AST-CNN: Innovative Breast Cancer Detection with Salp Swarm Optimization

Timely detection of breast cancer is essential for improving patient outcomes. Existing breast cancer detection methods with mammography, often suffer from time-consuming procedures and a notable rate of false positives. To address these issues, we propose an innovative approach for early breast cancer detection, merging Artistic Style Transfer with Convolutional Neural Networks (AST-CNN) and leveraging Salp Swarm Optimization (SSO). Our method starts with meticulous image preprocessing to enhance quality. We then employ AST -CNN to extract high-level features from the preprocessed images. These features are pivotal for distinguishing cancerous from non-cancerous tissue. For image classification, we harness the unique adaptability of SSO, an algorithm inspired by salp foraging behavior. Our approach was rigorously tested using a diverse dataset of breast cancer images, achieving an impressive accuracy of 98%, surpassing traditional methods and displaying remarkable speed. Beyond the laboratory, our method holds the potential to revolutionize breast cancer diagnostics. It can facilitate the development of more accurate, efficient, and accessible screening tests and aid radiologists in making precise breast cancer diagnoses, ultimately improving patient outcomes.