Comparative Evaluation of Conventional and AI-Assisted Medical Imaging Techniques for Early Detection of Breast Cancer
Keywords:
Breast Cancer, Artificial Intelligence, Medical Imaging, Mammography, Deep Learning, Machine Learning, Convolutional Neural Networks, Computer-Aided Diagnosis, Radiology, Early Cancer Detection, Magnetic Resonance Imaging, Ultrasound Imaging, Explainable Artificial Intelligence, Healthcare Analytics, Precision MedicineAbstract
Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide, making early detection an essential factor in improving survival rates and reducing treatment complexity. Conventional imaging techniques such as mammography, ultrasound, and magnetic resonance imaging have served as the foundation of breast cancer screening for decades, yet these modalities face limitations related to human interpretation, diagnostic variability, false-positive findings, and missed lesions, particularly in women with dense breast tissue. Recent advancements in artificial intelligence, especially deep learning and convolutional neural networks, have transformed medical imaging by enabling automated lesion detection, image classification, risk prediction, and decision support for radiologists. This research presents a comparative evaluation of conventional and AI-assisted medical imaging techniques for the early detection of breast cancer using a comprehensive experimental framework. A dataset consisting of mammographic, ultrasound, and MRI images was analysed through both traditional radiologist-based diagnosis and AI-supported diagnostic systems. Performance indicators including accuracy, sensitivity, specificity, precision, F1-score, area under the receiver operating characteristic curve, diagnostic time, and false-positive rate were evaluated.
