Scholarlink

<p>Breast cancer (BC) is a major public health concern, and accurate diagnosis is crucial for effective treatment. Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), offers promising solutions for BC detection and classification. This review comprehensively analyzes the literature on AI-based BC diagnosis, focusing on medical imaging modalities, AI techniques, performance metrics, and challenges. The major goal of this research is to analyze the efficiency of DL and ML in different BC tasks, including detection, classification, segmentation, and optimal feature selection (FS). We also discuss the limitations and challenges faced in AI-based BC diagnosis and propose potential solutions. We investigate the role of trainable FS and data augmentation techniques in improving BC diagnosis using AI. The literature search was conducted from 2020 to September 2024 using Science Direct, Web of Science, Scopus, PubMed, Springer, IEEE, and Google Scholar datasets. Overall, this review demonstrates the significant potential of AI for advancing BC diagnosis and improving patient outcomes. Future research should focus on addressing the identified challenges and exploring innovative AI techniques to further enhance the accuracy and clinical utility of BC diagnostic tools.</p>

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

A Comprehensive Examination of Machine Learning and Deep Learning Approaches for Breast Cancer Detection, Classification, Segmentation, Augmentation, and Feature Selection

  • 期刊论文

  • 发表日期：

    2025年9月3日

查看全文
  • Jafar Majidpour,
  • Hakem Beitollahi

摘要

Breast cancer (BC) is a major public health concern, and accurate diagnosis is crucial for effective treatment. Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), offers promising solutions for BC detection and classification. This review comprehensively analyzes the literature on AI-based BC diagnosis, focusing on medical imaging modalities, AI techniques, performance metrics, and challenges. The major goal of this research is to analyze the efficiency of DL and ML in different BC tasks, including detection, classification, segmentation, and optimal feature selection (FS). We also discuss the limitations and challenges faced in AI-based BC diagnosis and propose potential solutions. We investigate the role of trainable FS and data augmentation techniques in improving BC diagnosis using AI. The literature search was conducted from 2020 to September 2024 using Science Direct, Web of Science, Scopus, PubMed, Springer, IEEE, and Google Scholar datasets. Overall, this review demonstrates the significant potential of AI for advancing BC diagnosis and improving patient outcomes. Future research should focus on addressing the identified challenges and exploring innovative AI techniques to further enhance the accuracy and clinical utility of BC diagnostic tools.