Intelligent ultrasound imaging based on deep learning is one of the important applications in the field of intelligent medical care. In this article, we propose an automatic fetal ultrasound standard ...plane recognition (FUSPR) model based on deep learning in the Industrial Internet of Things (IIoT) environment. We build a distributed ultrasound data processing and predicting platform by using the IIoT and high-performance computing (HPC) technology. The FUSPR model deployed in the HPC center consists of a convolutional neural network (CNN) component and a recurrent neural network (RNN) component, which learns the spatial and temporal features of the ultrasound video stream by using multitask learning, respectively. The CNN component identifies fetal key anatomical structures from each video frame and accurately recognizes the potential four fetal standard planes. The RNN component obtains the temporal information between adjacent frames, and it realizes precise localization and tracking of fetal organs across frames. In addition, we introduce two feature fusion strategies into the FUSPR model, i.e., CNN fusion and RNN fusion, to fit the spatial sequence and motion representation in the video stream, thereby effectively improving the accuracy and robustness of the model. Extensive experiments conducted on more than 1000 ultrasound videos show that the FUSPR model is superior to the competing baselines in terms of accuracy and performance.
Circular RNAs (circRNAs) are 3'-5' covalently closed RNA rings produced from back-splicing of precursor mRNA in eukaryotes. Recent studies, using both computational and experimental approaches, have ...allowed advanced characterization of circRNAs, leading the research field into a new era and shedding light on the contribution of circRNAs to disease.
Abstract
Exosomes, which are nanosized endocytic vesicles that are secreted by most cells, contain an abundant cargo of different RNA species that can modulate the behavior of recipient cells and may ...be used as circulating biomarkers for diseases. Here, we develop a web-accessible database (http://www.exoRBase.org), exoRBase, which is a repository of circular RNA (circRNA), long non-coding RNA (lncRNA) and messenger RNA (mRNA) derived from RNA-seq data analyses of human blood exosomes. Experimental validations from the published literature are also included. exoRBase features the integration and visualization of RNA expression profiles based on normalized RNA-seq data spanning both normal individuals and patients with different diseases. exoRBase aims to collect and characterize all long RNA species in human blood exosomes. The first release of exoRBase contains 58 330 circRNAs, 15 501 lncRNAs and 18 333 mRNAs. The annotation, expression level and possible original tissues are provided. exoRBase will aid researchers in identifying molecular signatures in blood exosomes and will trigger new exosomal biomarker discovery and functional implication for human diseases.
Consumers’ software purchase decisions are influenced both by online reviews and by their experiences with free samples provided by firms. This paper empirically investigates the differential effects ...of online reviews (user and editor ratings) on consumers’ sample downloading behavior, using a dataset drawn from a large software free sampling website CNET.com. Our findings extend the previous research by suggesting that information disclosure levels of free samples (indicated by licenses) moderates the impacts of online reviews on consumers’ sample downloads. For samples that disclose a great level of information, higher user ratings can increase downloads; otherwise, higher user ratings fail to increase downloads. When both user and editor ratings are available to consumers, only user ratings can increase sample downloads. The findings can be explained by consumers’ two-stage information process whereby consumers first refer to online reviews and then determine whether to sample software. This study provides practical implications on the design of information disclosure channel and offers suggestions for firms regarding how to select and apply sample licenses.
Cervical cancer (CC) is the fourth leading cause of deaths in gynecological malignancies. Although the etiology of CC has been extensively investigated, the exact pathogenesis of CC remains ...incomplete. Recently, single-cell technologies demonstrated advantages in exploring intra-tumoral diversification among various tumor cells. However, single-cell transcriptome analysis (single-cell RNA sequencing scRNA-seq) of CC cells and microenvironment has not been conducted. In this study, a total of 20,938 cells from CC and adjacent normal tissues were examined by scRNA-seq. We identified four tumor cell subpopulations in tumor cells, which had specific signature genes with different biological functions and presented different prognoses. Among them, we identified a subset of cancer stem cells (CSCs) that was related to the developmental hierarchy of tumor progression. Then, we compared the expressive differences between tumor-derived endothelial cells (TECs) and normal ECs (NECs) and revealed higher expression of several metabolism-related genes in TECs. Then, we explored the potential biological function of ECs in vascularization and found several marker genes, which played a prior role in connections between cancer cells and ECs. Our findings provide valuable resources for deciphering the intra-tumoral heterogeneity of CC and uncover the developmental procedure of ECs, which paves the way for CC therapy.
Display omitted
This study characterizes intra-tumor heterogeneity and developmental procedures of cervical cancer (CC) at single-cell resolution and provides valuable resources for therapeutic strategies of CC.
In this article, sulfonic acid-grafted reduced graphene oxide (S-rGO) were synthesized using a one-pot method under mild conditions, and used as Pt catalyst supports to prepare Pt/S-rGO ...electrocatalysts through a self-assembly route. The structure, morphologies and physicochemical properties of S-rGO were examined in detail by techniques such as atomic force microscope (AFM), transmission electron microscopy (TEM) and X-ray photoelectron spectroscopy (XPS). The S-rGO nanosheets show excellent solubility and stability in water and the average particle size of Pt nanoparticles supported on S-rGO is ~3.8 nm with symmetrical and uniform distribution. The electrocatalytic properties of Pt/S-rGO were investigated for methanol oxidation reaction (MOR) in direct methanol fuel cells (DMFCs). In comparison to Pt supported on high surface area Vulcan XC-72 carbon (Pt/VC) and Pt/rGO, the Pt/S-rGO electrocatalyst exhibits a much higher electrocatalytic activity, faster reaction kinetics and a better stability. The results indicate that Pt/S-rGO is a promising and effective electrocatalyst for MOR of DMFCs.
Recurrent chromosomal aberrations have led to the discovery of oncogenes or tumour suppressors involved in carcinogenesis. Here we characterized an oncogenic long intergenic non-coding RNA in the ...frequent DNA-gain regions in hepatocellular carcinoma (HCC), LINC01138 (long intergenic non-coding RNA located on 1q21.2). The LINC01138 locus is frequently amplified in HCC; the LINC01138 transcript is stabilized by insulin like growth factor-2 mRNA-binding proteins 1/3 (IGF2BP1/IGF2BP3) and is associated with the malignant features and poor outcomes of HCC patients. LINC01138 acts as an oncogenic driver that promotes cell proliferation, tumorigenicity, tumour invasion and metastasis by physically interacting with arginine methyltransferase 5 (PRMT5) and enhancing its protein stability by blocking ubiquitin/proteasome-dependent degradation in HCC. The discovery of LINC01138, a promising prognostic indicator, provides insight into the molecular pathogenesis of HCC, and the LINC01138/PRMT5 axis is an ideal therapeutic target for HCC treatment.
Automatic localization of the standard plane containing complicated anatomical structures in ultrasound (US) videos remains a challenging problem. In this paper, we present a learning-based approach ...to locate the fetal abdominal standard plane (FASP) in US videos by constructing a domain transferred deep convolutional neural network (CNN). Compared with previous works based on low-level features, our approach is able to represent the complicated appearance of the FASP and hence achieve better classification performance. More importantly, in order to reduce the overfitting problem caused by the small amount of training samples, we propose a transfer learning strategy, which transfers the knowledge in the low layers of a base CNN trained from a large database of natural images to our task-specific CNN. Extensive experiments demonstrate that our approach outperforms the state-of-the-art method for the FASP localization as well as the CNN only trained on the limited US training samples. The proposed approach can be easily extended to other similar medical image computing problems, which often suffer from the insufficient training samples when exploiting the deep CNN to represent high-level features.
The Bohai Bay Basin, a typical intracontinental rift basin, records East Asia's kinematic plate history during the Cenozoic. The rifting process was driven by the counterclockwise rotation in the ...direction of the Pacific Plate subduction. From the early Eocene to the Oligocene, the rifting process can be divided into three stages: extension initiation, peak extension, and post-extension. The corresponding rifting rate was calculated based on 40Ar-39Ar data. Then, the provenance area evolution of the above three rifting stages was established by combining the detrital zircon U–Pb data and heavy mineral assemblage data (ZTR, GZi, and ATi). According to the results calculated by 40Ar/39Ar analysis, the topography of the sink area in the western Bohai bay basin was characterized by moderately rising subsidence rates (100 m/Ma) during the extension initiation stage (Paleocene-Early Eocene), when surface drainage was restricted to a limited area with steep channel slopes. During this stage, referring to the core description and seismic interpretation results, the fan delta distributes most of the sediment, most of which migrates from the proximal region. Until the peak extension stage, the source-sink system develops as the rate of subsidence increases (200 m/Ma), making the sink area larger, and this period involves multiple types of pathways, including synsedimentary faults and erosional valleys. Sediments from Taihang Massif and Jiaoliao Massif infill the subsidence zone at the distal end. Then, in the post-extension stage, the source-sink systems involve a multi-provenance area (i.e., sourcing from both proximal and distal areas), a large sink area, and a gentle channel gradient due to a decrease in subsidence rate (60–80 m/Ma). Catchment relief, sediment migration distance, and average fault displacement were used, and these parameters were related to the sediment supply (Qs) for the three rifting stages. We find that during extension initiation and peak extension, the source-to-sink systems show a high amount of sand influx (Qsand/) and that the ratio Qsand/Qs total shows a proportional relationship with catchment relief and average fault displacement; this relationship is inversely proportional to the catchment-unit area. Also, according to the types of pathways, we classified the source-to-sink systems during this period into three types, steep eroded pathway (Type-I S2S), gentle slope developed with several boundary faults (Type-II S2S), steep slope with observably eroded valleys or fault-troughs (Type-III S2S). The ratio of Qsand/Qs is only related to the sediment migration distance and average fault displacement in the post-extension stage. Besides the above three types of source-to-sink systems, we found that multi-stage faults developed along the slope (Type-IV S2S) predominated during this stage.
•Calculated rifting rate in Bozhong Depression.•Identified the provenance area evolution in Bozhong Depression during Paleogene.•Classified four types of Source-to-sink patterns corresponding to the rifting stage.•Put out the dominated factors to S2S system developed during various rifting stages.
•The three time monitoring parameters PDT, HDT, HLT are determined.•The characteristics of several common AE parameters are discussed.•Low frequency components dominate at the failure stage.•AE ...signals with high amplitude and high energy in the low-frequency can predict the failure.
Damage assessment of masonry buildings in service is the key to structural health monitoring. A uniaxial compression test of brick masonry specimens based on acoustic emission (AE) technology was conducted to monitor and assess the dynamic damage and failure mechanisms of masonry structures under load in real time. The variation characteristics of the ringing counts, energy, and peak frequency of the AE characteristic parameters of the masonry specimens during the entire uniaxial compression process were collected and recorded, and the reference values of the time parameters of AE monitoring were determined. Results showed that the number of AE ringing counts increased sharply and the slope of the cumulative energy curve increased remarkably at the final failure stage of the brick masonry specimens under compression. In addition, the component ratio of the peak frequency in the low-frequency band increased and that of the peak frequency in the high-frequency band decreased. The damage status of the masonry structures could be predicted qualitatively by the AE signals with high energy in the low-frequency band. The ringing counts of the AE sensors at different locations on the masonry specimens were compared, and the rationalities of the position and number of AE sensors fixed on the brick masonry specimens in the uniaxial compression test were discussed.