Search

Abstract Objective To construct the deep learning convolution neural network (CNN) model and machine learning support vector machine (SVM) model of bone remodeling of chronic maxillary sinusitis (CMS) based on CT image data to improve the accuracy of image diagnosis. Methods Maxillary sinus CT data of 1000 samples in 500 patients from January 2018 to December 2021 in our hospital was collected. The first part is the establishment and testing of chronic maxillary sinusitis detection model by 461 images. The second part is the establishment and testing of the detection model of chronic maxillary sinusitis with bone remodeling by 802 images. The sensitivity, specificity and accuracy and area under the curve (AUC) value of the test set were recorded, respectively. Results Preliminary application results of CT based AI in the diagnosis of chronic maxillary sinusitis and bone remodeling. The sensitivity, specificity and accuracy of the test set of 93 samples of CMS, were 0.9796, 0.8636 and 0.9247, respectively. Simultaneously, the value of AUC was 0.94. And the sensitivity, specificity and accuracy of the test set of 161 samples of CMS with bone remodeling were 0.7353, 0.9685 and 0.9193, respectively. Simultaneously, the value of AUC was 0.89. Conclusion It is feasible to use artificial intelligence research methods such as deep learning and machine learning to automatically identify CMS and bone remodeling in MSCT images of paranasal sinuses, which is helpful to standardize imaging diagnosis and meet the needs of clinical application.

BackgroundThe glymphatic system has been regarded as a pivotal factor in the pathogenesis of neurodegenerative diseases. Given the heightened risk of cognitive impairment in chronic tinnitus patients, the possible alterations of the glymphatic system in tinnitus patients remain elusive. This study was designed to evaluate glymphatic dysfunction in chronic tinnitus patients using the diffusion tensor imaging (DTI) along the perivascular space (DTI-ALPS) approach.MethodsFifty chronic tinnitus patients and 50 age, sex, and education-matched healthy controls (HCs) with normal hearing thresholds were recruited. The DTI-ALPS was calculated from each group. We investigated the differences in the DTI-ALPS index between the tinnitus patients and HCs. The relationships between the DTI-ALPS index and specific cognitive performance were further assessed.ResultsThere were significant differences in the DTI-ALPS index between the two groups. The DTI-ALPS index was significantly lower in the tinnitus group than in HCs group (p

BackgroundIndividuals with subjective cognitive decline (SCD) are at risk of developing Alzheimer's Disease (AD). Traditional seed-based analysis has shown biased functional connectivity (FC) in SCD individuals. To investigate unbiased altered FC by the brain-wide association study (BWAS) and to determine its association with cognition in SCD individuals.MethodsMeasure of association (MA) analysis was applied to detect significant voxels with FC changes. Based on these changes, we identified regions of interest (ROIs) and conducted ROI-wise FC analyses. Correlation analyses were then performed between these FC circuits and cognition.ResultsMA analysis identified 10 ROIs with significantly altered voxels. ROI-wise FC analyses revealed 14 strengthened FC, predominantly parietal-occipital link alterations. The FC between the right superior occipital gyrus and the right postcentral gyrus correlated positively with executive function, while the FC between the right middle occipital gyrus and the left angular gyrus correlated positively with episodic memory in SCD individuals.ConclusionSCD involves multifocal impairments, of which regions of default mode network (DMN) and occipital lobe should be specially focused. Cross-hemispheric alterations indicate an internal interactive impairment pattern in SCD. The reduced FC between the right superior occipital gyrus and the right postcentral gyrus, and between the right middle occipital gyrus and the left angular gyrus, which correlate with specific cognitive functions, could serve as potential biomarkers for SCD diagnosis.

ObjectiveImpaired interhemispheric connectivity and corpus callosum atrophy have been linked to cognitive impairment in Alzheimer’s disease (AD). Existing evidence indicates that repetitive transcranial magnetic stimulation (rTMS) targeting the bilateral precuneus may enhance cognitive function in AD. This study aims to investigate the effects of precuneus rTMS on cognitive function, as well as alterations in interhemispheric functional connectivity (FC) and its structural basis in patients with subjective cognitive decline (SCD) and mild cognitive impairment (MCI).MethodsA total of 14 patients with SCD and 16 patients with MCI were enrolled in this study and received 10 Hz rTMS intervention on the bilateral precuneus for 2 weeks. Neurocognitive scales, structural and functional magnetic resonance imaging were collected at enrollment and after the rTMS intervention. Interhemispheric FC was assessed using mirror homotopic functional connectivity (VMHC), while the structural equation modeling (SEM) was employed to analyze the relationship between corpus callosum volume, interhemispheric connectivity, and cognitive function after rTMS intervention.ResultsThe precuneus rTMS not only enhanced episodic memory in SCD, but also improved multiple cognitive domains in MCI. Post-rTMS intervention, decreased VMHC values in the lingual cortex, middle occipital gyrus, putamen, and fusiform gyrus were observed in SCD, and an increased VMHC value in the postcentral gyrus along with reduced VMHC value in the cerebellum and putamen in MCI. After intervention, more brain regions show decreased FC in SCD and MCI patients, suggesting that precuneus rTMS may protect cerebral cortical plasticity by reducing excessive functional compensation, and thus improve cognitive function. The SEM indicated that the corpus callosum serves as the structural foundation for rTMS regulation of interhemispheric FC to further improve cognitive function.Conclusion10 Hz rTMS in the bilateral precuneus could be a promising strategy to improve cognitive function in patients with SCD and MCI. Our study implies that improvements in cognition brought about by precuneus rTMS may result from the remodeling of interhemispheric FC, with the corpus callosum possibly acting as the anatomical basis for functional modulation.

Abstract Community detection is an important method to analyze the characteristics and structure of community networks, which can excavate the potential links between nodes and further discover subgroups from complex networks. However, most of the existing methods only unilaterally consider the direct link topology without comprehensively considering the internal and external characteristics of the community as well as the result itself, which fails to maximize the access to the network information, thus affecting the effectiveness of community detection. To compensate for this deficiency, we propose a new community detection method based on multi-constraint non-negative matrix factorization, named orthogonal regular sparse constraint non-negative matrix factorization (ORSNMF). Based on the network topology, the ORSNMF algorithm models the differences of the outside of the community, the similarities of the nodes inside the community, and the sparseness of the community membership matrices at the same time, which together guides the iterative learning process to better reflect the underlying information and inherent attributes of the community structure in order to improve the correct rate of dividing subgroups. An algorithm with convergence guarantee is also proposed to solve the model, and finally a large number of comparative experiments are conducted, and the results show that the algorithm has good results.

The application of deep learning in remote sensing image classification has been paid more and more attention by industry and academia. However, manually designed remote sensing image classification models based on convolutional neural networks usually require sophisticated expert knowledge. Moreover, it is notoriously difficult to design a model with both high classification accuracy and few parameters. Recently, neural architecture search (NAS) has emerged as an effective method that can greatly reduce the heavy burden of manually designing models. However, it remains a challenge to search for a classification model with high classification accuracy and few parameters in the huge search space. To tackle this challenge, we propose TPENAS, a two-phase evolutionary neural architecture search framework, which optimizes the model using computational intelligence techniques in two search phases. In the first search phase, TPENAS searches for the optimal depth of the model. In the second search phase, TPENAS searches for the structure of the model from the perspective of the whole model. Experiments on three open benchmark datasets demonstrate that our proposed TPENAS outperforms the state-of-the-art baselines in both classification accuracy and reducing parameters.

The dimension reduction of large scale high-dimensional data is a challenging task, especially the dimension reduction of face data and the accuracy increment of face recognition in the large scale face recognition system, which may cause large storage space and long recognition time. In order to further reduce the recognition time and the storage space in the large scale face recognition systems, on the basis of the general non-negative matrix factorization based on left semi-tensor (GNMFL) without dimension matching constraints proposed in our previous work, we propose a sparse GNMFL/L (SGNMFL/L) to decompose a large number of face data sets in the large scale face recognition systems, which makes the decomposed base matrix sparser and suppresses the decomposed coefficient matrix. Therefore, the dimension of the basis matrix and the coefficient matrix can be further reduced. Two sets of experiments are conducted to show the effectiveness of the proposed SGNMFL/L on two databases. The experiments are mainly designed to verify the effects of two hyper-parameters on the sparseness of basis matrix factorized by SGNMFL/L, compare the performance of the conventional NMF, sparse NMF (SNMF), GNMFL, and the proposed SGNMFL/L in terms of storage space and time efficiency, and compare their face recognition accuracies with different noises. Both the theoretical derivation and the experimental results show that the proposed SGNMF/L can effectively save the storage space and reduce the computation time while achieving high recognition accuracy and has strong robustness.