Current Medical Imaging

Author(s): Safia Naveed S.*

DOI: 10.2174/1573405618666220930150625

DownloadDownload PDF Flyer Cite As
Prediction of Breast Cancer Through Random Forest

Article ID: e300922209414 Pages: 12

  • * (Excluding Mailing and Handling)

Abstract

Background: 8% of women are diagnosed with breast cancer. (BC) BC is the second most common cause of death in both developed and undeveloped countries. BC is characterized by the mutation of genes, constant pain, changes in the size, color (redness), and skin texture of breasts. Classification of breast cancer leads pathologists to find a systematic and objective prognostic; generally, the most frequent classification is binary (benign/malignant).

Introduction: Machine Learning (ML) techniques are broadly used in breast cancer classification. They provide high classification accuracy and effective diagnostic capabilities. Breast cancer remains one of the top diseases that lead to thousands of deaths in women yearly. Artificial intelligence (AI) has been utilized to rapidly and accurately identify breast tumors and for early diagnosis. This paper aims to research, determine and classify these tumors.

Methods: Machine learning algorithm such as Random Forest (RF) is used to classify medical images into malignant and benign. Moreover, Machine learning has been employed recently for the same purpose.

Results: The results showed that Random Forest achieved high accuracy; therefore, the researchers utilized various functions for this algorithm and added more features such as bagging and boosting to increase its efficacy.

Conclusion: The random Forest algorithm achieved an enhanced accuracy of 98%.

Keywords: Breast cancer, machine learning, artificial intelligence, random forest, WDBC.