COMPUTER AIDED BREAST CANCER SEGMENTATION, FEATURE EXTRACTION, CLASSIFICATION AND DETECTION APPROACHES USING HISTOPATHOLOGICAL IMAGES: A REVIEW

Main Article Content

I.Sofiya, et. al.

Abstract

Breast cancer is one of the most common and lethal cancers in women. Since histopathological images provide adequate phenotypic information, they are essential in the diagnosis and treatment of breast cancers. Artificial Neural Network (ANN) methods are commonly used in the segmentation and classification tasks of breast histopathological images to increase the precision and objectivity of Breast Histopathological Image Analysis (BHIA). Histopathological photographs (HIs) are the gold standard for testing such forms of tumours for cancer diagnosis. Even for professional pathologists, analysing such images takes time and resources, and it is difficult, resulting in inter-observer and intra-observer disagreements. In this analysis, we provide a detailed overview of BHIA techniques based on ANNs. First and foremost, we divide the BHIA structures into classical and deep neural networks for further study. The related studies based on BHIA systems are then discussed. Following that, we study the current models to find the best algorithms. Finally, freely available datasets with download links are given for the convenience of potential researchers. In this article, we present a summary of ML and DL techniques with a focus on breast cancer.


 

Article Details

Section
Articles