Breast Cancer Detection with Optimized Machine-Learning Techniques

Breast cancer, ranking as the second-leading cause of cancer-related deaths in women globally, necessitates swift detection and advanced treatment strategies to mitigate its high mortality rate. This research explores the fusion of machine learning and image analysis techniques for early breast cancer detection using blood analysis data. The study introduces a novel approach by converting numerical blood analysis data into image data, significantly enhancing classification accuracy. Employing popular Convolutional Neural Network (CNN) models, namely AlexNet, ResNet50, and DenseNet201, the research achieves a superior classification accuracy of 95.33% with ResNet50. This surpasses existing studies using similar data and establishes the effectiveness of the proposed methodology. Furthermore, the conversion of numerical blood analysis images into image data represents a pioneering strategy. This research underscores the critical role of automated systems in breast cancer detection and emphasizes the potential for improved outcomes through early diagnosis.