Abstract: Breast cancer is the leading cause of cancer death in women. Early detection and diagnosis are the most effective strategy to control tumour progression. The currently recommended imaging method for early determination and diagnosis of breast tumours. Classifications of still a big challenge and play a crucial role in assisting radiologists in accurate diagnosis this project, we propose a convolution neural network-based classification technique which is one of the deep learning techniques. The architectural model of CNN is used for the classification of breast cancer into normal and abnormal.

Pre-processing is performed on the input mammogram image to remove unwanted elements. Segment the tumour region using morphological operations, and highlight the region on the original mammogram image. If the mammogram image is normal, it indicates that the patient is healthy. BC patients and healthy patients are classified using Random Forest (RF) Classifiers.

Keywords: Deep learning, Cancer Detection, CNN, Feature Extraction.

PDF | DOI: 10.17148/IJARCCE.2023.125121

Open chat
Chat with IJARCCE