Scholarlink

<p>Lung adenocarcinoma (LUAD) exhibits pronounced morphological heterogeneity, making accurate subtyping and grading a persistent challenge in pathology. Conventional deep learning methods often lack the granularity and interpretability required for clinical translation. We introduce <i>FigATree</i>, an interpretable AI framework for LUAD diagnosis that combines a foundation model-enhanced region-level encoder with an XGBoost-based pathology-informed slide-level classifier. Applied to 1186&#xa0;H&amp;E-stained whole-slide images, FigATree achieves <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(&gt;\!95\%\)</EquationSource> <EquationSource Format="MATHML"><math> <mrow> <mo>&gt;</mo> <mspace width="-0.166667em" /> <mn>95</mn> <mo>%</mo> </mrow> </math></EquationSource> </InlineEquation> accuracy in classifying six histological patterns at the region level and &#xa0;90% and &#xa0;85% accuracy in slide-level subtyping and differentiation grading, respectively, substantially outperforming guidelines-based baselines. Additionally, FigATree achieved region-level and slide-level accuracies of nearly 100% and 80%, respectively, on external validation, fully demonstrating its generalizability. The framework yields interpretable predictions aligned with pathological criteria, offering transparency at both region and slide levels. By integrating foundation model representations with a clinically grounded decision module, FigATree enables accurate, explainable classification of LUAD and represents a scalable paradigm for computational histopathology.</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

FigATree: a novel framework for histological subtyping and grading of lung adenocarcinoma

  • 期刊论文

  • 发表日期：

    2025年11月27日

查看全文
  • Qiang Huang,
  • Jiajun Zhang,
  • Qiming He,
  • Shu Wang,
  • Qilai Zhang,
  • Lan Lin,
  • Xunbin Yu,
  • Yu Wang,
  • Yonghong He,
  • Xin Chen,
  • Tian Guan,
  • Houqiang Li

摘要

Lung adenocarcinoma (LUAD) exhibits pronounced morphological heterogeneity, making accurate subtyping and grading a persistent challenge in pathology. Conventional deep learning methods often lack the granularity and interpretability required for clinical translation. We introduce FigATree, an interpretable AI framework for LUAD diagnosis that combines a foundation model-enhanced region-level encoder with an XGBoost-based pathology-informed slide-level classifier. Applied to 1186 H&E-stained whole-slide images, FigATree achieves \(>\!95\%\) > 95 % accuracy in classifying six histological patterns at the region level and  90% and  85% accuracy in slide-level subtyping and differentiation grading, respectively, substantially outperforming guidelines-based baselines. Additionally, FigATree achieved region-level and slide-level accuracies of nearly 100% and 80%, respectively, on external validation, fully demonstrating its generalizability. The framework yields interpretable predictions aligned with pathological criteria, offering transparency at both region and slide levels. By integrating foundation model representations with a clinically grounded decision module, FigATree enables accurate, explainable classification of LUAD and represents a scalable paradigm for computational histopathology.