Being the most common type of cancer worldwide, and affecting over 2.3 million women, breast cancer poses a significant health threat. Although survival rates have improved around the world due to advances in screening, diagnosis, and treatment, early detection remains crucial for effective management. This study seeks to introduce a novel hybrid model that makes use of image-preprocessing techniques and deep-learning algorithms on mammograms to enhance the detection and classification accuracy of breast cancer lesions. The model was tested on a dataset comprising 20,000 mammograms. First, image-processing techniques, such as Contrast-Limited Adaptive Histogram Equalization, Gaussian Blur, and sharpening methods were used to optimize the images for enhanced feature extraction. In addition, the Ensemble Deep Random Vector-Functional Link Neural Network algorithm, YOLOv5, and MedSAM segmentation models were utilized for robust deep learning-based extraction, classification, and visualization of lesions. Finally, the model was clinically validated on 800 patients. The study found a notable enhancement in both accuracy and processing time for benign and malignant diagnoses using the hybrid model. The model achieves an impressive accuracy of 99.7 % and demonstrates a remarkable processing time of 0.75 s. In clinical applications, the hybrid model exhibits high proficiency, reporting 97.2 % accuracy for benign cases and 98.6 % for malignant scenarios. These results highlight the effectiveness of the hybrid model in improving diagnostic accuracy, offering a promising tool for early breast cancer detection.

Ischemic brain strokes are severe medical conditions that occur due to blockages in the brain’s blood flow, often caused by blood clots or artery blockages. Early detection is crucial for effective treatment. This study aims to improve the detection and classification of ischemic brain strokes in clinical settings by introducing a new approach that integrates the stroke precision enhancement, ensemble deep learning, and intelligent lesion detection and segmentation models. The proposed hybrid model was trained and tested using a dataset of 10,000 computed tomography scans. A 25-fold cross-validation technique was employed, while the model’s performance was evaluated using accuracy, precision, recall, and F1 score. The findings indicate significant improvements in accuracy for different stages of stroke images when enhanced using the SPEM model with contrast-limited adaptive histogram equalization set to 4. Specifically, accuracy showed significant improvement (from 0.876 to 0.933) for hyper-acute stroke images; from 0.881 to 0.948 for acute stroke images, from 0.927 to 0.974 for sub-acute stroke images, and from 0.928 to 0.982 for chronic stroke images. Thus, the study shows significant promise for the detection and classification of ischemic brain strokes. Further research is needed to validate its performance on larger datasets and enhance its integration into clinical settings.

Background: The early and accurate classification of ischemic stroke stages on computed tomography (CT) remains challenging due to subtle attenuation differences and significant scanner variability. This study developed a neural network framework to dynamically optimize Hounsfield Unit (HU) transformations and CLAHE parameters for temporal stage-specific stroke classification. Methods: We analyzed 1480 CT cases from 68 patients across five stages (hyperacute, acute, subacute, chronic, and normal). The training data were augmented via horizontal flipping, ±7° rotation. A convolutional neural network (CNN) was used to optimize linear transformation and CLAHE parameters through a combined loss function incorporating the effective measure of enhancement (EME), peak signal-to-noise ratio (PSNR), and regularization. the enhanced images were classified using logistic regression (LR), support vector machines (SVMs), and random forests (RFs) with 25-fold cross-validation. Model interpretability was evaluated using Grad-CAM. Results: Neural network optimization significantly outperformed static parameters across validation metrics. Deep CLAHE achieved the following accuracies versus static CLAHE: hyperacute (0.9838 vs. 0.9754), acute (0.9904 vs. 0.9873), subacute (0.9948 vs. 0.9825), and chronic (near-perfect 0.9979 vs. 0.9808). Qualitative interpretability analysis confirmed that models focused on clinically relevant regions, with optimized enhancement producing more coherent attention patterns than static methods. Parameter analysis revealed stage-aware adaptation: conservative enhancement in early phases (slope: 1.249–1.257), maximized in subacute (slope: 1.290–1.292), and restrained in the chronic phase (slope: 1.240–1.258), reflecting underlying stroke pathophysiology. Conclusions: A neural network-optimized framework with interpretability validation provides stage-specific stroke classification that achieves superior performance over static methods. Its pathophysiology-aligned parameter adaptation offers a clinically viable and transparent solution for emergency stroke assessment.