•  
  •  
 

Abstract

This paper comprehensively reviews the classification of breast cancer histological images. The paper discusses the research objectives, methodologies used, and conclusions drawn, as well as suggestions for the future. The study is based on the ICIAR 2018 database, which is considered one of the largest databases available to support this research. The paper also addresses major challenges such as lack of data, variation in tissue preparation, class imbalance, and computational requirements. Advanced techniques such as deep learning (DL), transfer learning and data augmentation are explored, along with innovative models such as convolutional neural networks (CNNs) and generative adversarial networks (GANs). The study focuses on integrating multimodal (histological, genetic, and clinical) data to enhance diagnostic accuracy and enable personalized treatments. Breast cancer is responsible for 25.4% of cancer cases, with 1 in every 12 women developing this fatal disease. In 2020, a large number of women died as a result of the disease spreading through lymphatic and blood vessels, with the number of deaths reaching about 685,000 cases. Improving outcomes depends greatly on early detection of the disease and providing appropriate and effective treatment. Future directions include addressing challenges related to texture image classification and promoting standardized data sets with the goal of developing diagnostic tools and treatment strategies.

Download

Share

COinS