Predictive model Approach for Breast Cancer Detection using Deep Learning
Main Article Content
Abstract
Breast cancer is still among the most common causes of death among women in the world and early and correct detection can greatly help to increase the survival chances. This paper suggests a predictive algorithm of breast cancer detection with the help of deep learning algorithms and convolutional neural networks more specifically to process medical imaging data and determine the presence of a benign or a malignant tumor. The model is trained using publicly available data, which is properly preprocessed by normalizing and data augmentation to improve the performance and lessen overfitting. The primary evaluation measures of accuracy, precision, recall, F1-score, and ROC-AUC are used to evaluate the model effectiveness. The suggested solution has a better diagnostic accuracy than conventional machine learning and manual interpretation, fewer false negatives and aids in clinical decisionmaking. The research also identifies the prospect of incorporating the deep learning models into the healthcare systems to achieve effective, scalable, and dependable screening of breast cancer, which can be used to improve patient outcomes and early intervention measures.