An Extensive Analysis of Breast Cancer detection using Deep Learning Algorithms

Breast cancer remains a significant global health concern around the world, where early and accurate detection is essential for improving patient outcomes. This work aims to outdo the traditional diagonosis methods by employing three deep learning models: a fully connected neural network (FCNN), a convolutional neural network (CNN), and a feedforward neural network (FNN). Each model was analyzed for its ability to distinguish between benign and malignant cases using minimal feature variables. Among the models, the FNN showed higher validation accuracy compared to the CNN, which, while proficient at detecting complex patterns, was less effective in structured data. The FCNN, with added dense layers, performed similarly to the FNN, suggesting that the inclusion of dense layers did not significantly enhance the model’s accuracy. This research presents an innovative comparison to recent studies, demonstrating the flexibility and adaptability of neural networks for breast cancer diagnostics. The models’ ability to improve detection accuracy can significantly impact healthcare by providing reliable tools for early intervention. The findings contribute to the growing body of evidence supporting the integration of artificial intelligence into clinical practice, paving the way for more personalized treatment plans, reduced misdiagnosis rates, and overall improved patient care outcomes in cancer detection and treatment.