Scholarlink

<p>Type 2 diabetes (T2D) is a chronic disease currently affecting around 500 million people worldwide with often severe health consequences. Yet, histopathological analyses are still inadequate to infer the glycaemic state of a person based on morphological alterations linked to impaired insulin secretion and <i>β</i>-cell failure in T2D. Giga-pixel microscopy can capture subtle morphological changes, but data complexity exceeds human analysis capabilities. In response, we generate a dataset of pancreas whole-slide images from living donors with multiple chromogenic and multiplex immunofluorescence stainings and train deep learning models to predict the T2D status. Using explainable AI, we make the learned relationships interpretable, quantify them as biomarkers, and assess their association with T2D. Remarkably, the highest prediction performance is achieved by simultaneously focusing on islet <i>α</i>- and <i>δ</i>-cells and neuronal axons, alongside subtle pancreatic alterations in T2D donors such as larger adipocyte clusters, altered islet-adipocyte proximity and smaller islets. This data-driven approach provides a foundation for future research into relevant diagnostic and therapeutic targets, refining several hypotheses regarding tissue alterations associated with T2D.</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

Explainable AI-based analysis of human pancreas sections identifies traits of type 2 diabetes

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月9日

查看全文
  • Lukas Klein,
  • Sebastian Ziegler,
  • Felicia Gerst,
  • Yanni Morgenroth,
  • Karol Gotkowski,
  • Eyke Schöniger,
  • Martin Heni,
  • Nicole Kipke,
  • Daniela Friedland,
  • Annika Seiler,
  • Ellen Geibelt,
  • Hajime Yamazaki,
  • Hans-Ulrich Häring,
  • Silvia Wagner,
  • Silvio Nadalin,
  • Alfred Königsrainer,
  • Andre L. Mihaljevic,
  • Daniel Hartmann,
  • Falko Fend,
  • Daniela Aust,
  • Jürgen Weitz,
  • Reiner Jumpertz-von Schwartzenberg,
  • Marius Distler,
  • Klaus Maier-Hein,
  • Andreas L. Birkenfeld,
  • Susanne Ullrich,
  • Paul F. Jäger,
  • Fabian Isensee,
  • Michele Solimena,
  • Robert Wagner

摘要

Type 2 diabetes (T2D) is a chronic disease currently affecting around 500 million people worldwide with often severe health consequences. Yet, histopathological analyses are still inadequate to infer the glycaemic state of a person based on morphological alterations linked to impaired insulin secretion and β-cell failure in T2D. Giga-pixel microscopy can capture subtle morphological changes, but data complexity exceeds human analysis capabilities. In response, we generate a dataset of pancreas whole-slide images from living donors with multiple chromogenic and multiplex immunofluorescence stainings and train deep learning models to predict the T2D status. Using explainable AI, we make the learned relationships interpretable, quantify them as biomarkers, and assess their association with T2D. Remarkably, the highest prediction performance is achieved by simultaneously focusing on islet α- and δ-cells and neuronal axons, alongside subtle pancreatic alterations in T2D donors such as larger adipocyte clusters, altered islet-adipocyte proximity and smaller islets. This data-driven approach provides a foundation for future research into relevant diagnostic and therapeutic targets, refining several hypotheses regarding tissue alterations associated with T2D.