Improvised Breast Cancer Detection Using Cnn With Particle Swarm Optimization (Pso)
A. Poongodai, Sadlapalli Pavani, Shaik Mohammed Khalil, Pasham Jaya Prakash, Cheenepalli Reddy Ujwal · 2025
Early detection and accurate diagnosis of breast cancer continues to be one of the top common and deadly diseases among women across the globe. We propose in this work, an enhanced breast cancer detection system that synergizes the use of CNN model, MobileNetV2 using Particle Swarm Optimization (PSO) to improve diagnostic performance. Deep features are extracted from mammographic images by MobileNetV2 without any human intervention, and these features are capable of capturing the details that distinguish between benign and malignant tumors. PSO, a bio-inspired optimization algorithm, is used for the purpose of tuning the hyperparameters of CNN efficiently to further refine the model's accuracy and avoid overfitting. The results presented in this hybrid framework show that it greatly increases detection precision, reduces false positive incidence and speeds up convergence of the model. The proposed approach unites deep learning with optimization algorithms to furnish a reliable, robust, and scalable solution to computer aided breast cancer diagnosis which helps the healthcare professionals in making quicker and more correct decisions which would ultimately lead to better patient care, and therefore, better patient results.