Scholarlink

<p>Recently developed pathology foundation models, pretrained on large-scale pathology datasets, have demonstrated excellent performance in various downstream tasks. This study evaluated the utility of pathology foundation models combined with multiple instance learning (MIL) for kidney pathology analysis. We used 242 hematoxylin and eosin-stained whole slide images (WSIs) from the Kidney Precision Medicine Project (KPMP) and Japan-Pathology Artificial Intelligence Diagnostics Project databases as the development cohort, comprising 47 healthy controls, 35 acute interstitial nephritis, and 160 diabetic kidney disease (DKD) slides. External validation was performed using 83 WSIs from the University of Tokyo Hospital. Pretrained pathology foundation models were utilized as patch encoders and compared with ImageNet-pretrained ResNet50. Using the extracted patch features, we trained MIL models to classify diagnoses. In internal validation, all foundation models outperformed ResNet50, achieving area under the receiver operating characteristic curve (AUROC) over 0.980. In external validation, the performance of ResNet50 markedly dropped, which was in contrast to all foundation models. Visualization of attention heatmaps confirmed that foundation models accurately recognized diagnostically relevant structures. In overt proteinuria (albuminuria ≥ 300&#xa0;mg/gCre or proteinuria ≥ 1000&#xa0;mg/gCre) prediction task, foundation models also outperformed ResNet50. We successfully integrated pathology foundation models with MIL to achieve robust diagnostic performance.</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

Multiple instance learning using pathology foundation models effectively predicts kidney disease diagnosis and clinical classification

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年10月9日

查看全文
  • Yu Kurata,
  • Imari Mimura,
  • Satoshi Kodera,
  • Hiroyuki Abe,
  • Daisuke Yamada,
  • Haruki Kume,
  • Tetsuo Ushiku,
  • Tetsuhiro Tanaka,
  • Norihiko Takeda,
  • Masaomi Nangaku

摘要

Recently developed pathology foundation models, pretrained on large-scale pathology datasets, have demonstrated excellent performance in various downstream tasks. This study evaluated the utility of pathology foundation models combined with multiple instance learning (MIL) for kidney pathology analysis. We used 242 hematoxylin and eosin-stained whole slide images (WSIs) from the Kidney Precision Medicine Project (KPMP) and Japan-Pathology Artificial Intelligence Diagnostics Project databases as the development cohort, comprising 47 healthy controls, 35 acute interstitial nephritis, and 160 diabetic kidney disease (DKD) slides. External validation was performed using 83 WSIs from the University of Tokyo Hospital. Pretrained pathology foundation models were utilized as patch encoders and compared with ImageNet-pretrained ResNet50. Using the extracted patch features, we trained MIL models to classify diagnoses. In internal validation, all foundation models outperformed ResNet50, achieving area under the receiver operating characteristic curve (AUROC) over 0.980. In external validation, the performance of ResNet50 markedly dropped, which was in contrast to all foundation models. Visualization of attention heatmaps confirmed that foundation models accurately recognized diagnostically relevant structures. In overt proteinuria (albuminuria ≥ 300 mg/gCre or proteinuria ≥ 1000 mg/gCre) prediction task, foundation models also outperformed ResNet50. We successfully integrated pathology foundation models with MIL to achieve robust diagnostic performance.