A Comprehensive Review of Computer-Aided Models for Breast Cancer Diagnosis Using Histopathology Images

Abstract

Breast cancer is the second most common cancer in women who are mainly middle-aged and older. The American Cancer Society reported that the average risk of developing breast cancer sometime in their life is about 13%, and this incident rate has increased by 0.5% per year in recent years. A biopsy is done when screening tests and imaging results show suspicious breast changes. Advancements in computer-aided system capabilities and performance have fueled research using histopathology images in cancer diagnosis. Advances in machine learning and deep neural networks have tremendously increased the number of studies developing computerized detection and classification models. The dataset-dependent nature and trial-and-error approach of the deep networks' performance produced varying results in the literature. This work comprehensively reviews the studies published between 2010 and 2022 regarding commonly used public-domain datasets and methodologies used in preprocessing, segmentation, feature engineering, machine-learning approaches, classifiers, and performance metrics.

Keywords: breast cancer; classification; computer-aided diagnosis (CAD); deformable modes; histopathology; machine learning; review.

Figure 1

(a) The number of studies in CADe and CADx systems using breast histopathology images. (b) PRISMA flow diagram for the review of CADe and CADx systems using breast histopathology images.

Figure 2

Organization of the review of analysis and diagnosis of breast cancer from histopathology images.

Figure 3

Histopathology images from BreakHis 400× dataset. The blue, green, yellow, and red arrows indicate adipose tissue, a cell nucleus, a mitotic figure, and large nuclei in the images. The image in (a) is labeled malignant, while the image in (b) is labeled benign.

Figure 4

Images in (a,b) are from the BreakHis ×400 dataset. The image in (c) is from the BACH dataset. Images show various stain colors and illuminations.

Figure 5

Distribution of the machine learning methods in CADe and CADx systems using breast histopathology images.