Introduction: Diagnosing Alzheimer's disease (AD) lesions via visual examination of Electroencephalography (EEG) signals poses a considerable challenge. This has prompted the exploration of deep learning techniques, such as Convolutional Neural Networks (CNNs) and Visual Transformers (ViTs), for AD prediction. However, the classification performance of CNN-based methods has often been deemed inadequate. This is primarily attributed to CNNs struggling with extracting meaningful lesion signals from the complex and noisy EEG data.Methods: In contrast, ViTs have demonstrated proficiency in capturing global signal patterns. In light of these observations, we propose a novel approach to enhance AD risk assessment. Our proposition involves a hybrid architecture, merging the strengths of CNNs and ViTs to compensate for their respective feature extraction limitations. Our proposed Dual-Branch Feature Fusion Network (DBN) leverages both CNN and ViT components to acquire texture features and global semantic information from EEG signals. These elements are pivotal in capturing dynamic electrical signal changes in the cerebral cortex. Additionally, we introduce Spatial Attention (SA) and Channel Attention (CA) blocks within the network architecture. These attention mechanisms bolster the model's capacity to discern abnormal EEG signal patterns from the amalgamated features. To make well-informed predictions, we employ a two-factor decision-making mechanism. Specifically, we conduct correlation analysis on predicted EEG signals from the same subject to establish consistency.Results: This is then combined with results from the Clinical Neuropsychological Scale (MMSE) assessment to comprehensively evaluate the subject's susceptibility to AD. Our experimental validation on the publicly available OpenNeuro database underscores the efficacy of our approach. Notably, our proposed method attains an impressive 80.23% classification accuracy in distinguishing between AD, Frontotemporal dementia (FTD), and Normal Control (NC) subjects.Discussion: This outcome outperforms prevailing state-of-the-art methodologies in EEG-based AD prediction. Furthermore, our methodology enables the visualization of salient regions within pathological images, providing invaluable insights for interpreting and analyzing AD predictions.

Brain 18F-FDG PET images are commonly-known materials for effectively predicting Alzheimer's disease (AD). How-ever, the data volume of PET is usually insufficient, which is unfavorable to train an accurate AD prediction networks. Fur-thermore, the PET image is noisy with low signal-to-noise ratio, and simultaneously the feature (metabolic abnormality) used for predicting AD in PET image is not always obvious. Such charac-teristics of 18F-FDG PET images hinder the existing deep learning networks to learn the feature of lesion (i.e., glucose metabolism abnormality) effectively, which leads to unsatisfactory classifica-tion performance and poor robustness. In this paper, a contrastive-based learning method is proposed to address the challenges of PET image inherently possessed. Firstly, the slices of 3D PET image are amplified by cropping the image of anchors (i.e., an augmented version of the same image) to generate extended train-ing data. Meanwhile, contrastive loss is adopted to enlarge inter-class feature distances and reduce intra-class feature differences using subject fuzzy labels as supervised information. Secondly, we construct a double convolutional hybrid attention module to enhance the network to learn different perceptual domains where two convolutional layers with different convolutional kernels (7 × 7 and 5 × 5) are constructed. Moreover, we recommend a diagnosis mechanism by analyzing the consistency of predicted result for PET slices alone with clinical neuropsychological assessment to achieve a better AD diagnosis. The experimental results show that the proposed method outperforms the state-of-the-arts for brain 18F-FDG PET images while remaining satisfactory computational performance, and hence demonstrate the advantage of the method in effectively predicting AD.

Since captured finger vein images are usually of low quality, it is challenging to extract reliable finger vein features directly from the original finger vein images. Most current methods utilize texture change information and rich line features to extract features from finger vein images while neglecting the curvature of the finger veins. In this paper, a Weber local descriptor (WLD) with variable curvature Gabor filters is proposed for finger vein recognition. First, the differential excitation operator in the original WLD is improved by adding directional information, thereby allowing the local texture changes in an image to be better characterized and enhancing the differences between heterogeneous finger veins. Then, variable curvature Gabor filters are introduced to extract finger vein features that can simultaneously reflect the directional information and the curvature of the finger veins. In fact, two response values from the proposed Gabor filters are employed as features for each pixel; this approach is equivalent to defining intervals for the line features, rather than single values, and makes the results more robust to the rotation. The extensive experiments on the SDUMLA-FV and PolyU databases demonstrate that the proposed method can effectively improve the performance of finger vein recognition and show good robustness to translation, rotation, and illumination.