Breast cancer remains one of the most prevalent and life-threatening diseases affecting women worldwide. Early detection plays a vital role in improving survival rates and reducing treatment complications. This study presents a hybrid feature extraction-based system for early prediction of breast cancer using thermal infrared imaging. Thermal imaging offers a non-invasive, cost-effective, and radiation-free alternative for regular screening across all age groups. The proposed approach leverages both spatial and local intensity variations in breast thermal images to capture discriminative patterns associated with abnormal physiological changes. A combination of handcrafted and deep learning-based feature extraction techniques is employed to enhance diagnostic accuracy. The extracted features are then fed into machine learning classifiers to predict potential malignancies. Experimental results demonstrate the effectiveness of the hybrid system in identifying early-stage breast cancer, highlighting its potential as a supplementary tool in clinical decision support systems.

Keywords: Breast Cancer, Thermal Imaging, Early Detection, Hybrid Feature Extraction, Infrared Thermography, Machine Learning, Non-Invasive Screening, Deep Learning, Image Classification, Computer-Aided Diagnosis.