Search

The Pulmonary Function Test (PFT) is an widely utilized and rigorous classification test for lung function evaluation, serving as a comprehensive tool for lung diagnosis. Meanwhile, Electrical Impedance Tomography (EIT) is a rapidly advancing clinical technique that visualizes conductivity distribution induced by ventilation. EIT provides additional spatial and temporal information on lung ventilation beyond traditional PFT. However, relying solely on conventional isolated interpretations of PFT results and EIT images overlooks the continuous dynamic aspects of lung ventilation. This study aims to classify lung ventilation patterns by extracting spatial and temporal features from the 3D EIT image series. The study uses a Variational Autoencoder network with a MultiRes block to compress the spatial distribution in a 3D image into a one-dimensional vector. These vectors are then concatenated to create a feature map for the exhibition of temporal features. A simple convolutional neural network is used for classification. Data collected from 137 subjects were finally used for training. The model is validated by ten-fold and leave-one-out cross-validation first. The accuracy and sensitivity of normal ventilation mode are 0.95 and 1.00, and the f1-score is 0.94. Furthermore, we check the reliability and feasibility of the proposed pipeline by testing it on newly recruited nine subjects. Our results show that the pipeline correctly predicts the ventilation mode of 8 out of 9 subjects. The study demonstrates the potential of using image series for lung ventilation mode classification, providing a feasible method for patient prescreening and presenting an alternative form of PFT.

Image-to-text tasks, such as open-ended image captioning and controllable image description, have received extensive attention for decades. Here, we further advance this line of work by presenting Visual Spatial Description (VSD), a new perspective for image-to-text toward spatial semantics. Given an image and two objects inside it, VSD aims to produce one description focusing on the spatial perspective between the two objects. Accordingly, we manually annotate a dataset to facilitate the investigation of the newly-introduced task and build several benchmark encoder-decoder models by using VL-BART and VL-T5 as backbones. In addition, we investigate pipeline and joint end-to-end architectures for incorporating visual spatial relationship classification (VSRC) information into our model. Finally, we conduct experiments on our benchmark dataset to evaluate all our models. Results show that our models are impressive, providing accurate and human-like spatial-oriented text descriptions. Meanwhile, VSRC has great potential for VSD, and the joint end-to-end architecture is the better choice for their integration. We make the dataset and codes public for research purposes.

Non-small cell lung cancer (NSCLC) is the leading cause of cancer-related death due to its early recurrence and widespread metastatic potential. Accumulating studies have reported that dysregulation of circadian rhythms-associated regulators is implicated in the recurrence and metastasis of NSCLC. Therefore, identification of metastasis-associated circadian rhythm genes is clinically necessary. Here we report that the circadian gene hepatic leukemia factor (HLF), which was dramatically reduced in early-relapsed NSCLC tissues, was significantly correlated with early progression and distant metastasis in NSCLC patients. Upregulating HLF inhibited, while silencing HLF promoted lung colonization, as well as metastasis of NSCLC cells to bone, liver and brain in vivo. Importantly, downexpression of HLF promoted anaerobic metabolism to support anchorage-independent growth of NSCLC cells under low nutritional condition by activating NF-κB/p65 signaling through disrupting translocation of PPARα and PPARγ. Further investigations revealed that both genetic deletion and methylation contribute to downexpression of HLF in NSCLC tissues. In conclusion, our results shed light on a plausible mechanism by which HLF inhibits distant metastasis in NSCLC, suggesting that HLF may serve as a novel target for clinical intervention in NSCLC.

The impact of voltage sags on industry consumer has attracted more and more attention. Therefore, it is important to propose a risk assessment method of voltage sag for users. Due to the fuzziness of industrial users' response to sag events, most of the existing studies adopt the method of measuring the economic loss of voltage sag based on equipment tolerance. This method does not take into account the user-perceived voltage sag effect and the impact of voltage sag on industrial users in addition to economic losses. Based on the impact of voltage sag on the structure, function, economy and safety of user industry, a risk assessment method of voltage sag based on process immune events is proposed. This method can consider the temporary risk more completely.

Voltage sag have a significant impact on sensitive equipment and cause economic losses to users. Due to different power system conditions and load conditions, VTC (Voltage Tolerance Curve) of sensitive equipment has an area of uncertainty, so the fault condition of sensitive equipment is difficult to determine. In this paper, an equipment sensitivity evaluation method based on kernel density estimation is proposed. This method evaluates the probability density function of VTC based on the sample data of VTC without making any subjective assumptions about the distribution. Adjustable speed drive is taken as an example, and the proposed method is compared with the traditional method in case studies. The results show that the proposed method has smaller evaluation error and better adaptability compared with the traditional methods.

Embedding entities and relations into a continuous multi-dimensional vector space have become the dominant method for knowledge graph embedding in representation learning. However, most existing models ignore to represent hierarchical knowledge, such as the similarities and dissimilarities of entities in one domain. We proposed to learn a Domain Representations over existing knowledge graph embedding models, such that entities that have similar attributes are organized into the same domain. Such hierarchical knowledge of domains can give further evidence in link prediction. Experimental results show that domain embeddings give a significant improvement over the most recent state-of-art baseline knowledge graph embedding models., Comment: Acceptted by NLPCC2019