DMA-HPCNet: Dual Multi-Level Attention Hybrid Pyramid Convolution Neural Network for Alzheimer's Disease Classification.

Computer-aided diagnosis (CAD) plays a crucial role in the clinical application of Alzheimer's disease (AD). In particular, convolutional neural network (CNN)-based methods are highly sensitive to subtle changes caused by brain atrophy in medical images (e.g., magnetic resonance imaging, MRI). Due to computational resource constraints, most CAD methods focus on quantitative features in specific regions, neglecting the holistic nature of the images, which poses a challenge for a comprehensive understanding of pathological changes in AD. To address this issue, we propose a lightweight dual multi-level hybrid pyramid convolutional neural network (DMA-HPCNet) to aid clinical diagnosis of AD. Specifically, we introduced ResNet as the backbone network and modularly extended the hybrid pyramid convolution (HPC) block and the dual multi-level attention (DMA) module. Among them, the HPC block is designed to enhance the acquisition of information at different scales, and the DMA module is proposed to sequentially extract different local and global representations from the channel and spatial domains. Our proposed DMA-HPCNet method was evaluated on baseline MRI slices of 443 subjects from the ADNI dataset. Experimental results show that our proposed DMA-HPCNet model performs efficiently in AD-related classification tasks with low computational cost.

Deep Self-Reconstruction Fusion Similarity Hashing for the Diagnosis of Alzheimer's Disease on Multi-Modal Data.

The pathogenesis of Alzheimer's disease (AD) is extremely intricate, which makes AD patients almost incurable. Recent studies have demonstrated that analyzing multi-modal data can offer a comprehensive perspective on the different stages of AD progression, which is beneficial for early diagnosis of AD. In this paper, we propose a deep self-reconstruction fusion similarity hashing (DS-FSH) method to effectively capture the AD-related biomarkers from the multi-modal data and leverage them to diagnose AD. Given that most existing methods ignore the topological structure of the data, a deep self-reconstruction model based on random walk graph regularization is designed to reconstruct the multi-modal data, thereby learning the nonlinear relationship between samples. Additionally, a fused similarity hash based on anchor graph is proposed to generate discriminative binary hash codes for multi-modal reconstructed data. This allows sample fused similarity to be effectively modeled by a fusion similarity matrix based on anchor graph while modal correlation can be approximated by Hamming distance. Especially, extracted features from the multi-modal data are classified using deep sparse autoencoders classifier. Finally, experiments conduct on the AD Neuroimaging Initiative database show that DS-FSH outperforms comparable methods of AD classification. To conclude, DS-FSH identifies multi-modal features closely associated with AD, which are expected to contribute significantly to understanding of the pathogenesis of AD.

Diagnosis-Guided Deep Subspace Clustering Association Study for Pathogenetic Markers Identification of Alzheimer's Disease Based on Comparative Atlases.

The roles of brain region activities and genotypic functions in the pathogenesis of Alzheimer's disease (AD) remain unclear. Meanwhile, current imaging genetics methods are difficult to identify potential pathogenetic markers by correlation analysis between brain network and genetic variation. To discover disease-related brain connectome from the specific brain structure and the fine-grained level, based on the Automated Anatomical Labeling (AAL) and human Brainnetome atlases, the functional brain network is first constructed for each subject. Specifically, the upper triangle elements of the functional connectivity matrix are extracted as connectivity features. The clustering coefficient and the average weighted node degree are developed to assess the significance of every brain area. Since the constructed brain network and genetic data are characterized by non-linearity, high-dimensionality, and few subjects, the deep subspace clustering algorithm is proposed to reconstruct the original data. Our multilayer neural network helps capture the non-linear manifolds, and subspace clustering learns pairwise affinities between samples. Moreover, most approaches in neuroimaging genetics are unsupervised learning, neglecting the diagnostic information related to diseases. We presented a label constraint with diagnostic status to instruct the imaging genetics correlation analysis. To this end, a diagnosis-guided deep subspace clustering association (DDSCA) method is developed to discover brain connectome and risk genetic factors by integrating genotypes with functional network phenotypes. Extensive experiments prove that DDSCA achieves superior performance to most association methods and effectively selects disease-relevant genetic markers and brain connectome at the coarse-grained and fine-grained levels.

An adaptive weighted attention-enhanced deep convolutional neural network for classification of MRI images of Parkinson's disease.

BACKGROUND: Parkinson's disease (PD) is the second prevalent neurological diseases with a significant growth rate in incidence. Convolutional neural networks using structural magnetic resonance images (sMRI) are widely used for PD classification. However, the areas of change in the patient's MRI images are small and unfixed. Thus, capturing the features of the areas accurately where the lesions changed became a problem. METHOD: We propose a deep learning framework that combines multi-scale attention guidance and multi-branch feature processing modules to diagnose PD by learning sMRI T2 slice features. In this scheme, firstly, to achieve effective feature transfer and gradient descent, a deep convolutional neural network framework based on dense block is designed. Next, an Adaptive Weighted Attention algorithm is proposed, whose pursers is to extract multi branch and even diverse features. Finally, Dropout layer and SoftMax layer are added to the network structure to obtain good classification results and rich and diverse feature information. The Dropout layer is used to reduce the number of intermediate features to increase the orthogonality between features of each layer. The activation function SoftMax increases the flexibility of the neural network by increasing the degree of fitting to the training set and converting linear to nonlinear. RESULTS: The best performance of the proposed method an accuracy of 92%, a sensitivity of 94%, specificity of 90% and a F1 score of 95% respectively for identifying PD and HC. CONCLUSION: Experiments show that the proposed method can successfully distinguish PD and NC. Good classification results were obtained in PD diagnosis classification task and compared with advanced research methods.

Integrated analysis identifies the IL6/JAK/STAT signaling pathway and the estrogen response pathway associated with the pathogenesis of intracranial aneurysms.

Objective: We intended to identify the potential key biomarker and pathways that correlated with infiltrating immune cells during the pathogenesis of intracranial aneurysms (IA), to develop a diagnostic model, and to predict therapeutic drugs. Methods: Three datasets containing intracranial aneurysm tissue samples and normal artery control samples from Gene Expression Omnibus (GEO) were included. Gene-set variation analysis(GSVA) and gene set enrichment analysis (GSEA) were conducted to find the significant differentially expressed pathways in IA formation. The least absolute shrinkage and selection operator (LASSO) regression and the multivariate logistic regression analysis were performed to identify the characteristic genes in the IL6/JAK/STAT signaling pathway (ISP) and the estrogen response pathway (ERP). A diagnostic model was constructed. xCell was used to identify immune cell types in IA pathogenesis. We used the weighted gene co-expression network analysis (WGCNA) algorithm to explore the correlations between the key modules and the four traits. Potential therapeutic drugs were investigated in Enrichr and Drugbank database. Results: The ISP is significant positively correlated with IA onset. The biological function of the ISP is positively correlated with that of the ERP, and is significantly associated with immune cells activities. CSF2RB, FAS, IL6, PTPN1, STAT2, TGFB1 of the ISP gene set and ALDH3A2, COX6C, IGSF1, KRT18, MICB, NPY1R of the ERP gene set were proved to be the characteristic genes. The STAT2 gene can be the potential biomarker of IA onset. The immune score of IA samples was significantly higher than the controls. The STAT2 gene expression is associated with infiltration of immune cells. The WGCNA results were consistent with our finds. Acetaminophen can be a potential therapeutic drug for IA targeting STAT2. Conclusions: We identified that the ISP was one of the most significant positively correlated pathways in IA onset, and it was activated in this process concordant with the ERP and immune responses. Except for beneficial effects, complex and multiple roles of estrogen may be involved in IA formation. STAT2 could be a potential biomarker and a promising therapeutic target of IA pathogenesis.

Bioinformatics analysis reveals potential biomarkers associated with the occurrence of intracranial aneurysms.

To better understand the molecular mechanisms of intracranial aneurysm (IA) pathogenesis, we used gene coexpression networks to identify hub genes and functional pathways associated with IA onset. Two Gene Expression Omnibus (GEO) datasets encompassing intracranial aneurysm tissue samples and cerebral artery control samples were included. To discover functional pathways and potential biomarkers, weighted gene coexpression network analysis was employed. Next, single-gene gene set enrichment analysis was employed to investigate the putative biological roles of the chosen genes. We also used receiver operating characteristic analysis to confirm the diagnostic results. Finally, we used a rat model to confirm the hub genes in the module of interest. The module of interest, which was designated the green module and included 115 hub genes, was the key module that was most strongly and negatively associated with IA formation. According to gene set variation analysis results, 15 immune-related pathways were significantly activated in the IA group, whereas 7 metabolic pathways were suppressed. In two GEO datasets, SLC2A12 could distinguish IAs from control samples. Twenty-nine hub genes in the green module might be biomarkers for the occurrence of cerebral aneurysms. SLC2A12 expression was significantly downregulated in both human and rat IA tissue. In the present study, we identified 115 hub genes related to the pathogenesis of IA onset and deduced their potential roles in various molecular pathways; this new information may contribute to the diagnosis and treatment of IAs. By external validation, the SLC2A12 gene may play an important role. The molecular function of SLC2A12 in the process of IA occurrence can be further studied in a rat model.

An optimized digital watermarking algorithm in wavelet domain based on differential evolution for color image.

In this paper, a new color watermarking algorithm based on differential evolution is proposed. A color host image is first converted from RGB space to YIQ space, which is more suitable for the human visual system. Then, apply three-level discrete wavelet transformation to luminance component Y and generate four different frequency sub-bands. After that, perform singular value decomposition on these sub-bands. In the watermark embedding process, apply discrete wavelet transformation to a watermark image after the scrambling encryption processing. Our new algorithm uses differential evolution algorithm with adaptive optimization to choose the right scaling factors. Experimental results show that the proposed algorithm has a better performance in terms of invisibility and robustness.