A novel attention-guided ECA-CNN architecture for sEMG-based gait classification.

Gait recognition and classification technology is one of the essential technologies for detecting neurodegenerative dysfunction. This paper presents a gait classification model based on a convolutional neural network (CNN) with an efficient channel attention (ECA) module for gait detection applications using surface electromyographic (sEMG) signals. First, the sEMG sensor was used to collect the experimental sample data, and various gaits of different persons were collected to construct the sEMG signal data sets of different gaits. The CNN is used to extract the features of the one-dimensional input sEMG signal to obtain the feature vector, which is input into the ECA module to realize cross-channel interaction. Then, the next part of the convolutional layer is input to learn the signal features further. Finally, the model is output and tested to obtain the results. Comparative experiments show that the accuracy of the ECA-CNN network model can reach 97.75%.

Mining whole-lung information by artificial intelligence for predicting EGFR genotype and targeted therapy response in lung cancer: a multicohort study.

BACKGROUND: Epidermal growth factor receptor (EGFR) genotype is crucial for treatment decision making in lung cancer, but it can be affected by tumour heterogeneity and invasive biopsy during gene sequencing. Importantly, not all patients with an EGFR mutation have good prognosis with EGFR-tyrosine kinase inhibitors (TKIs), indicating the necessity of stratifying for EGFR-mutant genotype. In this study, we proposed a fully automated artificial intelligence system (FAIS) that mines whole-lung information from CT images to predict EGFR genotype and prognosis with EGFR-TKI treatment. METHODS: We included 18 232 patients with lung cancer with CT imaging and EGFR gene sequencing from nine cohorts in China and the USA, including a prospective cohort in an Asian population (n=891) and The Cancer Imaging Archive cohort in a White population. These cohorts were divided into thick CT group and thin CT group. The FAIS was built for predicting EGFR genotype and progression-free survival of patients receiving EGFR-TKIs, and it was evaluated by area under the curve (AUC) and Kaplan-Meier analysis. We further built two tumour-based deep learning models as comparison with the FAIS, and we explored the value of combining FAIS and clinical factors (the FAIS-C model). Additionally, we included 891 patients with 56-panel next-generation sequencing and 87 patients with RNA sequencing data to explore the biological mechanisms of FAIS. FINDINGS: FAIS achieved AUCs ranging from 0·748 to 0·813 in the six retrospective and prospective testing cohorts, outperforming the commonly used tumour-based deep learning model. Genotype predicted by the FAIS-C model was significantly associated with prognosis to EGFR-TKIs treatment (log-rank p<0·05), an important complement to gene sequencing. Moreover, we found 29 prognostic deep learning features in FAIS that were able to identify patients with an EGFR mutation at high risk of TKI resistance. These features showed strong associations with multiple genotypes (p<0·05, t test or Wilcoxon test) and gene pathways linked to drug resistance and cancer progression mechanisms. INTERPRETATION: FAIS provides a non-invasive method to detect EGFR genotype and identify patients with an EGFR mutation at high risk of TKI resistance. The superior performance of FAIS over tumour-based deep learning methods suggests that genotype and prognostic information could be obtained from the whole lung instead of only tumour tissues. FUNDING: National Natural Science Foundation of China.

A generative adversarial network-based CT image standardization model for predicting progression-free survival of lung cancer.

Progression-free survival (PFS) prediction using computed tomography (CT) images is important for treatment planning in lung cancer. However, the generalization ability of current analysis methods is usually affected by the scanning parameters of CT images, such as slice thickness and reconstruction kernel. In this paper, we proposed a generative adversarial network (GAN)-based model to convert heterogenous CT images into standardized CT images with uniform slice thickness and reconstruction kernel to increase the generalization of the predictive model. This model was trained in 173 patients with multiple CT sequences including both thin/thick voxel-spacing and sharp/soft reconstruction kernel. Afterward, we built a 3D-CNN model to predict the individualized 1year PFS of lung cancer using the standardized CT images in 281 patients. Finally, we evaluated the predictive model by 5-fold cross-validation and the mean area under the receiver operating characteristic curve (AUC). After transforming to the heterogenous CT images into the uniform thin-spacing and sharp kernel CT images, the AUC value of the 3D-CNN model improved from 0.614 to 0.686. Furthermore, this model can stratify the patients into high-risk and low-risk groups, where patients in these two groups showed significant difference in PFS (P < 0.001).

Quercitrin Rapidly Alleviated Depression-like Behaviors in Lipopolysaccharide-Treated Mice: The Involvement of PI3K/AKT/NF-κB Signaling Suppression and CREB/BDNF Signaling Restoration in the Hippocampus.

Quercitrin (Qc) is a well-known flavonoid compound that exerts anti-inflammation effects on various diseases. The present study aimed to investigate the antidepressant-like response of Qc and its underlying mechanisms concerning neuroinflammation and neuroplasticity in mice with lipopolysaccharide (LPS)-induced depression-like behaviors. The results showed a single dose of Qc (10 mg/kg) produced an antidepressant-like effect at 2 h postadministration and lasted for at least 3 days. The expressions of neuroplasticity signaling molecules of pCREB/BDNF/PSD95/Synapsin1 were upregulated at 2 h, and ERK signaling was upregulated for 3 days in the hippocampus after a single administration of Oc or ketamine. A 5-day treatment of LPS led to depression-like behaviors, including reduced sucrose preference and increased immobility in the tail suspension test or forced swim test, which were all reversed by a single dose of Qc. In LPS-treated mice, Qc reduced the levels of inflammation-related factors including IL-10, IL-1ß, and TNF-α in serum, as well as the activations of PI3K/AKT/NF-κB and MEK/ERK pathways in the hippocampus. Moreover, Qc restored the expressions of pCREB/BDNF/PSD95/Synapsin1 signaling in the hippocampus that were impaired by LPS. LY294002, a PI3K inhibitor, but not PD98059, a MEK inhibitor, produced effects similar to Qc. LY294002 also restored the expressions of pCREB/BDNF/PSD95/Synapsin1 signaling in the hippocampus impaired by LPS. Additionally, subeffective doses of Qc and LY294002 induced behavioral and molecular synergism. Together, the depression-like behaviors in LPS-treated mice were alleviated by a single dose of Qc likely via inhibition of the activations PI3K/AKT/NF-κB inflammation signaling and subsequent improvement of neuroplasticity.

Latent Sex Differences in CaMKII-nNOS Signaling That Underlie Antidepressant-Like Effects of Yueju-Ganmaidazao Decoction in the Hippocampus.

Previous studies have demonstrated that Yueju-Ganmaidazao (YG) decoction induces rapid antidepressant-like effects, and the antidepressant response is mostly dependent on the suppression of nitric oxide-cyclic guanosine monophosphate signaling in male mice. This study aimed to investigate the sex difference mediated by calcium/calmodulin-dependent protein kinase II (CaMKII)-neuronal nitric oxide synthase (nNOS) signaling involved in the antidepressant-like effect of YG in mice. We found that the immobility times in the tail suspension test (TST) were found to be decreased after the single injection of YG in male and female mice with the same dosage. Additionally, chronic administration for 4 days of subthreshold dosage of YG and escitalopram (ES) also significantly decreased the immobility time in mice of both sexes. Chronic subthreshold dosage of YG and ES in LPS-treated mice and in chronic unpredictable stress (CUS) mice both decreased the immobility time, which was increased by stress. Meanwhile, in CUS-treated mice, sucrose preference test, forced swimming test, and open field test were applied to further confirm the antidepressant-like effects of YG and ES. Moreover, CUS significantly decreased the expression of nNOS and CaMKII, and both YG and ES could enhance the expression in the hippocampus of female mice, which was opposite to that in male mice, while endothelial nitric oxide synthase expression was not affected by stress or drug treatment neither in male mice nor in female mice. Finally, subthreshold dosage of YG combined with 7-nitroindazole (nNOS inhibitor) induced the antidepressant-like effects both in female and in male mice, while the single use of YG or 7-NI did not display any effect. However, pretreatment with KN-93 (CaMKII inhibitor) only blocked the antidepressant-like effect of high-dosage YG in female mice. Meanwhile, in CUS mice, chronic stress caused NR1 overexpression and inhibited cAMP response element binding protein action, which were both reversed by YG and ES in male and female mice, implying that YG and ES produced the same antidepressant-like effect in mice of both sexes. The study revealed that chronic treatment with a subthreshold dose of YG also produced antidepressant-like effects in female mice, and these effects depended on the regulation of the CaMKII-nNOS signaling pathway.