Research on migraine time-series features classification based on small-sample functional magnetic resonance imaging data / 生物医学工程学杂志

The extraction of neuroimaging features of migraine patients and the design of identification models are of great significance for the auxiliary diagnosis of related diseases. Compared with the commonly used image features, this study directly uses time-series signals to characterize the functional state of the brain in migraine patients and healthy controls, which can effectively utilize the temporal information and reduce the computational effort of classification model training. Firstly, Group Independent Component Analysis and Dictionary Learning were used to segment different brain areas for small-sample groups and then the regional average time-series signals were extracted. Next, the extracted time series were divided equally into multiple subseries to expand the model input sample. Finally, the time series were modeled using a bi-directional long-short term memory network to learn the pre-and-post temporal information within each time series to characterize the periodic brain state changes to improve the diagnostic accuracy of migraine. The results showed that the classification accuracy of migraine patients and healthy controls was 96.94%, the area under the curve was 0.98, and the computation time was relatively shorter. The experiments indicate that the method in this paper has strong applicability, and the combination of time-series feature extraction and bi-directional long-short term memory network model can be better used for the classification and diagnosis of migraine. This work provides a new idea for the lightweight diagnostic model based on small-sample neuroimaging data, and contributes to the exploration of the neural discrimination mechanism of related diseases.

Research of electroencephalography representational emotion recognition based on deep belief networks / 生物医学工程学杂志

In recent years, with the rapid development of machine learning techniques,the deep learning algorithm has been widely used in one-dimensional physiological signal processing. In this paper we used electroencephalography (EEG) signals based on deep belief network (DBN) model in open source frameworks of deep learning to identify emotional state (positive, negative and neutrals), then the results of DBN were compared with support vector machine (SVM). The EEG signals were collected from the subjects who were under different emotional stimuli, and DBN and SVM were adopted to identify the EEG signals with changes of different characteristics and different frequency bands. We found that the average accuracy of differential entropy (DE) feature by DBN is 89.12%±6.54%, which has a better performance than previous research based on the same data set. At the same time, the classification effects of DBN are better than the results from traditional SVM (the average classification accuracy of 84.2%±9.24%) and its accuracy and stability have a better trend. In three experiments with different time points, single subject can achieve the consistent results of classification by using DBN (the mean standard deviation is1.44%), and the experimental results show that the system has steady performance and good repeatability. According to our research, the characteristic of DE has a better classification result than other characteristics. Furthermore, the Beta band and the Gamma band in the emotional recognition model have higher classification accuracy. To sum up, the performances of classifiers have a promotion by using the deep learning algorithm, which has a reference for establishing a more accurate system of emotional recognition. Meanwhile, we can trace through the results of recognition to find out the brain regions and frequency band that are related to the emotions, which can help us to understand the emotional mechanism better. This study has a high academic value and practical significance, so further investigation still needs to be done.

The brain functioning of aphasic Uyghur and Mandarin speakers after stroke / 中华物理医学与康复杂志

Objective To observe any differences in the spontaneous activity of brain areas between Manda rin-speaking and Uyghur-speaking aphasics at rest and explore the reasons.Methods Functional magnetic resonance imaging was used to scan the brains of 15 Mandarin-speaking and 12 Uyghur-speaking subjects.Statistical parametric maps of the active brain areas were prepared and low-frequency amplitude (ALEF) indexes were calculated.Results While at rest the ALEF indexes of the Mandarin-speakers were,on averge,larger than those of the Uyghur-speakers.The difference was primarily in the ALEF of the right thalamus.Conclusion At rest,the average ALEF of the right thalamus of aphasic Mandarin-speakers is larger than that of Uyghur-speakers.It might be that after a left-brain stroke the Mandarin-speakers form new language circuits with the help of the right thalamus which compensates for the loss of language function.

Classification and Correlative Technology Development of Wearable Devices / 生物医学工程学杂志

Wearable devices bring us an innovative human-computer interaction which plays an irreplaceable role in enhancing the users' ability in environmental awareness, acquirements of their own state and "ubiquitous" computing power. Since 2013, wearable devices have quickly appeared around us. In this article we classify most of the wearable devices which have been appeared in the markets or reported in the literature according to their functions and the positions where they are worn. Furthermore, we review the technologies related to wearable devices, such as sensing technology, wireless communication, power manager, display technology and big data. At last, we analyze the challenges which the wearable devices will face in near future, and look forward to development trends of wearable devices.

Research progress of brain functional magnetic resonance imaging in post-traumatic stress disorder / 生物医学工程学杂志

Post-traumatic stress disorder (PTSD) is a mental disorder causing great distress to individuals, families and even society, and there is not yet effective way of unified prevention and treatment up till now. Lots of neuroimaging techniques, however, such as the magnetic resonance imaging, are widely used to the study of the pathogenesis of PTSD with the development of medical imaging. Functional magnetic resonance imaging (fMRI) can be applied to detect the abnormalities not only of the brain morphology but also of the function of various cerebral areas and neural circuit, and plays an important role in studying the pathogenesis of psychiatric diseases. In this paper, we mainly review the task-related and resting-state functional magnetic resonance imaging studies of the PTSD, and finally suggest possible directions for future research.

The cortical organization in language tasks of Mandarin and Uyghur speakers / 中华物理医学与康复杂志

Objective To observe the difference in activated brain regions when speaking Mandarin and Uyghur.Methods Blood oxygenation level dependent magnetic resonance imaging (BOLD-fMRI) was used to scan the brains of 30 healthy,right handed volunteers-15 native Uyghur speakers and 15 native Mandarin speakers-while they performed semantic identification and verb generation tasks.The fMRI data were used to generate statistical parametric maps of the brain areas activated by each task.Results In the semantic identification task the left anterior cingulate gyrus (BA23) and the midline mesophyll wedge were activated significantly more strongly in the Uyghur group compared with the Mandarin speakers.In the verb generation task the left inferior temporal gyrus (BA37),the inferior parietal lobule,the fusiform gyrus and the parahippocampal gyrus in the Uyghur group were all significantly more active.The right superior temporal gyrus (BA38) in the Mandarin group was significantly more active during verb generation than among the Uyghur speakers.Conclusions The brain regions activated during semantic processing and verb generation differ when speaking Uyghur and Mandarin.The cingulate gyrus and the praecuneus are more involved in Uyghur-language semantic processing,especially the left anterior cingulate gyrus.The right hemisphere is more important in Mandarin processing than in Uyghur.

Mutagenecity and proliferative activity of duodenal reflux juice from patients with remote postgastrectomy / 中国实用外科杂志

Objective This study was conducted to ascertain whether study on carcinogenic potential of reflux juice from long-standing gastrectomy patients could clarify the relationship between duodenogastric reflux and gastric stump cancer. Methods A total of 48 reflux juice samples(11 Billroth Ⅰ,37 BillrothⅡ)were employed in our study.Ames test and MTT proliferation assay were carried out to evaluate the mutagenicity and proliferative activity of aspirates, respectively. Results There was no difference in mutagenicity of the samples in respect of surgical procedures(P＞0.05). While Billroth Ⅱ samples exhibited stronger proliferative activity than Billroth Ⅰ samples(P=0.751),In addition, the proliferative activity well correlated with pH of aspirates(rs=0.73,P＜0.001),but the mutagenicity failed to this correlation. Conclusion We confirm the duodenal reflux theory for the gastric stump cancer with the aspirates from long-standing postgastrectomy patients, and further suggest that proliferative activity of aspirates should be responsible for the high incidence of gastric cancer in the long-standing gastrectomy patients, thus roviding direct evidence for the etiology of the gastric stump cancer. Simultaneously closely endoscopic surveillance or postgastrectomy patients with moderate/severe dysplasia is highly recommended. In addition, to decrease the incidence of stump cancer effectively, it seems reasonable to perform reconstruction procedures(e.g,Roux-en-Y anastomosis)for those with severe duodenal reflux and to focus the chemoprevention of this cancer on proliferative activity of the reflux juice.