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.
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.
Post-traumatic stress disorder (PTSD) presents with complex and diverse clinical manifestations, making accurate and objective diagnosis challenging when relying solely on clinical assessments. Therefore, there is an urgent need to develop reliable and objective auxiliary diagnostic models to provide effective diagnosis for PTSD patients. Currently, the application of graph neural networks for representing PTSD is limited by the expressiveness of existing models, which does not yield optimal classification results. To address this, we proposed a multi-graph multi-kernel graph convolutional network (MK-GCN) model for classifying PTSD data. First, we constructed functional connectivity matrices at different scales for the same subjects using different atlases, followed by employing the k-nearest neighbors algorithm to build the graphs. Second, we introduced the MK-GCN methodology to enhance the feature extraction capability of brain structures at different scales for the same subjects. Finally, we classified the extracted features from multiple scales and utilized graph class activation mapping to identify the top 10 brain regions contributing to classification. Experimental results on seismic-induced PTSD data demonstrated that our model achieved an accuracy of 84.75%, a specificity of 84.02%, and an AUC of 85% in the classification task distinguishing between PTSD patients and non-affected subjects. The findings provide robust evidence for the auxiliary diagnosis of PTSD following earthquakes and hold promise for reliably identifying specific brain regions in other PTSD diagnostic contexts, offering valuable references for clinicians.
目的 利用局部一致性（ReHo）方法探測創傷后應激障礙（PTSD）患者在靜息狀態下是否存在著大腦功能異常。 方法 2010年5月－7月對18例未經治療的地震PTSD患者和19例同樣經歷地震但未患PTSD的對照者進行了靜息態功能磁共振成像（Rs-fMRI） 掃描。應用ReHo方法處理Rs-fMRI數據，得出PTSD患者的異常腦區，并將患者存在組間差異的腦區ReHo值與臨床用PTSD診斷量表（CAPS）、漢密爾頓抑郁量表（HAMD）和漢密爾頓焦慮量表（HAMA）分別進行相關分析。 結果 ① PTSD組ReHo顯著增加的腦區包括右側顳下回、楔前葉、頂下葉、中扣帶回，左側枕中回以及左/右側后扣帶回；ReHo顯著降低的腦區包括左側海馬和左/右側腹側前扣帶回。② 異常腦區中后扣帶回和右側中扣帶回ReHo與HAMD呈負相關（中扣帶回r=?0.575，P=0.012；右側后扣帶回：r=?0.507，P=0.032），其余腦區ReHo與臨床指標無明顯相關性（P＞0.05），左側海馬與CAPS的相關性相對其他腦區較大（r=?0.430，P=0.075）。 結論 PTSD患者在靜息狀態下即存在著局部腦功能活動的降低和增加，ReHo方法可能有助于研究PTSD患者靜息狀態腦活動。