Scholarlink

Background <p>Cervical cancer continues to be the second most prevalent type of cancer in women globally, especially in the less developed areas. Among several screening methods Pap test, more popularly known as the Papanicolaou test or Pap smear, is one of the most efficient ones for the early detection of this type of cancer. AI has recently made possible the large-scale screening of the whole process. This whole thing has been done in order to increase the early detection rates, which is the long-term aim of reducing the number of cases and deaths that are due to cervical cancer.</p> Objective <p>This systematic review aimed to investigate the role of artificial intelligence in the diagnosis of cervical cancer based on Pap smear results.</p> Methods <p>A comprehensive search was conducted in PubMed, Web of Science, Scopus, Cochrane Library, and Google Scholar from database inception to January 2025, with the final search update performed on January 30, 2025. The search strategy was designed using relevant keywords and their synonyms related to “artificial intelligence,” “diagnosis,” and “cervical cancer.”This review included only the English-language studies that had investigated the application of AI in the diagnosis of cervical cancer using Pap test data. The titles and abstracts were initially reviewed by two independent reviewers, and subsequently, full-text assessment was carried out. Data extraction followed the use of standardized forms that collected information on study title, country, number of participants, study purposes, AI technique, error rate, accuracy, and performance outcomes.</p> Results <p>The initial search identified 844 studies, of which 22 met the inclusion criteria and were included in the final analysis. Most studies reported that AI-based algorithms improved the accuracy and efficiency of cervical cancer detection using Pap smear images. Deep learning and machine learning approaches demonstrated high diagnostic performance, with several studies reporting accuracy rates above 90%.</p> Conclusion <p>AI-based approaches show considerable potential for improving the accuracy and timeliness of cervical cancer diagnosis using Pap smear analysis. However, further high-quality studies are required to validate these tools and support their integration into clinical practice.</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

Artificial intelligence for cervical cancer screening and diagnosis using Pap smear images: a systematic review

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月30日

查看全文
  • Aynaz Esmailzadeh,
  • Asma Rashki Kemmak,
  • Alireza Rasoulian,
  • Fatemeh Sadat Alizadeh Tabatabaei,
  • Mohammad Reza Mazaheri Habibi

摘要

Background

Cervical cancer continues to be the second most prevalent type of cancer in women globally, especially in the less developed areas. Among several screening methods Pap test, more popularly known as the Papanicolaou test or Pap smear, is one of the most efficient ones for the early detection of this type of cancer. AI has recently made possible the large-scale screening of the whole process. This whole thing has been done in order to increase the early detection rates, which is the long-term aim of reducing the number of cases and deaths that are due to cervical cancer.

Objective

This systematic review aimed to investigate the role of artificial intelligence in the diagnosis of cervical cancer based on Pap smear results.

Methods

A comprehensive search was conducted in PubMed, Web of Science, Scopus, Cochrane Library, and Google Scholar from database inception to January 2025, with the final search update performed on January 30, 2025. The search strategy was designed using relevant keywords and their synonyms related to “artificial intelligence,” “diagnosis,” and “cervical cancer.”This review included only the English-language studies that had investigated the application of AI in the diagnosis of cervical cancer using Pap test data. The titles and abstracts were initially reviewed by two independent reviewers, and subsequently, full-text assessment was carried out. Data extraction followed the use of standardized forms that collected information on study title, country, number of participants, study purposes, AI technique, error rate, accuracy, and performance outcomes.

Results

The initial search identified 844 studies, of which 22 met the inclusion criteria and were included in the final analysis. Most studies reported that AI-based algorithms improved the accuracy and efficiency of cervical cancer detection using Pap smear images. Deep learning and machine learning approaches demonstrated high diagnostic performance, with several studies reporting accuracy rates above 90%.

Conclusion

AI-based approaches show considerable potential for improving the accuracy and timeliness of cervical cancer diagnosis using Pap smear analysis. However, further high-quality studies are required to validate these tools and support their integration into clinical practice.