Formulation of Algorithms for Intelligent Hybrid Image Processing Model for Breast Cancer Detection Using Machine Learning Techniques

Abstract

Breast cancer remains one of the leading causes of mortality among women worldwide, where early and accurate diagnosis plays a critical role in improving survival rates and treatment outcomes. Despite significant advances in medical imaging and artificial intelligence, existing diagnostic systems still face key limitations related to data privacy, lack of interpretability, and limited generalization across diverse clinical settings. This paper presents the formulation and development of an intelligent hybrid biomedical image processing framework for breast cancer detection, prediction, and classification using Federated Explainable Artificial Intelligence (XAI)–based machine learning models. The proposed approach integrates hybrid image pre-processing techniques for noise reduction and feature enhancement, deep learning–based segmentation for precise region-of-interest extraction, and hybrid classification models that combine deep neural networks with ensemble learning methods. By incorporating federated learning, the framework enables decentralized model training across multiple healthcare institutions without sharing sensitive patient data, ensuring compliance with privacy regulations while enhancing model robustness and generalization. Furthermore, the proposed system embeds explainable AI mechanisms such as Grad-CAM, LIME, and SHAP to provide transparent and interpretable diagnostic insights, thereby improving clinician trust and supporting informed medical decision-making. Extensive evaluation using benchmark mammographic and histopathological datasets demonstrates that the hybrid federated explainable framework achieves high accuracy, sensitivity, and specificity while maintaining strong privacy guarantees and interpretability. Overall, this work contributes a scalable, privacy-preserving, and clinically reliable diagnostic framework that has strong potential for real-world deployment in intelligent healthcare systems aimed at early breast cancer detection and improved patient outcome.