced by decreases in GPX4, SLC7A11, and ferritin levels, but increases in NCOA4 levels. Interestingly, melatonin administration ameliorated neuronal damage by inhibiting ferroptosis and ferritinophagy both in vivo and in vitro. At the molecular level, we found that not only the ferroptosis inducer p53 but also the ferritinophagy mediator NCOA4 was the potential target of miR-214-3p, which was downregulated by DM status or HG insult, but was increased after melatonin treatment. However, the inhibitory effects of melatonin on ferroptosis and ferritinophagy were blocked by miR-214-3p downregulation. These findings suggest that melatonin is a potential drug for improving diabetic brain damage by inhibiting p53-mediated ferroptosis and NCOA4-mediated ferritinophagy through regulating miR-214-3p in neurons.

BAG-Net: a boundary detection and multiple attention-guided network for liver ultrasound image automatic segmentation in ultrasound guided surgery.

Objective.Automated segmentation of targets in ultrasound (US) images during US-guided liver surgery holds the potential to assist physicians in fast locating critical areas such as blood vessels and lesions. However, this remains a challenging task primarily due to the image quality issues associated with US, including blurred edges and low contrast. In addition, studies specifically targeting liver segmentation are relatively scarce possibly since studying deep abdominal organs under US is difficult. In this paper, we proposed a network named BAG-Net to address these challenges and achieve accurate segmentation of liver targets with varying morphologies, including lesions and blood vessels.Approach.The BAG-Net was designed with a boundary detection module together with a position module to locate the target, and multiple attention-guided modules combined with the depth supervision strategy to enhance detailed segmentation of the target area.Main Results.Our method was compared to other approaches and demonstrated superior performance on two liver US datasets. Specifically, the method achieved 93.9% precision, 91.2% recall, 92.4% Dice coefficient, and 86.2% IoU to segment the liver tumor. Additionally, we evaluated the capability of our network to segment tumors on the breast US dataset (BUSI), where it also achieved excellent results.Significance.Our proposed method was validated to effectively segment liver targets with diverse morphologies, providing suspicious areas for clinicians to identify lesions or other characteristics. In the clinic, the method is anticipated to improve surgical efficiency during US-guided surgery.

Improving Needle Tip Tracking and Detection in Ultrasound-Based Navigation System Using Deep Learning-Enabled Approach.

Ultrasound-guided percutaneous interventions have numerous advantages over traditional techniques. Accurate needle placement in the target anatomy is crucial for successful intervention, and reliable visual information is essential to achieve this. However, previous studies have revealed several challenges, such as the variability in needle echogenicity and the common misalignment of the ultrasound beam and the needle. Advanced techniques have been developed to optimize needle visualization, including hardware-based and image-processing-based methods. This paper proposes a novel strategy of integrating ultrasound-based deep learning approaches into an optical navigation system to enhance needle visualization and improve tip positioning accuracy. Both the tracking and detection algorithms are optimized utilizing optical tracking information. The information is introduced into the tracking network to define the search patch update strategy and form a trajectory reference to correct tracking results. In the detection network, the original image is processed according to the needle insertion position and current position given by the optical localization system to locate a coarse region, and the depth-score criterion is adopted to optimize detection results. Extensive experiments demonstrate that our approach achieves promising tip tracking and detection performance with tip localization errors of 1.11 ± 0.59 mm and 1.17 ± 0.70 mm, respectively. Moreover, we establish a paired dataset consisting of ultrasound images and their corresponding spatial tip coordinates acquired from the optical tracking system and conduct real puncture experiments to verify the effectiveness of the proposed methods. Our approach significantly improves needle visualization and provides physicians with visual guidance for posture adjustment.

An automatic cephalometric landmark detection method based on heatmap regression and Monte Carlo dropout.

Cephalometric analysis plays an important role in orthodontic diagnosis and treatment planning. It depends on the detection of multiple landmarks, while the process is time-consuming and tedious. Although some deep learning-based automatic landmark detection algorithms have achieved excellent performance, most of them adopt multi-stage models increasing the complexity and detection time. Meanwhile, few studies focused on the uncertainty of detection results, thereby ignoring its significant clinical value. In this paper, we propose a novel approach based on heatmap regression for landmark detection, which can achieve competitive accuracy and good robustness with only one step. Furthermore, by applying Monte Carlo dropout to a U-shaped convolutional neural network, we can obtain not only the coordinate of each landmark but also the corresponding simple uncertainty, so that doctors can pay more attention to those landmarks with higher uncertainty. The evaluation results showed the mean radial error is 1.39±1.06mm and the average successful detection rate is 79.65%, 97.22% within 2mm, 4mm for the IEEE ISBI2015 Test Dataset 1, the indicators for the IEEE ISBI2015 Test Dataset 2 are 1.33±0.93mm, 80.05% and 97.53%, respectively. Our method has the potential to become an assistant tool in clinical practice. Automatic and accurate detection with uncertainty analysis is expected to help guide the doctor's judgment.

The effect of allyl isothiocyanate on chondrocyte phenotype is matrix stiffness-dependent: Possible involvement of TRPA1 activation.

Osteoarthritis (OA) is a chronic joint disease with increasing prevalence. Chondrocytes (CHs) are highly differentiated end-stage cells with a secretory phenotype that keeps the extracellular matrix (ECM) balanced and the cartilage environment stable. Osteoarthritis dedifferentiation causes cartilage matrix breakdown, accounting for one of the key pathogenesis of osteoarthritis. Recently, the activation of transient receptor potential ankyrin 1 (TRPA1) was claimed to be a risk factor in osteoarthritis by causing inflammation and extracellular matrix degradation. However, the underlying mechanism is still unknown. Due to its mechanosensitive property, we speculated that the role of TRPA1 activation during osteoarthritis is matrix stiffness-dependent. In this study, we cultured the chondrocytes from patients with osteoarthritis on stiff vs. soft substrates, treated them with allyl isothiocyanate (AITC), a transient receptor potential ankyrin 1 agonist, and compared the chondrogenic phenotype, containing cell shape, F-actin cytoskeleton, vinculin, synthesized collagen profiles and their transcriptional regulatory factor, and inflammation-related interleukins. The data suggest that allyl isothiocyanate treatment activates transient receptor potential ankyrin 1 and results in both positive and harmful effects on chondrocytes. In addition, a softer matrix could help enhance the positive effects and alleviate the harmful ones. Thus, the effect of allyl isothiocyanate on chondrocytes is conditionally controllable, which could be associated with transient receptor potential ankyrin 1 activation, and is a promising strategy for osteoarthritis treatment.

Effectiveness of clinical mentorship program for students of long-term aged care: A mixed-methods study.

BACKGROUND: Internationally, the population is rapidly aging with a strong demand for aged care services. In Taiwan, both recruiting and retaining staff to aged care poses difficulties. Good clinical role models can positively impact students' confidence and professional development and influence their willingness to enter the long-term aged care workforce. OBJECTIVES: To clarify clinical mentors' roles and competencies and assess the effectiveness of a mentorship program for improving students' professional commitment and self-efficacy in long-term aged care. DESIGN: A mixed-methods study with a quasi-experimental research design and qualitative interviews. SETTINGS: Purposive sampling was used to recruit long-term aged care professional clinical mentors with preceptor qualifications and nursing and aged care students enrolled in a two-year technical program in a Taiwanese university's gerontology care department. PARTICIPANTS: Fourteen mentors and 48 students participated. The student control group received regular education; the experimental group received mentorship guidance. METHODS: This study included three phases. Phase one involved qualitative interviews to identify clinical mentors' roles and competencies. Phase two involved expert panel meetings to establish the clinical mentorship program's content and implementation. Phase three involved the program's evaluation. Quantitative questionnaires were administered before the program and subsequently at 6, 12, and 18 months to assess mentors' effectiveness and students' professional commitment and self-efficacy in long-term aged care. Qualitative focus groups solicited participants' feelings and suggestions for the program. RESULTS: Clinical mentors' roles and competencies centered on two themes: professional role model and establishing good rapport. Quantitative analysis showed that mentoring effectiveness initially recorded a decline, followed by a subsequent increase. Both groups' professional self-efficacy and commitment followed an increasing trend. While the experimental group's professional commitment score was significantly higher than the control groups, their professional self-efficacy scores did not differ significantly. CONCLUSIONS: The clinical mentorship program improved students' long-term aged care professional commitment and self-efficacy.

Icaritin Derivative IC2 Induces Cytoprotective Autophagy of Breast Cancer Cells via SCD1 Inhibition.

Breast cancer is one of the most prevalent malignancies and the leading cause of cancer-associated mortality in China. Icaritin (ICT), a prenyl flavonoid derived from the Epimedium Genus, has been proven to inhibit the proliferation and stemness of breast cancer cells. Our previous study demonstrated that IC2, a derivative of ICT, could induce breast cancer cell apoptosis by Stearoyl-CoA desaturase 1 (SCD1) inhibition. The present study further investigated the mechanism of the inhibitory effects of IC2 on breast cancer cells in vitro and in vivo. Our results proved that IC2 could stimulate autophagy in breast cancer cells with the activation of adenosine monophosphate (AMP)-activated protein kinase (AMPK) signaling and mitogen-activated protein kinase (MAPK) signaling. Combination treatment of the AMPK inhibitor decreased IC2-induced autophagy while it markedly enhanced IC2-induced apoptosis. In common with IC2-induced apoptosis, SCD1 overexpression or the addition of exogenous oleic acid (OA) could also alleviate IC2-induced autophagy. In vivo assays additionally demonstrated that IC2 treatment markedly inhibited tumor growth in a mouse breast cancer xenograft model. Overall, our study was the first to demonstrate that IC2 induced cytoprotective autophagy by SCD1 inhibition in breast cancer cells and that the autophagy inhibitor markedly enhanced the anticancer activity of IC2. Therefore, IC2 was a potential candidate compound in combination therapy for breast cancer.

Impact of Social Support and Reciprocity on Consumer Well-Being in Virtual Medical Communities.

This study pursues a better understanding of consumer well-being in online medical cosmetics communities by investigating the antecedents of well-being and moderating influence of community norms. A total valid sample of 484 respondents was collected from 2 popular medical cosmetics discussion platforms. A partial least squares analysis was used to validate the research model. Emotional support, informational support, and sense of belonging were important predictors of well-being. Among these 3 antecedents, emotional support showed the strongest influence on consumer well-being. Sense of belonging was significantly and positively influenced by emotional support and reciprocity, and hence plays a pivotal role in mediating the effects of emotional support and reciprocity on well-being. However, informational support does not appear to significantly influence sense of belonging. Members' compliance with community norms positively moderates the influence of sense of belonging on well-being. This study contributes to the literature on realizing members' social behaviors specifically in virtual medical cosmetics communities and provides insights for the management of online communities.

Development and Evaluation of Neighborhood Care Volunteer Training Programs-Preparing for Older Adult Community Care in Taiwan.

BACKGROUND: The prevalence of chronic diseases and functional disorders is projected to escalate as the older adult population increases. Thus, the demand for and burdens of long-term care are increasing. Training middle-aged and older volunteers at the community level will enhance health promotion and disease prevention in communities. PURPOSE: In this study, multilevel volunteer training programs and related implementation methods were designed for neighborhood caregivers. METHODS: This study was divided into two phases. In Phase 1, an expert review was conducted using the modified Delphi method to congregate expert opinions into an interdisciplinary consensus and establish the content and methods of implementation of the multilevel training program. In Phase 2, the training programs were implemented and evaluated. RESULTS: In Phase 1, 17 experts in geriatric and long-term care were enrolled in the Delphi surveys. Consensus was defined as at least 80% agreement. These experts devised volunteer training programs for neighborhood caregivers at three levels: basic caregiver training, advanced caregiver training, and volunteer caregiver instructor training. The curriculum focused on fulfilling the health demands of neighborhood care; adopted disability-prevention and disability-delaying healthcare as the basic framework; and referred to the attention, relevance, confidence, and satisfaction model of motivational design. This model of motivational design drew on the attributes of volunteers and the current state of care programs, including interest, program difficulty, and feasibility of future services. In Phase 2, 50 community middle-aged and older volunteers enrolled in the training programs and, after completing the program, were asked to evaluate their satisfaction with the program content and program effectiveness. A high level of satisfaction was reported across all three levels. CONCLUSIONS/IMPLICATIONS FOR PRACTICE: The training programs achieved satisfactory consistency and convergence and were well received by the volunteer trainees. These programs may be referenced in the development of future training programs and the creation of a model of community healthcare services. The curriculum was designed from the learners' perspective with direct healthcare applications. A progressive multilevel set of neighborhood care volunteer training programs was offered to cultivate community volunteers.

Resource allocation algorithm of an indoor OFDMA VLC system.

In this work, a resource management algorithm is proposed for an indoor visible light communication (VLC) access network using an orthogonal frequency division multiple access (OFDMA) scheme. With OFDMA, adaptive modulation is adopted to improve the frequency spectrum efficiency of this VLC system. Specifically, the long-term time-averaged optimization problem is transformed into a series of single timeslot online problems via a Lyapunov optimization technique. Then, each user is provided with a separate queue to maintain the random arrival data by a VLC access point, and a subcarrier allocation solution is subsequently presented to maximize the transmission rate. Numerical simulation shows that compared with the best channel state information (BC) algorithm and round robin (RR) algorithm, the proposed algorithm can not only ensure the transmission rate but also greatly improve system stability. In particular, for mean arrival rate B=7Kbits/timeslot, the system stability by the proposed algorithm improves by about 53.36% and 61.36% in comparison with BC and RR algorithms, respectively. This work will benefit the design and development of indoor OFDMA VLC systems.

[Corrigendum] High glucose promotes hepatic fibrosis via miR­32/MTA3­mediated epithelial­to­mesenchymal transition.

Subsequently to the publication of this paper, the authors have realized that Fig. 2 was published containing some incorrectly assembled data panels. The E­cadherin control data panel in Fig. 3F was re­used in Fig. 2C; furthermore, the HG / Vimentin data panel in Fig. 4E was re­used in Fig. 2D. The authors have re­examined their original data, and were able to identify that Fig. 2 contained the erroneously assembled data panels. The revised version of Fig. 2, showing the correct E­cadherin control data panel for Fig. 2C and the correct HG / Vimentin data panel for Fig. 2D, is shown below. It was also noted that the white rectangles were not explained in the figure legend; these represent an enlargement of the cells in the E­cad/vimentin panels, and the details are now included in the figure legend (shown in bold). Note that these errors did not significantly affect either the results or the conclusions reported in this paper, and all the authors agree to the publication of this corrigendum. Furthermore, the authors thank the Editor of Molecular Medicine Reports for allowing them the opportunity to publish this corrigendum, and apologize to the readership for any inconvenience caused. [Molecular Medicine Reports 19: 3190­3200, 2019; DOI: 10.3892/mmr.2019.9986].

Identification of icaritin derivative IC2 as an SCD-1 inhibitor with anti-breast cancer properties through induction of cell apoptosis.

BACKGROUND: Breast cancer is the most common malignancy affecting women, yet effective targets and related candidate compounds for breast cancer treatment are still lacking. The lipogenic enzyme, stearoyl-CoA desaturase-1 (SCD1), has been considered a potential target for breast cancer treatment. Icaritin (ICT), a prenylflavonoid derivative from the Traditional Chinese Medicine Epimedii Herba, has been reported to exert anticancer effects in various types of cancer. The purpose of the present study was to explore the effect of the new ICT derivative, IC2, targeting SCD1 on breast cancer cells and to explore the specific mechanism. METHODS: Immunohistochemistry and semiquantitative evaluation were performed to detect the expression level of SCD1 in normal and tumor samples. Computer-aided drug design (CADD) technology was used to target SCD1 by molecular docking simulation, and several new ICT derivatives were prepared by conventional chemical synthesis. Cell viability was evaluated by an MTT assay and dead cell staining. SCD1 expression in cancer cells was determined by Western blot and qRT-PCR analyses. The enzymatic activity of SCD1 was evaluated by detecting the conversion rate of [d31] palmitic acid (PA) using Gas chromatography-mass spectrometry (GC-MS). DAPI staining, flow cytometry and Western blot were used to detect cell apoptosis. Mitochondrial membrane potential and reactive oxygen species (ROS) assays were used to determine cell mitochondrial function. Lentiviral transduction was utilized to generate SCD1-overexpressing cell lines. RESULTS: We found that SCD1 was overexpressed and correlated with poor prognosis in breast cancer patients. Among a series of ICT derivatives, in vitro data showed that IC2 potentially inhibited the viability of breast cancer cells, and the mechanistic study revealed that IC2 treatment resulted in ROS activation and cellular apoptosis. We demonstrated that IC2 inhibited SCD1 activity and expression in breast cancer cells in a dose-dependent manner. Moreover, SCD1 overexpression alleviated IC2-induced cytotoxicity and apoptosis in breast cancer cells. CONCLUSIONS: The new ICT derivative, IC2, was developed to induce breast cancer cell apoptosis by inhibiting SCD1, which provides a basis for the development of IC2 as a potential clinical compound for breast cancer treatment.

Feature pyramid self-attention network for respiratory motion prediction in ultrasound image guided surgery.

PURPOSE: The robot-assisted automated puncture system under ultrasound guidance can well improve the puncture accuracy in ablation surgery. The automated puncture system requires advanced definition of the puncture location, while the displacement of thoracic-abdominal tumors caused by respiratory motion makes it difficult for the system to locate the best puncture position. Predicting tumor motion is an effective way to help the automated puncture system output a more accurate puncture position. METHODS: In this paper, we propose a self-attention-based feature pyramid algorithm FPSANet for time-series forecasting, which can extract both linear and nonlinear dependencies of time series. Firstly, we use the temporal convolutional network as the backbone to extract different scale time-series features, and the self-attention module is followed to weigh more significant features to improve nonlinear prediction. Secondly, we use autoregressive models to perform linear prediction. Finally, we directly combine the above two kinds of predictions as the final prediction. RESULTS: FPSANet is trained and tested on our private datasets captured from clinical individuals, and we predict the target position after 50 ms, 150 ms, 300 ms and 400 ms. The result shows the evaluation criteria of the MAE is less than 1 mm at 50 ms and 150 ms, and less than 2 mm at 300 ms. Compared with the AR model, bidirectional LSTM and RVM, our method not only outperforms both models in accuracy (AR: ~ 7.7%; bidirectional LSTM: ~ 75.9%; RVM: ~ 76.5%) but is also more stable on different types of respiratory curves. CONCLUSION: Respiratory motion in the liver in actual clinical practice vary widely from person to person, while sometimes having less distinct periodic patterns. Under these conditions, our algorithm has the advantage of excellent stability for prediction on various sequences, and its running time of performing single sequence prediction can meet clinical requirements.

Exogenous Parathyroid Hormone Alleviates Intervertebral Disc Degeneration through the Sonic Hedgehog Signalling Pathway Mediated by CREB.

As an important hormone that regulates the balance of calcium and phosphorus, parathyroid hormone (PTH) has also been found to have an important function in intervertebral disc degeneration (IVDD). Our aim was to investigate the mechanism by which PTH alleviates IVDD. In this study, the PTH 1 receptor was found to be highly expressed in severely degenerated human nucleus pulposus (NP) cells. We found in the mouse model of IVDD that supplementation with exogenous PTH alleviated the narrowing of the intervertebral space and the degradation of the extracellular matrix (ECM) caused by tail suspension (TS). In addition, inflammation, oxidative stress, and apoptosis levels were significantly increased in the intervertebral disc tissues of TS-induced mice, and the activity of NP cells was decreased. TS also led to the downregulation of Sonic hedgehog (SHH) signalling pathway-related signal molecules in NP cells such as SHH, Smoothened, and GLI1. However, supplementation with exogenous PTH can reverse these changes. In vitro, PTH also promotes the activity of NP cells and the secretion of ECM. However, the antagonist of the SHH signalling pathway can inhibit the therapeutic effect of PTH on NP cells. In addition, a cAMP-response element-binding protein, as an important transcription factor, was found to mediate the promotion of PTH on the SHH signalling pathway. Our results revealed that PTH can alleviate IVDD by inhibiting inflammation, oxidative stress, and apoptosis and improving the activity of NP cells via activating the SHH signalling pathway.

Micro-patterned cell populations as advanced pharmaceutical drugs with precise functional control.

Human cells are both advanced pharmaceutical drugs and 'drug deliverers'. However, functional control prior to or after cell implantation remains challenging. Micro-patterning cells through geometrically defined adhesion sites allows controlling morphogenesis, polarity, cellular mechanics, proliferation, migration, differentiation, stemness, cell-cell interactions, collective cell behavior, and likely immuno-modulatory properties. Consequently, generating micro-patterned therapeutic cells is a promising idea that has not yet been realized and few if any steps have been undertaken in this direction. This review highlights potential therapeutic applications, summarizes comprehensively the many cell functions that have been successfully controlled through micro-patterning, details the established micro-pattern designs, introduces the available fabrication technologies to the non-specialized reader, and suggests a quality evaluation score. Such a broad review is not yet available but would facilitate the manufacturing of therapeutically patterned cell populations using micro-patterned cell-instructive biomaterials for improved functional control as drug delivery systems in the context of cells as pharmaceutical products.

Rebalance of the Polyamine Metabolism Suppresses Oxidative Stress and Delays Senescence in Nucleus Pulposus Cells.

Intervertebral disk degeneration (IDD) is a major cause of low back pain that becomes a prevalent age-related disease. However, the pathophysiological processes behind IDD are rarely known. Here, we used bioinformatics analysis based on the microarray datasets (GSE34095) to identify the differentially expressed genes (DEGs) as biomarkers and therapeutic targets in degenerated discs. From the previous studies, oxidative stress has been notified as a positive inducement of IDD, which causes DNA damage and accelerates cell senescence. Polyamine oxidase (PAOX), a member of the observed 1057 DEGs, is involved in polyamine metabolism and influences the oxidative balance in cells. However, it is uncertain if the IDD is implicated in the dysregulation of PAOX and polyamine metabolism. This study firstly verified the PAOX upregulation in human degenerated disc samples and applied an IL-1ß-induced nucleus pulposus (NP) cell degeneration model to demonstrate that spermidine supplementation balanced polyamine metabolism and delayed NP cell senescence. Moreover, we confirmed that spermidine/N-acetylcysteine supplementation or Cdkn2a gene deletion stabilized the polyamine metabolism, suppressed oxidative stress, and therefore delayed the progress of IDD in older mice. Collectively, our study highlights the role of polyamine metabolism in IDD and foresees spermidine would be the advanced therapeutical drug for IDD.

Differentially expressed tRNA-derived fragments and their roles in primary cardiomyocytes stimulated by high glucose.

Diabetic cardiomyopathy (DCM) is a serious complication of diabetes mellitus that can cause malignant arrhythmia and sudden death and is associated with cardiomyocyte dysfunction induced by hyperglycemia. Emerging evidence has revealed that transfer RNA-derived fragments (tRFs), a novel class of noncoding RNAs, play a crucial role in a variety of pathophysiologic processes, including cell death, cell growth and proliferation. However, it remains unknown whether and how tRFs are involved in cardiomyocyte dysfunction during the progression of DCM. In this study, we found that cardiomyocyte abnormalities were induced by high glucose (HG) treatment, as demonstrated by a decrease in cell viability and autophagy activation as well as an increase in cell death and proinflammatory cytokine release. Moreover, HG treatment resulted in differential expression of tRFs in cardiomyocytes, of which 4 upregulated and 1 downregulated tRFs were observed compared with the control group. The differential expression of 4 upregulated tRFs was primarily involved in cardiac dysfunction-related processes, such as autophagy, AGE-RAGE signaling pathway in diabetic complications, MAPK signaling pathway, insulin signaling pathway, FoxO signaling pathway, insulin resistance and peroxisome pathways based on Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis. Furthermore, we found that tRF-5014a, the most significantly upregulated tRF among all tested tRFs, negatively regulated the expression of the autophagy-related protein ATG5. Importantly, inhibition of tRF-5014a not only abolished autophagy inactivation but also attenuated the decrease in cell viability and increase in cell death as well as proinflammatory cytokine release under HG conditions. These findings suggest that tRFs may contribute to HG-induced cardiomyocyte injury during DCM progression.

Multi-feature Multi-Scale CNN-Derived COVID-19 Classification from Lung Ultrasound Data.

The global pandemic of the novel coronavirus disease 2019 (COVID-19) has put tremendous pressure on the medical system. Imaging plays a complementary role in the management of patients with COVID-19. Computed tomography (CT) and chest X-ray (CXR) are the two dominant screening tools. However, difficulty in eliminating the risk of disease transmission, radiation exposure and not being cost-effective are some of the challenges for CT and CXR imaging. This fact induces the implementation of lung ultrasound (LUS) for evaluating COVID-19 due to its practical advantages of noninvasiveness, repeatability, and sensitive bedside property. In this paper, we utilize a deep learning model to perform the classification of COVID-19 from LUS data, which could produce objective diagnostic information for clinicians. Specifically, all LUS images are processed to obtain their corresponding local phase filtered images and radial symmetry transformed images before fed into the multi-scale residual convolutional neural network (CNN). Secondly, image combination as the input of the network is used to explore rich and reliable features. Feature fusion strategy at different levels is adopted to investigate the relationship between the depth of feature aggregation and the classification accuracy. Our proposed method is evaluated on the point-of-care US (POCUS) dataset together with the Italian COVID-19 Lung US database (ICLUS-DB) and shows promising performance for COVID-19 prediction.

Transmission rate Optimization by dynamic resource allocation algorithm for RF/VLC heterogeneous networks.

In this work, a dynamic resource allocation (DRA) algorithm is proposed to optimize the transmission rate subject to the access point assignment, bandwidth and transmit power allocation in RF/VLC heterogeneous networks, which combines the visible light communication (VLC) access point (AP) and radio frequency (RF) AP. To optimize the allocation among resource block (RB), subchannel and power, the time-average transmission rate is maximized under time-average transmit power budget. Specifically, the time-average optimization problem is converted into series of single timeslot online problem by Lyapunov optimization technique. Because of its complexity and non-convexity, the problem is decomposed into three independent subproblems for which a non-iterative solution is presented on the basis of Lagrange relaxation and convex optimization theory. Numerical simulations are conducted to demonstrate the effectiveness of the proposed DRA algorithm. And the comparisons with two classical algorithms are also given in terms of transmission rate and system stability. This work will benefit the design and development of hybrid RF/VLC system.

Uniformity improvement on received optical power for an indoor visible light communication system with an angle diversity receiver.

In this work, an angle diversity receiver (ADR) structure is proposed to optimize the uniformity of the received optical power distribution in an indoor visible light communication (VLC) system. Taking the rectangular and hybrid layouts with 16 light-emitting diodes as examples, different inclination angles and the number of side detectors are investigated with three diversity combining techniques in a typical room, where the primary reflection of the wall is considered. Simulation results showed that the inclination angles and the number of side detectors would affect the variance and average of the received optical power, and the variance would decrease with the increase of the number of side detectors. In addition, maximal ratio combining is more suitable for the ADR when the variance and average of the received optical power are considered simultaneously. By applying the ADR with five side detectors, the variances of the received optical power will decrease by 81.34% and 86.09% under the rectangle layout and the hybrid layout, respectively. This work will benefit the design and development of the VLC system.