Classification of Histopathological Image for Predication of Breast Cancer Using Pre-Trained Resnet 50 Model

Abstract

One of the most common and deadly types of cancer that affects women globally is breast cancer. Accurate diagnosis and early detection are essential for enhancing patient outcomes. Recent developments in deep learning and computer vision have demonstrated promising outcomes in the processing of medical images. To improve the precision of breast cancer detection, this project offers a study on the categorization of breast cancer images using transfer learning techniques and the ResNet50 model. In terms of classification accuracy and reliable feature extraction, this project showed ResNet50 to perform better than CNNs, highlighting its higher potential for precise breast cancer prediction from CT-SCAN images. The significance of deep learning architectures like ResNet50 in enhancing medical picture classification tasks is highlighted by these findings.