In recent years, Vision Transformer (ViT) models for hyperspectral image (HSI) classification have increased popularity due to their excellence in modeling long-range spatial-spectral dependencies, which have achieved state-of-the-art performance in classification, object detection, and segmentation tasks. However, ViTs are likely to miss local spatial features with fine granularity, while convolutional neural networks (CNNs) excel at extracting local patterns but cannot model long-range dependencies. We propose a hybrid framework that combines a 3D Residual CNN and a ViT module to counter these limitations. The CNN component possesses the ability to extract fine-grained local spectral and spatial information, which is passed through the ViT for extracting global contextual dependencies. Experimental evaluation on three benchmark HSI datasets, Indian Pines (IP), Pavia University (PU), and Salinas (SA), confirms the superiority of our approach. Experimental results show that our method outperforms the state-of-the-art methods in Hyperspectral image classification tasks, demonstrating good performance and potential application prospects.

Alzheimer's disease is a progressive neurodegenerative disorder that has been shown to increase in frequency in individuals with mild cognitive impairment. This study proposes a deep learning (DL)approach for the categorical diagnosis of Alzheimer's using MRI images. It employs Federated Learning (FL) for privacy preservation and Local Interpretable Modelagnostic Explanations (LIME) for explainability. The model uses a convolutional neural network (CNN) for classification, incorporating data decentralization to ensure patient confidentiality. FL allows multiple clients to train the model without exchanging any raw data, thus providing a security mechanism for sensitive kinds of medical information. Specifically, a federated setup is used where three clients have different datasets, and Krum aggregation is applied to enhance robustness. In addition, Adaptive Synthetic Sampling (ADASYN) is used to address class imbalance. The model was assessed within the framework of both a centralized setup and a federated approach, achieving 98.33% classification accuracy in the centralized training and 91.72% in the FL scheme. Thus, FL protects data privacy while still attaining high classification performance. While federated training slightly lowers the accuracy, it increases data security and hence mitigates data-sharing risks in a centralized manner. We use LIME to provide the explainability needed by the clinician to retrain their decision, thus raising trust in diagnostics. The research proves to be a big endorsement for employing FL in medical imaging applications for the effective yet responsible detection of Alzheimer's, a step toward aiding diagnosis and treatment strategies.

Skin cancer is among the most prevalent and deadly types of cancer. Dermatologists mostly use visual cues to diagnose this illness. The classification of multiclass skin cancer is challenging due to the fine-grained variability in the appearance of its several diagnostic categories. Advances in deep neural networks have led to a significant increase in skin lesion classification methods in recent years, with more performante models like vision transformers (ViTs) emerging and improving skin lesion classification performance. Our explainable skin cancer classification with ViT and Grad-CAM (XSC-ViT) is presented in this paper. This uses a specifically designed ViT to classify skin cancer. Our solution integrates L2 regularization in some ViT layers to prevent overfitting and applies the Grad-CAM (Gradient-weighted Class Activation Mapping) method for decision explainability. Our approach demonstrated remarkable performance results for skin cancer classification with an accuracy of 92%, precision of 91.73%, recall of 91.46%, F1 score of 91.51%, and loss of 22.05% when tested on the HAM10000 dataset.

Abstract Alzheimer’s disease (AD) is a neurodegenerative disorder that affects millions of people worldwide, making early detection essential for effective intervention. This review paper provides a comprehensive analysis of the use of deep learning techniques, specifically convolutional neural networks (CNN) and vision transformers (ViT), for the classification of AD using brain imaging data. While previous reviews have covered similar topics, this paper offers a unique perspective by providing a detailed comparison of CNN and ViT for AD classification, highlighting the strengths and limitations of each approach. Additionally, the review presents an updated and thorough analysis of the most recent studies in the field, including the latest advancements in CNN and ViT architectures, training methods, and performance evaluation metrics. Furthermore, the paper discusses the ethical considerations and challenges associated with the use of deep learning models for AD classification, such as the need for interpretability and the potential for bias. By addressing these issues, this review aims to provide valuable insights for future research and clinical applications, ultimately advancing the field of AD classification using deep learning techniques.

The processing of hyperspectral remote sensing images is a crucial field of study. As one of the most important phases in image processing right now, the classification task has attracted our attention. The Convolutional Neuronal Network (CNN) is one of the most demonstrative algorithms for deep learning since it is a sort of feed-forward neural network that uses convolutional computation. In this paper we proposed a customized model based on CNN applied on SAT 4 and SAT6 datasets. The experimental results outperformances methodology with accuracy value of 99.4%, loss of 2% and 99.8%, loss of 3.2% for SAT4 and SAT6, respectively.

Malaria disease should be considered and handled as a potential restorative catastrophe. One of the most challenging tasks in the field of microscopy image processing is due to differences in test design and vulnerability of cell classifications. In this article, we focused on applying deep learning to classify patients by identifying images of infected and uninfected cells. We performed multiple forms, counting a classification approach using the HSV color space. HSV is used since of its superior ability to speak to image brightness, at long last, for classification, a convolutional neural network (CNN) architecture is created. Clusters of focuses were used to deliver the classification. The highlights gotten to be forbidden, and a few more clamor sorts are included to the information. The suggested method has a precision of 99.79%, a recall value of 99.55%, and provides 99.96% accuracy.

Classification methods are carried out in several steps. The most important step is the development of classification rules based on a priori available knowledge; this is the learning phase. This phase uses either deductive or inductive learning. Inductive learning algorithms derive a set of classification rules (or standards) from a set of already classified examples. The goal of these algorithms is to produce classification rules to predict the assignment class of a new case. Among the available knowledge we can mention the choice of the initial cluster centers which is a very important factor in the final definition of clusters. For this purpose, we proposed an evolutionary algorithm EK-means based on the combination of k-means and fuzzy c-means by touching the initialization phase of the centroids. the performance of EK-means is compared with k-means according to the metrics of interclass and intraclass distances. To compare the efficiency of our optimization solution with traditional K-means, we rely on a UCI machine learning repository. The comparative study indicates a remarkable efficiency of our proposal, regardless of the type of data.