Abstract
Pathological examination is the most accurate method for the diagnosis of cancer. Breast cancer histopathology evaluation analyses the chemical and cellular characteristics of the cells of a suspicious breast tumor. A computer-aided automatic classifier with the help of machine learning can improve the diagnosis system in terms of accuracy and time consumption. These types of system can automatically distinguish a benign and malignant pattern in a breast histopathology image. It can reduce the workload of pathologists and can provide a more accurate process. In recent years, like in other areas, deep networks have also attracted for histopathology image analysis. Convolution Neural Network has become a preferred choice for images analysis including breast histopathology. In this paper, we review various deep learning concepts applied to breast cancer histopathology analysis and summarizes contributions to this field. We present a summary of the recent developments and a discussion about the best practices done using deep in breast histopathology analysis and improvements that can be done in future research.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call