Abstract

Simple SummaryBreast cancer is one of the most commonly diagnosed diseases in females around the world. The most threatening is when cancer spreads uncontrollably to other parts of the body and can cause death. Early detection of breast cancer lowers the risk of death among patients and enables appropriate treatments to control the progression of cancer. To diagnose breast cancer, high complex visuals of the breast tissue can be collected through histopathology images that provide informative details which validate the stage of the cancer. The aim of this study is to investigate techniques applied in histopathology images in diagnosing breast cancer.A computer-aided diagnosis (CAD) expert system is a powerful tool to efficiently assist a pathologist in achieving an early diagnosis of breast cancer. This process identifies the presence of cancer in breast tissue samples and the distinct type of cancer stages. In a standard CAD system, the main process involves image pre-processing, segmentation, feature extraction, feature selection, classification, and performance evaluation. In this review paper, we reviewed the existing state-of-the-art machine learning approaches applied at each stage involving conventional methods and deep learning methods, the comparisons within methods, and we provide technical details with advantages and disadvantages. The aims are to investigate the impact of CAD systems using histopathology images, investigate deep learning methods that outperform conventional methods, and provide a summary for future researchers to analyse and improve the existing techniques used. Lastly, we will discuss the research gaps of existing machine learning approaches for implementation and propose future direction guidelines for upcoming researchers.

Highlights

  • Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.Licensee MDPI, Basel, Switzerland.The human body is formed of trillions of cells

  • Belsare et al proposed to extract the textural features such as grey-level co-occurrence matrix (GLCM), graph run length matrix (GRLM) features, and Euler number; their system was able to achieve a 100% accuracy in 70 histopathological images on a dataset from Department of Pathology, Govt

  • It requires more effort and skills to ogy images of breast cancer to train the convolutional neural networks (CNN) model. It requires more effort and skills achieve a reliable performance CNN model when it comes to selecting hyperparamto achieve a reliable performance CNN model when it comes to selecting hyperpaeters such as learning rate, number of layers, convolutional filters and more, which rameters such as learning rate, number of layers, convolutional filters and more, can be a challenging task

Read more

Summary

Introduction

Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. The human body is formed of trillions of cells. ‘Cancer’ is a term used when a cell divides abnormally or uncontrollably, which can happen in various parts of the body. The disease type is categorised based on which part of the body cancer occurs. This situation, if left unchecked, will lead to death. Amongst the distinct types of cancer, the most common type of cancer happening in females is breast cancer. H.; Zheng, B.; Yoon, S.W.; Ko, H.S. A Support Vector Machine-Based Ensemble Algorithm for Breast Cancer Diagnosis

Objectives
Methods
Discussion
Conclusion
Full Text
Published version (Free)

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