Search

The morbidity of pulmonary embolism (PE) is only lower than that of coronary heart disease and hypertension. Early detection, early diagnosis, and timely treatment are the keys to effectively reduce the risk of death. Nevertheless, PE segmentation is still a challenging task at present. The automatic segmentation of PE is particularly important. On the one hand, manual segmentation of PE from a computed tomography (CT) sequence is very time-consuming and prone to misdiagnose. On the other hand, an accurate contour of the location, volume, and shape of PE can help radiotherapists carry out targeted treatment and thus greatly increase the survival rate of patients. Therefore, developing an automatic and efficient PE segmentation approach is an urgent demand in clinical diagnosis.An accurate segmentation of PE is critical for the diagnosis of PE. However, it remains a difficult and relevant problem in the field of medical image processing due to factors like incongruent sizes and shapes of emboli regions, and low contrast between embolisms and other tissues. To address this conundrum, in this study, a deep neural network (CAM-Wnet) that incorporates coordinate attention (CA) mechanisms and pyramid pooling modules (PPMs) is proposed to end-to-end segment PE from CT image.CAM-Wnet architecture is composed of coarse U-Net and subdivision U-Net stacked on top of each other. First, the coarse U-Net uses a pretrained VGG-19 as an encoder, which can transfer the features learned from ImageNet to other tasks. At the same time, CA residual blocks (CARBs) are introduced into the decoder of the coarse network to obtain a wider range of semantic information and find out the correlation between channels. Then, the multiplied results of input image and preliminary mask are put into the subdivision U-Net for secondary feature distillation, and the encoder and decoder of the subdivision U-Net are both constructed from CARBs, too. The PPMs are used between the encoder and the decoder of two U-Net architectures to utilize global context information and further enhance the feature extraction effect. Finally, the improved focal loss function is used to train the network to further improve the segmentation effect.In this study, we used the doctors' manual contours of the China-Japan Friendship Hospital dataset to test the proposed architecture. We calculated the Precision, Recall, IoU, and F1-score to evaluate the accuracy of the architecture for PE segmentation. The segmentation Precision for PE was found to be 0.9703, Recall was 0.963, IoU was 0.9353, and F1-score was 0.9665. The experimental results show the effectiveness of the proposed method to automatically and accurately segment embolism in lung CT images. Furthermore, we also test the performance of our method on the liver tumor segmentation public dataset, which demonstrates the effectiveness and generalization ability of our method.CAM-Wnet obtained more global information and semantic information with the introduction of multiscale pooling and attention mechanisms. Experimental results showed that the proposed method effectively improved the segmentation effect of PE in lung CT images and could be applied to assist doctors in clinical treatment.

Water is one of the most significant factors influencing the mechanical properties of rocks. Triaxial unloading acoustic emission (AE) tests were performed to study the unloading mechanical characteristics and damage evolution mechanism of shale with various water contents. The damage evolution characteristics of shale under triaxial unloading conditions were analyzed using AE time series parameters. The results show that when the water saturation coefficient rises, the number of AE rings and the energy value of shale decrease. Based on the results of the AE test, the ratios of the crack initiation stress and damage stress to the peak stress are 0.4 ~ 0.6 and 0.9, respectively. The closure stress, crack initiation stress, damage stress, and other characteristic stresses determined by the stress axial strain method and the AE method all decrease with the increase of the water saturation coefficient, demonstrating that water has a significant impact on the mechanical characteristics of the shale during the unloading damage and damage process. Based on the test results, a statistical damage constitutive model is established, and it uses the AE cumulative ringing count to represent the damage variable. The calculated results of the model are in good agreement with the experimental data, indicating that the established model can more accurately depict the evolution process of shale unloading damage and failure under different water contents. The study's findings can be used as a reference for determining the extent of rock damage caused by water-rock interaction.

Understanding the mechanisms of candidate drugs play an important role in drug discovery. The activating/inhibiting mechanisms between drugs and targets are major types of mechanisms of drugs. Owing to the complexity of drug–target (DT) mechanisms and data scarcity, modelling this problem based on deep learning methods to accurately predict DT activating/inhibiting mechanisms remains a considerable challenge. Here, by considering network pharmacology, we propose a multi-view deep learning model, DrugAI, which combines four modules, i.e. a graph neural network for drugs, a convolutional neural network for targets, a network embedding module for drugs and targets and a deep neural network for predicting activating/inhibiting mechanisms between drugs and targets. Computational experiments show that DrugAI performs better than state-of-the-art methods and has good robustness and generalization. To demonstrate the reliability of the predictive results of DrugAI, bioassay experiments are conducted to validate two drugs (notopterol and alpha-asarone) predicted to activate TRPV1. Moreover, external validation bears out 61 pairs of mechanism relationships between natural products and their targets predicted by DrugAI based on independent literatures and PubChem bioassays. DrugAI, for the first time, provides a powerful multi-view deep learning framework for robust prediction of DT activating/inhibiting mechanisms.

Motivation: This paper proposes a motion artifact removal (MAR) algorithm and its evaluation method for wearable functional near infrared spectroscopy (fNIRS) system. Methods: Two types of motion artifacts (MAs) and their characteristics have been investigated, and a coarse/fine dual-stage MAR method is proposed, which can remove the MAs with different features and magnitudes to protect the original data from damage. In addition, an evaluation method is also proposed based on the classification of 4 mental tasks, which objectively quantize the performance of the MAR algorithms. Results: With the proposed MAR algorithm, the mental-task classification accuracy increased from 74.73% to 83.70% in average.

Computer-aided detection of pulmonary embolism is an important technology method for diagnosing pulmonary embolism, which can help doctors diagnose quickly and save a lot of manpower. However, due to the small area of pulmonary embolism in the Computed Tomography Pulmonary Angiography (CTPA) slice images, some previous methods for detecting pulmonary embolism have a high number of false detection and missed detection. This study proposes a detection method of pulmonary embolism based on the improved faster region-based convolutional neural network (Faster R-CNN) named More Accurate Faster R-CNN (MA Faster R-CNN). A new feature fusion network named Multi-scale Fusion Feature Pyramid Network (MF-FPN) is proposed by extending and adding two bottom-up paths on the Feature Pyramid Network (FPN). It enhances the feature extraction capability of the entire network by transmitting low-level accurate location information, and makes up for the original information lost after multiple down-sampling, strengthens the use of detailed information, which is more helpful to the detection of small object. In the prediction module, the residual block is added before the fully-connected layer to deepen the network and enhance the classification accuracy, named residual prediction module (RPM). Compared with the original Faster R-CNN, the proposed MA Faster R-CNN which combines MF-FPN and RPM has a higher detection precision and solves the problems of false detection and missed detection of pulmonary embolism effectively. The average precision (AP) reached 85.88% on the CTPA pulmonary embolism dataset used in this article.

Background Shen-Zhi-Ling oral liquid (SZL) is an herbal formula known for its efficacy of nourishing “heart and spleen”, and is used for the treatment and prevention of middle- and early-stage dementia. This study investigated the effects of SZL on amelioration of AD, and examined whether the underlying mechanisms from the perspective of neuroprotection are related to brain glucose metabolism. Methods Firstly, LC–MS/MS was used to analysis the SZL mainly enters the blood component. Then, the effects of SZL on cognitive and behavioral ability of APP/PS1 double transgenic mice and amyloid protein characteristic pathological changes were investigated by behavioral study and morphological observation. The effects of SZL on the ultrastructure of mitochondria, astrocytes, and micrangium related to cerebral glucose metabolism were observed using transmission electron microscopy. Then, micro-PET was also used to observe the effects of SZL on glucose uptake. Furthermore, the effects of SZL on insulin signaling pathway InR/PI3K/Akt and glucose transporters (GLUT1 and GLUT3) were observed by immunohistochemistry, Western-blot and RT-qPCR. Finally, the effects of SZL on brain glucose metabolism and key enzyme were observed. In vitro, the use of PI3K and/or GSK3β inhibitor to observe the effects of SZL drug-containing serum on GLUT1 and GLUT3. Results In vivo, SZL could significantly ameliorate cognitive deficits, retarded the pathological damage, including neuronal degeneration, Aβ peptide aggregation, and ultrastructural damage of hippocampal neurons, improve the glucose uptake, transporters and glucolysis. Beyond that, SZL regulates the insulin signal transduction pathway the insulin signal transduction pathway InR/PI3K/Akt. Furthermore, 15% SZL drug-containing serum increased Aβ42-induced insulin signal transduction-pathway related indicators and GLUT1 and GLUT3 expression in SH-SY5Y cells. The improvement of GLUT1 and GLUT3 in the downstream PI3K/Akt/GSK3β signaling pathway was reversed by the use of PI3K and/or GSK3β inhibitor. Conclusions In summary, our results demonstrated that improving glucose uptake, transport, and glycolysis in the brain may underlie the neuroprotective effects of SZL, and its potential molecular mechanism may be related to regulate the insulin signal transduction pathway.

Most forms of Alzheimer’s disease are sporadic. A model of sporadic Alzheimer’s disease induced with bilateral intraventricular injection of streptozotocin leads to insulin resistance in the brain accompanied by memory decline, synaptic dysfunction, amyloid plaque deposition, oxidative stress, and neuronal apoptosis, all of which mimic the pathologies associated with sporadic Alzheimer’s disease. Myelin injury is an essential component of Alzheimer’s disease, playing a key role in early cognitive impairment. Our previously research found that sporadic Alzheimer’s disease model showed myelin injury and that Shenzheling oral solution improved mild-to-moderate Alzheimer’s disease; therefore, the protective effect of Shenzheling oral solution on myelin injury in early cognitive impairment is worth attention. In this study, the Morris water maze test results showed impairments in the learning and memory functions of mice in the model group, whereas the learning and memory function significantly improved after drug intervention. Immunohistochemistry showed increased β-amyloid plaques in the model group and decreased amounts in the drug group. Moreover, results of electron microscopy, western blot, and polymerase chain reaction showed that Shenzhiling oral solution improved early cognitive impairment and repaired myelin sheath damage; the potential mechanism of these effects may relate to the PI3K/Akt-mTOR signaling pathway. These findings support the application and promotion of Shenzhiling oral solution to treat sporadic Alzheimer’s disease. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s13205-021-02900-x.

Functional near-infrared spectroscopy (fNIRS) is considered as a non-invasive and effective brain-computer interface technology. Wearable high-resolution fNIRS requires a large-scale LED array, which consumes a lot of power, and shorten the battery life. This paper proposes a spatial adaptive sampling (SAS) method that can take advantage of the spatial sparsity of fNIRS devices and greatly reduce the power consumption while maintaining high image quality. To improve the performance of the proposed SAS technique, a low power binary neural network (BNN) is proposed to accurately predict the current brain task. And the optimal dynamic LED pattern for each brain task is investigated. The proposed SAS technique is validate through an off-line experiment, it can reduce the power consumption of the LED array by 62.5% compared to not using SAS technology while maintaining a PSNR (Peak Signal to Noise Ratio) of 33 dB.

Objective Our aim was to evaluate the efficacy and safety of intracoronary autologous bone marrow mesenchymal stem cell (BM-MSC) transplantation in patients with ST-segment elevation myocardial infarction (STEMI). Methods In this randomized, single-blind, controlled trial, patients with STEMI (aged 39–76 years) were enrolled at 6 centers in Beijing (The People’s Liberation Army Navy General Hospital, Beijing Armed Police General Hospital, Chinese People’s Liberation Army General Hospital, Beijing Huaxin Hospital, Beijing Tongren Hospital, Beijing Chaoyang Hospital West Hospital). All patients underwent optimum medical treatment and percutaneous coronary intervention and were randomly assigned in a 1:1 ratio to BM-MSC group or control group. The primary endpoint was the change of myocardial viability at the 6th month’s follow-up and left ventricular (LV) function at the 12th month’s follow-up. The secondary endpoints were the incidence of cardiovascular event, total mortality, and adverse event during the 12 months’ follow-up. The myocardial viability assessed by single-photon emission computed tomography (SPECT). The left ventricular ejection fraction (LVEF) was used to assess LV function. All patients underwent dynamic ECG and laboratory evaluations. This trial is registered with ClinicalTrails.gov, number NCT04421274. Results Between March 2008 and July 2010, 43 patients who had underwent optimum medical treatment and successful percutaneous coronary intervention were randomly assigned to BM-MSC group (n = 21) or control group (n = 22) and followed-up for 12 months. At the 6th month’s follow-up, there was no significant improvement in myocardial activity in the BM-MSC group before and after transplantation. Meanwhile, there was no statistically significant difference between the two groups in the change of myocardial perfusion defect index (p = 0.37) and myocardial metabolic defect index (p = 0.90). The LVEF increased from baseline to 12 months in the BM-MSC group and control group (mean baseline-adjusted BM-MSC treatment differences in LVEF 4.8% (SD 9.0) and mean baseline-adjusted control group treatment differences in LVEF 5.8% (SD 6.04)). However, there was no statistically significant difference between the two groups in the change of the LVEF (p = 0.23). We noticed that during the 12 months’ follow-up, except for one death and one coronary microvascular embolism in the BM-MSC group, no other events occurred and alanine transaminase (ALT) and C-reactive protein (CRP) in BM-MSC group were significantly lower than that in the control group. Conclusions The present study may have many methodological limitations, and within those limitations, we did not identify that intracoronary transfer of autologous BM-MSCs could largely promote the recovery of LV function and myocardial viability after acute myocardial infarction.

Ethnopharmacological relevance Shenzhiling oral liquid (SZL), a traditional Chinese medicine (TCM) compound, is firstly approved by the Chinese Food and Drug Administration (CFDA) for the treatment of mild to moderate Alzheimer's disease (AD). SZL is composed of ten Chinese herbs, and the precise therapy mechanism of its action to AD is far from fully understood. Aim of the study The purpose of this study was to observe whether SZL is an effective therapy for amyloid-beta (Aβ)-induced myelin sheath and oligodendrocytes impairments. Notably, the primary aim was to elucidate whether and through what underlying mechanism SZL protects the myelin sheath through the PI3K/Akt-mTOR signaling pathway in Aβ42-induced OLN-93 oligodendrocytes in vitro. Materials and methods APP/PS1 mice were treated with SZL or donepezil continuously for three months, and Aβ42-induced oligodendrocyte OLN-93 cells mimicking AD pathogenesis of myelin sheath impairments were incubated with SZL-containing serum or with donepezil. LC-MS/MS was used to analysis the active components of SZL and SZL-containing serum. The Y maze test was administered after 3 months of treatment, and the hippocampal tissues of the APP/PS1 mice were then harvested for observation of myelin sheath and oligodendrocyte morphology. Cell viability and toxicity were assessed using CCK-8 and lactate dehydrogenase (LDH) release assays, and flow cytometry was used to measure cell apoptosis. The expression of the myelin proteins MBP, PLP, and MAG and that of Aβ42 and Aβ40 in the hippocampi of APP/PS1 mice were examined after SZL treatment. Simultaneously, the expression of p-PI3K, PI3K, p-Akt, Akt, p-mTOR, and mTOR were also examined. The expression of proteins, including CNPase, Olig2, NKX2.2, MBP, PLP, MAG, MOG, p-PI3K, PI3K, p-Akt, Akt, p-mTOR, and mTOR, was determined by immunofluorescence and Western blot, and the corresponding gene expression was evaluated by qPCR in Aβ42-induced OLN-93 oligodendrocytes. Results LC-MS/MS detected a total of 126 active compounds in SZL-containing serum, including terpenoids, flavones, phenols, phenylpropanoids and phenolic acids. SZL treatment significantly improved memory and cognition in APP/PS1 mice and decreased the G-ratio of myelin sheath, alleviated myelin sheath and oligodendrocyte impairments by decreasing Aβ42 and Aβ40 accumulation and increasing the expression of myelin proteins MBP, PLP, MAG, and PI3K/Akt-mTOR signaling pathway associated protein in the hippocampi of APP/PS1 mice. SZL-containing serum also significantly reversed the OLN-93 cell injury induced by Aβ42 by increasing cell viability and enhanced the expression of MBP, PLP, MAG, and MOG. Meanwhile, SZL-containing serum facilitated the maturation and differentiation of oligodendrocytes in Aβ42-induced OLN-93 cells by heightening the expression of CNPase, Olig2 and NKX2.2. SZL-containing serum treatment also fostered the expression of p-PI3K, PI3K, p-Akt, Akt, p-mTOR, and mTOR, indicating an activating PI3K/Akt-mTOR signaling pathway in OLN-93 cells. Furthermore, the effects of SZL on myelin proteins, p-Akt, and p-mTOR were clearly inhibited by LY294002 and/or rapamycin, antagonists of PI3K and m-TOR, respectively. Conclusions Our findings indicate that SZL exhibits a neuroprotective effect on the myelin sheath by promoting the expression of myelin proteins during AD, and its mechanism of action is closely related to the activation of the PI3K/Akt-mTOR signaling pathway.

Background Cholinergic dysfunction and oxidative stress are the crucial mechanisms of Alzheimer's disease (AD). GAPT, also called GEPT (a combination of several active components extracted from the Chinese herbs ginseng, epimedium, polygala and tuber curcumae) or Jinsiwei, is a patented Chinese herbal compound, has been clinically widely used to improve learning and memory impairment, but whether it can play a neuroprotective role by protecting cholinergic neurons and reducing oxidative stress injury remains unclear. Methods Male ICR mice were intraperitoneally injected with scopolamine (3 mg/kg) to establish a learning and memory disordered model. An LC‐MS method was established to study the chemical compounds and in vivo metabolites of GAPT. After scopolamine injection, a step‐down passive‐avoidance test (SDPA) and a Y maze test were used to estimate learning ability and cognitive function. In addition, ELISA detected the enzymatic activities of acetylcholinesterase (AChE), acetylcholine (ACh), choline acetyltransferase (ChAT), malondialdehyde (MDA), glutathione peroxidase (GPX), and total superoxide dismutase (T‐SOD). The protein expressions of AChE, ChAT, SOD1, and GPX1 were observed by western blot, and the distribution of ChAT, SOD1, and GPX1 was observed by immunohistochemical staining. Results After one‐half or 1 month of intragastric administration, GAPT can ameliorate scopolamine‐induced behavioral changes in learning and memory impaired mice. It can also decrease the activity of MDA and protein expression level of AChE, increase the activity of Ach, and increase activity and protein expression level of ChAT, SOD, and GPX in scopolamine‐treated mice. After one and a half month of intragastric administration of GAPT, echinacoside, salvianolic acid A, ginsenoside Rb1, ginsenoside Rg2, pachymic acid, and beta asarone could be absorbed into mice blood and pass through BBB. Conclusions GAPT can improve the learning and memory ability of scopolamine‐induced mice, and its mechanism may be related to protecting cholinergic neurons and reducing oxidative stress injury., GAPT can improve the learning and memory ability of scopolamine‐induced mice, and its mechanism may be related to protecting cholinergic neurons and reducing oxidative stress injury.