Year: 2025
Type: article
Abstract: : Breast cancer (BC) is the second most prevalent type of cancer among women and a leading cause of cancer-related deaths. Its mortality rate is alarmingly high, but early detection can significantly reduce its impact. Timely diagnosis of BC greatly improves the prognosis and chances of recovery, often enabling prompt surgical or therapeutic interventions. Therefore, it is crucial to have a system that allows the healthcare industry to detect breast cancer both quickly and accurately. Machine learning (ML) has emerged as a powerful tool for breast cancer pattern classification, owing to its ability to model and extract critical features from complex datasets. In this paper, we propose a system for the automatic detection of breast cancer diagnosis and prognosis using an ensemble of classifiers. We begin by reviewing various machine learning algorithms, including artificial neural networks (ANN), and explore the use of ensemble techniques combining different classifiers. The study provides an overview of these ML algorithms and discusses their application in automating BC diagnosis and prognosis. Furthermore, we present and compare multiple ensemble models, along with other ML-based approaches, both with and without up-sampling techniques, using two benchmark datasets. We also examine the impact of applying balanced class weights to the prognosis dataset and evaluate its performance relative to other methods. Our experimental results demonstrate that the proposed ensemble method outperforms existing state-of-the-art techniques, achieving a high accuracy of 98.83%. Due to its superior performance, the proposed system holds significant potential for adoption in the medical field and could be of great value to the broader research community
Authors: Rohan Berad, Jyoti Mali, Aniket Kadam, Sagar Pandule, Shrikrishna Nimbekar
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4409404203