Scholarlink

<p>The field of forensic dentistry has witnessed a marked rise in the utilization of artificial intelligence (AI), particularly in the domains of age estimation, gender classification, and human identification through dental image analysis. Although there are more publications in this field now than there used to be, there has not been a full review of how good the methods are and how things have changed over time. The aim of this systematic review is to assess the state of the literature on AI-based forensic dental image analysis using two complementary methods: (1) Publication dynamics and keyword trends are examined using bibliometric analysis, and (2) study goals, AI techniques, and experimental protocols are evaluated using systematic content review. A well-planned search was done in the Web of Science for the years between 2020 and 2024. The review followed PRISMA 2020 guidelines. Sixty-four articles met the criteria and were analyzed both quantitatively and qualitatively. The highest publication count was observed in 2022, with a stabilization trend noted in 2023 and 2024. Most of the studies focused on age estimation, with gender classification and identification coming a close second. CNNs were the dominant model architecture. While the field is maturing, there are still key challenges, such as the heterogeneity of datasets, the lack of external validation, and the limited attention given to forensic admissibility. The addressing of these issues will be vital for the translation of AI innovations into robust forensic 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

Advancing forensic dentistry: a comprehensive review of machine learning and deep learning applications in dental image analysis

  • 期刊论文

  • 发表日期：

    2025年9月12日

查看全文
  • Abdullah Ammar Karcioglu,
  • Rabia Meryem Yilmaz,
  • Mete Yaganoglu,
  • Mahmoud Almohammad,
  • Abubekir Laloglu

摘要

The field of forensic dentistry has witnessed a marked rise in the utilization of artificial intelligence (AI), particularly in the domains of age estimation, gender classification, and human identification through dental image analysis. Although there are more publications in this field now than there used to be, there has not been a full review of how good the methods are and how things have changed over time. The aim of this systematic review is to assess the state of the literature on AI-based forensic dental image analysis using two complementary methods: (1) Publication dynamics and keyword trends are examined using bibliometric analysis, and (2) study goals, AI techniques, and experimental protocols are evaluated using systematic content review. A well-planned search was done in the Web of Science for the years between 2020 and 2024. The review followed PRISMA 2020 guidelines. Sixty-four articles met the criteria and were analyzed both quantitatively and qualitatively. The highest publication count was observed in 2022, with a stabilization trend noted in 2023 and 2024. Most of the studies focused on age estimation, with gender classification and identification coming a close second. CNNs were the dominant model architecture. While the field is maturing, there are still key challenges, such as the heterogeneity of datasets, the lack of external validation, and the limited attention given to forensic admissibility. The addressing of these issues will be vital for the translation of AI innovations into robust forensic tools.