Subject adaptation convolutional neural network for EEG-based motor imagery classification.

Objective.Deep transfer learning has been widely used to address the nonstationarity of electroencephalogram (EEG) data during motor imagery (MI) classification. However, previous deep learning approaches suffer from limited classification accuracy because the temporal and spatial features cannot be effectively extracted.Approach.Here, we propose a novel end-to-end deep subject adaptation convolutional neural network (SACNN) to handle the problem of EEG-based MI classification. Our proposed model jointly optimizes three modules, i.e. a feature extractor, a classifier, and a subject adapter. Specifically, the feature extractor simultaneously extracts the temporal and spatial features from the raw EEG data using a parallel multiscale convolution network. In addition, we design a subject adapter to reduce the feature distribution shift between the source and target subjects by using the maximum mean discrepancy. By minimizing the classification loss and the distribution discrepancy, the model is able to extract the temporal-spatial features to the prediction of a new subject.Main results.Extensive experiments are carried out on three EEG-based MI datasets, i.e. brain-computer interface (BCI) competition IV dataset IIb, BCI competition III dataset IVa, and BCI competition IV dataset I, and the average accuracy reaches to 86.42%, 81.71% and 79.35% on the three datasets respectively. Furthermore, the statistical analysis also indicates the significant performance improvement of SACNN.Significance.This paper reveals the importance of the temporal-spatial features on EEG-based MI classification task. Our proposed SACNN model can make fully use of the temporal-spatial information to achieve the purpose.

Combined immune score predicts the prognosis of newly diagnosed multiple myeloma patients in the bortezomib-based therapy era.

ABSTRACT: To investigate the effect of a combined immune score including the lymphocyte-to-monocyte ratio (LMR) and uninvolved immunoglobulin (u-Ig) levels on the prognosis of newly diagnosed multiple myeloma (NDMM) patients treated with bortezomib.Clinical data of 201 NDMM patients were retrospectively analyzed. Patients with LMR ≥ 3.6 and LMR < 3.6 were scored 0 and 1, respectively. Patients with preserved u-Ig levels, suppression of 1 u-Ig, and suppression of at least 2 u-Igs were scored 0, 1, and 2, respectively. The immune score, established from these individual scores, was used to separate patients into good (0-1 points), intermediate (2 points), and poor (3 points) risk groups. The baseline data, objective remission rate (ORR), whether receive maintenance treatment regularly and overall survival of patients before treatment were analyzed.The ORR of the good-risk group was significantly higher than that of the intermediate-risk group (75.6% vs 57.7%, P = .044) and the poor-risk group (75.6% vs 48.2%, P = .007). The multivariate analysis results showed that age ≥ 65 years, International Staging System stage III, platelet count ≤ 100 × 109/L, lactate dehydrogenase (LDH) > 250 U/L, serum calcium > 2.75 mmol/L, no receipt of regular maintenance treatment, LMR < 3.6, suppressed u-Igs = 1, suppressed u-Igs ≥ 2, intermediate-risk group and poor-risk group were independent predictors of poor overall survival.In the bortezomib era, the LMR, u-Ig levels, and the immune score play an important role in the prognosis of NDMM patients. Among them, the immune score showed the strongest prognostic value, and it could be a beneficial supplement for the early identification of high-risk patients.

The Expression and Function of Circadian Rhythm Genes in Hepatocellular Carcinoma.

Hepatocellular carcinoma (HCC) is among the most common and lethal form of cancer worldwide. However, its diagnosis and treatment are still dissatisfactory, due to limitations in the understanding of its pathogenic mechanism. Therefore, it is important to elucidate the molecular mechanisms and identify novel therapeutic targets for HCC. Circadian rhythm-related genes control a variety of biological processes. These genes play pivotal roles in the initiation and progression of HCC and are potential diagnostic markers and therapeutic targets. This review gives an update on the research progress of circadian rhythms, their effects on the initiation, progression, and prognosis of HCC, in a bid to provide new insights for the research and treatment of HCC.

The value of 18 F-FDG PET/CT in diagnosing and localising deep sternal wound infection to guide surgical debridement.

Deep sternal wound infection (DSWI) is a severe complication in patients after open heart surgery (OHS). But there is a lack of appropriate imaging tool to detect the infection sites, which may lead to incomplete debridement. The present study aims to investigate the value of 18 F-fluorodeoxyglucose positron emission tomography/computed tomography (18 F-FDG PET/CT) in comparison with CT scan in diagnosing and localising DSWI. A total of 102 patients with DSWI after OHS were retrospectively collected from January 2012 to December 2017 in our hospital. All the patients had surgical debridements for DSWI with pretreatment imaging of either 18 F-FDG PET/CT or CT scan. The sensitivity, specificity, and accuracy of localising infection sites were compared between PET/CT and CT groups, with surgical, microbiological, and histopathological findings as the gold standard. The length of hospital stays and the rate of recurrence were also compared. Ten patients in the PET/CT group had a follow-up PET/CT scan after debridement, and the correlations between the changes of PET/CT findings and surgical outcomes were analysed. 18 F-FDG PET/CT is more accurate than CT in diagnosing and localising DSWI after OHS, which leads to a more successful surgical debridement with a lower rate of recurrence and a shorter length of hospital stay. In addition, follow-up PET/CT after debridement could evaluate the treatment effect.

Paeoniflorin inhibits proliferation and induces apoptosis of human glioma cells via microRNA-16 upregulation and matrix metalloproteinase-9 downregulation.

Paeoniflorin is one of the active ingredients of the commonly used herbal medicine derived from Paeonia, which exhibits anticancer properties. MicroRNA-16 (miR-16) is upregulated in CD133(-) cells, but downregulated in CD133(+) cells from glioma tissue. Matrix metalloproteinase-9 (MMP-9) expression in glioma tissue samples is significantly higher than that in healthy brain tissue samples. Therefore, miR-16 and MMP-9 expression may be associated with glioma pathogenesis. In the present study, the effects of paeoniflorin on glioma were analyzed. U87 cells were treated with paeoniflorin at 0, 5, 10 and 20 µΜ concentrations. The results suggested that paeoniflorin inhibited U87 cell proliferation and accelerated cell apoptosis. In the present study paeoniflorin treatment increased miR-16 expression and reduced MMP-9 protein expression in U87 cells. Additionally, the results of the present study suggested that miR-16 may regulate MMP-9 expression in miR-16-transfected U87 cells. Furthermore, anti-miR-16 antibodies were used in order to investigate the apoptotic effects of paeoniflorin on U87 cells. The results demonstrated that paeoniflorin inhibits proliferation and induces apoptosis of human glial cells, via miR-16 upregulation and MMP-9 downregulation.