Detection of Breast Cancer from Histopathological Images using Image Processing and Deep-Learning

Abstract

Breast cancer is the most commonly occurring cancer in women. Cancer patients frequently develop metastasis, which is responsible for more than 90% of their deaths. The mortality rate will be significantly reduced if it is identified and treated in an early phase. The categorization of cancer cells is critical for medical diagnosis, tailored therapy, and disease prevention. Classifying various types of these cells with great precision has remained a difficult issue. Deep learning has emerged as a significant tool for such challenging tasks in the fields of biology and medicine. In this research, we propose a novel model that throws light on image processing and deep learning for breast cancer classification from histopathological images. The proposed Vision transformer model outperforms the state-of-the-art convolution neural networks in classifying the breast cancer cell with an accuracy of 96%.