Scholarlink

<p>In recent years, there has been a rise in interest in the application of deep learning (DL) to breast cancer identification. This work intends to deliver a review demonstrating new DL applications for identifying and categorizing breast cancer and offers a bibliometric analysis of advancements in this field. A comprehensive search between January 1, 2016, and February 20, 2023, was done on the Scopus database to perform the bibliometric analysis of DL applications in breast cancer detection. The statistics on publications, journals, authors, nations, and keywords were created using VOSviewer software. Moreover, Medline (through PubMed), Web of Science (WoS), and Scopus were used for the scoping review (from January 1, 2016, to December 24, 2022); all retrieved titles were checked for eligibility requirements by the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) methodology. Since 2016, the frequency of papers being recovered has grown, and in 2022, a significant number of citations were retrieved. This paper gives a general overview of the various DL methodologies and tailored architectures for the detection, categorization, and segmentation of breast cancer. Performance of the approaches is assessed using accuracy, sensitivity, specificity, area under curve (AUC), F1 score, Dice similarity coefficient (DSC), and intersection over union (IoU); results with high accuracy are frequently obtained at the expense of sensitivity.</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 scoping and bibliometric review of deep learning techniques in breast cancer imaging: mapping the landscape and future directions

  • 期刊论文

  • 发表日期：

    2025年5月13日

查看全文
  • Sorayya Rezayi,
  • Merhbakhsh Nilashi,
  • Erfan Esmaeeli,
  • Nahid Ramezanghorbani,
  • Goli Arji,
  • Hossein Ahmadi,
  • Leila Shahmoradi,
  • Maryam Zahmatkeshan

摘要

In recent years, there has been a rise in interest in the application of deep learning (DL) to breast cancer identification. This work intends to deliver a review demonstrating new DL applications for identifying and categorizing breast cancer and offers a bibliometric analysis of advancements in this field. A comprehensive search between January 1, 2016, and February 20, 2023, was done on the Scopus database to perform the bibliometric analysis of DL applications in breast cancer detection. The statistics on publications, journals, authors, nations, and keywords were created using VOSviewer software. Moreover, Medline (through PubMed), Web of Science (WoS), and Scopus were used for the scoping review (from January 1, 2016, to December 24, 2022); all retrieved titles were checked for eligibility requirements by the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) methodology. Since 2016, the frequency of papers being recovered has grown, and in 2022, a significant number of citations were retrieved. This paper gives a general overview of the various DL methodologies and tailored architectures for the detection, categorization, and segmentation of breast cancer. Performance of the approaches is assessed using accuracy, sensitivity, specificity, area under curve (AUC), F1 score, Dice similarity coefficient (DSC), and intersection over union (IoU); results with high accuracy are frequently obtained at the expense of sensitivity.