Multi class breast cancer classification from multi magnification scales using histopathological images

Over the last few decades, cases of breast cancer have increased enormously. Early detection of cancer is one of the main approaches to prevent death. The only way to cure this disease is to detect breast cancer at early stages. Delay in identifying breast cancer leads to an increase in the death rate. The advent of technology has made it easier for humans to automate patient prognosis and deduction of disease from symptoms and report analysis. Although modern era technology makes it easy to detect cancers early. A machine learning algorithm is applied to diagnose breast cancer early in this research. This research proposed a decision level fusion based on convolutional neural network (CNN) and deep extreme learning machine (DELM) algorithms for multi-class breast cancer classification. CNN is a sort of deep learning that is unique. This study used a CNN to categorize and distinguish breast cancer images from the BreakHis dataset, divided into four benign and four malignant subtypes. Deep extreme machine learning generally uses sequences of several layers to accomplish the feature extraction and classification tasks. It implemented and succeeded in breast cancer disease classification in early stages by achieving better accuracy