Breast Cancer Detection Using Machine Learning and Transfer Learning

Abstract

This study explored the application of deep learning techniques to enhance the detection of breast cancer. The research aimed to improve the accuracy, reliability, and efficiency of breast cancer diagnosis methods by addressing the limitations of traditional imaging and computeraided diagnostic (CAD) systems. The study focused on the development and evaluation of advanced deep learning models, including YOLOv8 for object detection and Mask R-CNN for segmentation and tumour size prediction. The findings of the research indicate that the Random Forest model demonstrated the highest accuracy in identifying various BI-RADS categories, supporting the reliability and effectiveness of the model in breast cancer detection. The integration of these advanced deep learning models into the clinical workflow can streamline the diagnostic process, reduce false positives and negatives, and improve patient outcomes by enabling early detection and treatment. The study contributes to the field of breast cancer detection by showcasing the transformative impact of deep learning in addressing the complex challenges of medical imaging. The comparative analysis of different models provides valuable insights and a foundation for future research and development efforts in this area.