Scholarlink

Background <p>Machine learning may significantly support forensic medicine, particularly in age estimation through medical imaging soon. This technology offers great potential for supporting decisions especially when age documentation is missing or disputed.</p> Objective <p>This study investigates the potential of generative models for forensic age estimation. The focus is on addressing the challenges of interpretability and generalizability commonly faced by traditional discriminative models.</p> Methods <p>We applied a&#xa0;family of generative models to postmortem computed tomography (PMCT) scans, focusing on the ossification of the medial clavicular epiphysis for age prediction. The latent space representations from these models were analyzed for their ability to predict age accurately and interpretably across different datasets.</p> Results <p>While the methods did not perform as well as discriminative state of the art approaches using German Working Group for Forensic Age Diagnostics (AGFAD) guidelines, the variational autoencoders were able to learn a&#xa0;meaningful latent space. The age of the participants could even be visualized within a&#xa0;two-dimensional projection. Additionally, the re-use of the learned space led to high performance on a&#xa0;smaller dataset collected from a&#xa0;forensic center.</p> Conclusion <p>The consideration of “soft factors”, such as explainability in addition to absolute performance remains crucial for bringing machine learning methods into forensic practice. Depending on the set-up, generative models might be attractive for assessing the reasoning within models and sharing information between datasets.</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

Latent spaces of generative models for forensic age estimation

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年3月3日

查看全文
  • Anastasia Chernysheva,
  • Christopher Gundler,
  • Alexander Johannes Wiederhold,
  • Eilin Jopp-van Well,
  • Axel Heinemann,
  • Benjamin Ondruschka

摘要

Background

Machine learning may significantly support forensic medicine, particularly in age estimation through medical imaging soon. This technology offers great potential for supporting decisions especially when age documentation is missing or disputed.

Objective

This study investigates the potential of generative models for forensic age estimation. The focus is on addressing the challenges of interpretability and generalizability commonly faced by traditional discriminative models.

Methods

We applied a family of generative models to postmortem computed tomography (PMCT) scans, focusing on the ossification of the medial clavicular epiphysis for age prediction. The latent space representations from these models were analyzed for their ability to predict age accurately and interpretably across different datasets.

Results

While the methods did not perform as well as discriminative state of the art approaches using German Working Group for Forensic Age Diagnostics (AGFAD) guidelines, the variational autoencoders were able to learn a meaningful latent space. The age of the participants could even be visualized within a two-dimensional projection. Additionally, the re-use of the learned space led to high performance on a smaller dataset collected from a forensic center.

Conclusion

The consideration of “soft factors”, such as explainability in addition to absolute performance remains crucial for bringing machine learning methods into forensic practice. Depending on the set-up, generative models might be attractive for assessing the reasoning within models and sharing information between datasets.