Early and accurate detection of Alzheimer's disease (AD) is crucial for a timely clinical intervention. Atrophy of the hippocampus has been established as a key neurodegenerative biomarker. This study presents a Hybrid 3D CNN–ResNet model for automated hippocampal segmentation and dementia classification using high-resolution MRI scans. The proposed framework integrates 3D U-Net-based hippocampal segmentation with multi-scale feature extraction and deep residual learning, enabling a precise atrophy quantification and robust classification across the AD stages. A standardized preprocessing pipeline, incorporating NIfTI conversion, spatial normalization, denoising, and contrast enhancement, ensures consistency across multi-site datasets. The model was optimized using AdamW, Cyclical Learning Rate (CLR), and early stopping, achieving 97.31% classification accuracy and a 92.84% Dice Similarity Coefficient (DSC) for hippocampal segmentation. Grad-CAM and SHAP-based interpretability confirm the biologically meaningful feature representations, aligning with established hippocampal atrophy patterns in AD progression. The external validation on the OASIS dataset demonstrated strong generalization, with only a 2.3% accuracy reduction, underscoring the model’s robustness and clinical applicability. These findings establish the proposed approach as an effective and interpretable deep learning framework for early AD diagnosis and longitudinal disease monitoring.
Camouflaged Object Detection (COD), is a technology with applications in military surveillance, protection of animals, and intelligent security systems. Traditional computer vision COD methods, such as edge detection and color-based segmentation, frequently fail to function well in real-world scenarios that undergo rapid transformations over time. CamoVision is a Deep Learning (DL)-based dual-mode framework that has the ability to locate camouflaged objects in photos (CamoVision 1.0) and video streams (CamoVision 2.0). To improve the design, which is based on the U-Net and a ResNet-50 encoder, a hybrid loss function that consisted of Dice and BCE was utilized. In addition, the model was trained using strategies that involved mixed precision to maximize its efficiency and speed up the convergence process. The acquired Intersection-over-Union (IoU) score of 0.82 and Dice coefficient of 0.85 showcase the robustness of the proposed system. In addition, the video pipeline operates in real time at a rate of 30 fps, which makes it versatile enough to be utilized in settings where time is of particular significance.