AI-Powered Breast Cancer Classification: Leveraging CNNs for Early Detection
Vishnu Kant, Deepak P. Gupta, Srinivas Aluvala · 2024
Among the most common and fatal diseases afflicting women throughout is breast cancer. Early detection greatly increases survival rates, hence reliable and effective diagnostic instruments are rather important for patient treatment. Although conventional screening techniques like mammography are efficient, false positives and false negatives present problems that can cause treatment delays. Using deep learning methods to enhance diagnosis accuracy and provide scalable screening systems, this work investigates the application of Convolutional Neural Networks (CNNs) for breast cancer categorization. CNNs provide great accuracy in spotting anomalies and automatically recognize patterns and characteristics, hence improving medical imaging. This work created and trained a proprietary CNN model using a dataset obtained from the Kaggle platform comprising 549 photos encompassing both malignant and non-cancerous samples. With an accuracy of 89%, the proposed model shows promise to help radiologists in early breast cancer detection, so improving healthcare outcomes and supporting the worldwide goals of improving health and well-being, so lowering inequalities in medical access, and so promoting innovation in healthcare technologies. In line with more general goals for excellent healthcare systems worldwide, our work helps the continuous endeavor to provide more sustainable and scalable options for early diagnosis of breast cancer.