The characteristic features of brain magnetic resonance image (MRI) scans of Alzheimer’s disease (AD) patients and normal controls (NC) are difficult to differentiate because of very similar brain patterns and image intensities at the initial stages. Thus, it is difficult to detect AD at earlier stages. The earlier detection can lead to earlier medication for the patients to avoid further and permanent damage to their brains. Thus, computer-aided systems for early Alzheimer’s disease detection are needed. For this purpose, the lossless feature extraction method combined with feature reduction using a selection approach is one of the best possible solutions presented in this paper. The dataset used for experimentation for AD detection is a combination of MRI images with very mild and mild cognitive impairments. The 2D dual-tree complex wavelet transform (DTCWT) is used for feature extraction. A recurrent neural network (RNN) architecture is used for classification purposes. The long short-term memory (LSTM) and gated recurrent unit (GRU) are used in combination in the proposed architecture. The performance evaluation of combinations of LSTM and GRU and individual layers is performed, in which LSTM sandwiched between two GRU in the proposed model shows better performance.
Lung cancer continues to be one of the leading causes of cancer-related deaths worldwide, as pulmonary nodules are often diagnosed at later stages. Therefore, accurate nodule classification is crucial for enabling early detection and supporting timely clinical decision-making. This study proposes a computer-aided diagnosis (CAD) system for lung nodule classification using computed tomography (CT) images, specifically focused on malignancy prediction and structural morphology analysis. The proposed framework is based on a novel attention-based Convolutional Neural Network (CNN) that incorporates both channel-wise and spatial attention mechanisms. This dual-attention structure enables the model to emphasize diagnostically relevant features while suppressing irrelevant background information, thereby improving interpretability and classification accuracy. For benchmarking purposes, CNN, CNN-SVM, and ResNet101 architectures were implemented for comparison. Experimental results on the LIDC-IDRI dataset for binary classification (benign vs. malignant) and on the IQ-OTH/NCCD dataset for both binary and three-class (normal, benign, malignant) classification tasks demonstrate that the proposed Attention-Based CNN outperforms all baseline models, achieving a maximum classification accuracy of 98% in the binary setting. In addition to accuracy, the proposed model achieves strong performance across multiple evaluation metrics, including precision, recall, F1-score, AUC, and separately reported confusion matrices for both binary and multiclass evaluations, indicating the robustness of the approach. The dual-attention mechanism enhances salient feature localization and discriminative representation learning, thereby contributing to improved performance in both binary and multiclass classification tasks