Machine-driven techniques for early-stage tumor identification and categorization in Digital Mammography: A comprehensive overview
Ravindra Moje, Harshada Vishal Mhetre, Mangal V. Patil, Prashant Chougule, Pramod Jadhav, Priyanka Paygude, Shwetambari Chiwhane · Journal of Integrated Science and Technology · 2025
Breast cancer remains a critical research focus in medical image analysis, being a leading cause of mortality among women. Digital mammography enhances early detection accuracy, crucial for improved prognosis. By 2020, breast cancer is projected to account for 25% of all cancer cases, characterized by uncontrolled cell proliferation in breast tissue. X-ray imaging can reveal tumor formation, with malignancy defined by metastatic potential. Traditional diagnostic approaches, often time-consuming and operator-dependent, necessitate more efficient detection methods. This study proposes an innovative deep learning-based classification system for automated breast cancer identification using biopsy images. The model's performance is evaluated using statistical metrics including precision, recall, and accuracy. By addressing key challenges in AI-assisted risk assessment, this research aims to accelerate the integration of advanced predictive tools, potentially optimizing and personalizing mammography screening programs in the future.