Magnetic resonance imaging (MRI) technology shows significant potential in predicting early pathological changes associated with Alzheimer's disease (AD). However, the complexity of MRI and their multidimensional characteristics pose challenges in model classification tasks, and single-scale features often fail to capture subtle changes in lesion areas effectively. To improve the accuracy of AD predictions, we propose a network model based on multi-scale features and a dual self-attention mechanism (MSDA). This model integrates depthwise separable convolutions with an improved self-attention mechanism, thereby enhancing the classification ability for AD. First, MRI undergo head motion correction, image alignment, and skull stripping to enhance the model's capability to extract features related to AD lesions. Second, we designed a multi-scale convolutional network structure that utilizes depthwise separable convolution kernels of varying sizes, allowing the network to effectively capture multi-scale feature information from MRI and accurately identify lesion areas. Finally, we introduced a dual self-attention module, which includes channel self-attention and spatial self-attention, further augmenting the model's ability to extract lesion features by learning the differences in features across different categories of MRI in both channel and spatial dimensions. Experimental results indicate that the MSDA network model demonstrates exceptional performance in classifying normal controls (NC) and AD within the ADNI dataset, outperforming existing models in classification accuracy, performance, and generalization capability. The accuracy, sensitivity, and specificity of the model reached 97.8%, 96.3%, and 99.4%, respectively.

Alzheimer’s disease (AD) is a common neurodegenerative disease in the elderly, characterized by progressive memory decline, language impairment, and behavioral abnormalities. MRI has been widely utilized as a non-invasive technique for diagnosing AD. However, traditional cnn have limitations in extracting multi-scale lesion features, making it challenging to fully capture the local information and global dependencies of the lesion area. To overcome this issue, we propose a multi-scale feature attention network (MSFAN), which integrates multi-scale feature extraction (MSF), channel attention mechanism (CAM) and non-local block for AD classification. Specifically, the MSF module extracts local features at different scales through cascaded multi-scale convolution kernels; the CAM module adaptively reweights channel responses to emphasize critical lesion areas; and the non-local block captures long-range dependencies across different brain regions, thereby enhancing global feature representation. Experimental results show that MSFAN performs well compared to other cnn models in AD classification tasks, with accuracy, precision, recall and F1 score all significantly improved.

Alzheimer’s disease (AD) is a neurodegenerative disorder that primarily affects the elderly, characterized by cognitive decline and memory loss. Magnetic resonance imaging (MRI) plays a crucial role in the auxiliary diagnosis of AD. Recent studies have demonstrated that deep learning algorithms have achieved remarkable success in predicting AD. As an innovative feature extraction technology, ResNet has considerably advanced the application of deep learning in medical imaging. 3D convolutional neural networks (CNNs) can process three-dimensional MRI data directly, capturing the intricate three-dimensional characteristics of the brain’s structure. This study proposes a novel framework based on 3D ResNet, which integrates spatial and channel attention mechanisms to significantly enhance the sensitivity and accuracy of feature representation. Furthermore, we have incorporated non-local blocks within the residual blocks to enable the model to capture long-range dependencies. Experimental analysis indicates that our 3D ResNet model exhibits outstanding classification performance and can effectively support the clinical diagnosis of AD.

In the realm of e-commerce, the process of search stands as the primary point of interaction for users, wielding a profound influence on the platform's revenue generation. Notably, spelling correction assumes a pivotal role in shaping the user's search experience by rectifying erroneous query inputs, thus facilitating more accurate retrieval outcomes. Within the scope of this research paper, our aim is to enhance the existing state-of-the-art discriminative model performance with generative modelling strategies while concurrently addressing the engineering concerns associated with real-time online latency, inherent to models of this category. We endeavor to refine LSTM-based classification models for spelling correction through a generative fine-tuning approach hinged upon pre-trained language models. Our comprehensive offline assessments have yielded compelling results, showcasing that transformer-based architectures, such as BART (developed by Facebook) and T5 (a product of Google), have achieved a 4% enhancement in F1 score compared to baseline models for the English language sites. Furthermore, to mitigate the challenges posed by latency, we have incorporated model pruning techniques like no-teacher distillation. We have undertaken the deployment of our model (English only) as an A/B test candidate for real-time e-commerce traffic, encompassing customers from the US and the UK. The model attest to a 100% successful request service rate within real-time scenarios, with median, 90th percentile, and 99th percentile (p90/p99) latencies comfortably falling below production service level agreements. Notably, these achievements are further reinforced by positive customer engagement, transactional and search page metrics, including a significant reduction in instances of search results page with low or almost zero recall. Moreover, we have also extended our efforts into fine-tuning a multilingual model, which, notably, exhibits substantial accuracy enhancements, amounting to a minimum of 16%, across four distinct European languages and English.

Alzheimer's disease (AD) is a neurodegenerative disorder that progresses in a slow and irreversible manner. Although many computer-aided methods have been used to diagnose AD, the issue of underutilization of detailed information and features persists. In this study, we propose a new AD diagnostic network (FPRes-Net) that can fully learn the rich information of 3D MRI slices by extracting multi-scale features and feature fusion. Firstly, in order to fully extract multi-scale information, a network structure combining ResNet-50 with feature pyramids was designed. Next, a feature fusion method was designed to reduce noise and increase the importance of important features. Finally, a visually interpretable method called Gradient-weighted Class Activation Mapping (Grad-CAM) was introduced to visualize important feature regions in AD diagnosis. Experimental analysis was conducted on the publicly accessible ADNI-1 dataset, and our proposed FPRes-Net model performed better than other advanced research methods, with an accuracy rate of 99.5%. Our proposed model can be effectively used for clinical diagnosis of AD.

For radiometric normalization (RN) of multiple remote sensing (MRS) images within large-scale coverage, the traditional methods ignore the error accumulation and adaptive allocation of cumulative errors caused by the transfer paths in the classical one-after-another pipeline. To this end, a block adjustment-based RN method of MRS images is proposed by considering the global and local radiometric differences (RDs) in this letter. First, the block adjustment-based global RN is conducted to eliminate the global differences of MRS images. This step is independent of transfer paths so that it breaks through the corresponding error accumulation and uneven distribution in the one-after-another pipeline. Second, two local strategies based on block adjustment and edge optimization are further adopted to remove the local residual RDs. In the experiments, it demonstrates that the proposed method can obtain MRS images with a balanced and appealing visual effect, which outperforms the moment matching (MM) method and the popular ENVI software.