A great number of studies have demonstrated the structural and functional abnormalities in chronic schizophrenia (SZ) patients. However, few studies analyzed the differences between first-episode, drug-naive SZ (FESZ) patients and normal controls (NCs). In this study, we recruited 44 FESZ patients and 56 NCs, and acquired their multi-modal magnetic resonance imaging (MRI) data, including structural and resting-state functional MRI data. We calculated gray matter volume (GMV), regional homogeneity (ReHo), amplitude of low frequency fluctuation (ALFF), and degree centrality (DC) of 90 brain regions, basing on an automated anatomical labeling (AAL) atlas. We then applied these features into support vector machine (SVM) combined with recursive feature elimination (RFE) to discriminate FESZ patients from NCs. Our results showed that the classifier using the combination of ReHo and ALFF as input features achieved the best performance (an accuracy of 96.97%). Moreover, the most discriminative features for classification were predominantly located in the frontal lobe. Our findings may provide potential information for understanding the neuropathological mechanism of SZ and facilitate the development of biomarkers for computer-aided diagnosis of SZ patients.
Multi-modal brain-computer interface and multi-modal brain function imaging are developing trends for the present and future. Aiming at multi-modal brain-computer interface based on electroencephalogram-near infrared spectroscopy (EEG-NIRS) and in order to simultaneously acquire the brain activity of motor area, an acquisition helmet by NIRS combined with EEG was designed and verified by the experiment. According to the 10-20 system or 10-20 extended system, the diameter and spacing of NIRS probe and EEG electrode, NIRS probes were aligned with C3 and C4 as the reference electrodes, and NIRS probes were placed in the middle position between EEG electrodes to simultaneously measure variations of NIRS and the corresponding variation of EEG in the same functional brain area. The clamp holder and near infrared probe were coupled by tightening a screw. To verify the feasibility and effectiveness of the multi-modal EEG-NIRS helmet, NIRS and EEG signals were collected from six healthy subjects during six mental tasks involving the right hand clenching force and speed motor imagery. These signals may reflect brain activity related to hand clenching force and speed motor imagery in a certain extent. The experiment showed that the EEG-NIRS helmet designed in the paper was feasible and effective. It not only could provide support for the multi-modal motor imagery brain-computer interface based on EEG-NIRS, but also was expected to provide support for multi-modal brain functional imaging based on EEG-NIRS.
Autoimmune pancreatitis (AIP) is a unique subtype of chronic pancreatitis, which shares many clinical presentations with pancreatic ductal adenocarcinoma (PDA). The misdiagnosis of AIP often leads to unnecessary pancreatic resection. 18F-FDG positron emission tomography/ computed tomography (PET/CT) could provide comprehensive information on the morphology, density, and functional metabolism of the pancreas at the same time. It has been proved to be a promising modality for noninvasive differentiation between AIP and PDA. However, there is a lack of clinical analysis of PET/CT image texture features. Difficulty still remains in differentiating AIP and PDA based on commonly used diagnostic methods. Therefore, this paper studied the differentiation of AIP and PDA based on multi-modality texture features. We utilized multiple feature extraction algorithms to extract the texture features from CT and PET images at first. Then, the Fisher criterion and sequence forward floating selection algorithm (SFFS) combined with support vector machine (SVM) was employed to select the optimal multi-modality feature subset. Finally, the SVM classifier was used to differentiate AIP from PDA. The results prove that texture analysis of lesions helps to achieve accurate differentiation of AIP and PDA.
The emergence of single-cell sequencing technology enables people to observe cells with unprecedented precision. However, it is difficult to capture the information on all cells and genes in one single-cell RNA sequencing (scRNA-seq) experiment. Single-cell data of a single modality cannot explain cell state and system changes in detail. The integrative analysis of single-cell data aims to address these two types of problems. Integrating multiple scRNA-seq data can collect complete cell types and provide a powerful boost for the construction of cell atlases. Integrating single-cell multimodal data can be used to study the causal relationship and gene regulation mechanism across modalities. The development and application of data integration methods helps fully explore the richness and relevance of single-cell data and discover meaningful biological changes. Based on this, this article reviews the basic principles, methods and applications of multiple scRNA-seq data integration and single-cell multimodal data integration. Moreover, the advantages and disadvantages of existing methods are discussed. Finally, the future development is prospected.