Scholarlink

The basic building blocks of the human body are cells, and cancer is defined as an abnormal proliferation of bodily cells. There are however numerous other causes of cancer. Cancer has emerged as one of the world's most perilous causes of death in recent years. The fatality rate of Breast Cancer (BC) is increasing globally on a daily basis. The majority of women worldwide lost their lives as a result of BC. In 2020, an estimated 2,261,419 new breast cancer cases for women were reported worldwide. Histopathology image data analysis can be used to diagnose or forecast breast cancer in the majority of instances, but this type of analysis at the genetic level is very time-consuming and expensive. In this study, the main objective is to examine various well-known Machine Learning (ML) techniques, including Logistic Regression, Random Forest, KNN, and Decision Tree, in order to investigate BC. This proposed technique introduces a hybrid approach based on the overlap value of particular features and also attempts to calculate the accuracy at every stage. Additionally, thoroughly examine the correctness of the suggested system in comparison to existing models.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

An Innovative Machine Learning Approach for Breast Cancer Detection Based on Comparative Analysis

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Manab Kumar Das,
  • Swapnamoy Bhattacharjee,
  • Saikat Mondal,
  • Soham Goswami

摘要

The basic building blocks of the human body are cells, and cancer is defined as an abnormal proliferation of bodily cells. There are however numerous other causes of cancer. Cancer has emerged as one of the world's most perilous causes of death in recent years. The fatality rate of Breast Cancer (BC) is increasing globally on a daily basis. The majority of women worldwide lost their lives as a result of BC. In 2020, an estimated 2,261,419 new breast cancer cases for women were reported worldwide. Histopathology image data analysis can be used to diagnose or forecast breast cancer in the majority of instances, but this type of analysis at the genetic level is very time-consuming and expensive. In this study, the main objective is to examine various well-known Machine Learning (ML) techniques, including Logistic Regression, Random Forest, KNN, and Decision Tree, in order to investigate BC. This proposed technique introduces a hybrid approach based on the overlap value of particular features and also attempts to calculate the accuracy at every stage. Additionally, thoroughly examine the correctness of the suggested system in comparison to existing models.