Scholarlink

Background <p>Prognostication for pancreatic ductal adenocarcinoma (PDAC) using histologic images is difficult due to tumor heterogeneity. We developed an artificial intelligence (AI) model to predict postoperative recurrence using histologic image patches.</p> Methods <p>We included 591 patients with resected PDAC to train an AI model for recurrence prediction at 12 or 24 months and validated it using external cohorts (<i>n</i> = 302&#xa0;in total). Image patches from hematoxylin and eosin-stained slides were clustered via uniform manifold approximation and projection (UMAP) and used to train a random forest model. Predictive performance was evaluated using area under the receiver operating characteristic curve (AUC). Gene expression analysis was conducted to characterise survival-related clusters.</p> Results <p>Seventeen patch clusters were identified. Two were linked to high recurrence risk, and one to low risk. In external validation, the model achieved an AUC of up to 0.792. The random forest score independently predicted recurrence. Greater heterogeneity in patch composition correlated with shorter time to recurrence (<i>P</i> &lt; 0.01). High-risk clusters showed elevated CSF3R expression; the low-risk cluster showed increased IGFBP3 expression.</p> Conclusions <p>Our AI model, using only archival histologic slides, accurately predicted postoperative recurrence in PDAC and revealed image features linked to outcomes and gene expression.</p> <p></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

Prognostic model for pancreatic cancer based on machine learning of routine slides and transcriptomic tumor analysis

  • 期刊论文

  • 发表日期：

    2026年1月8日

查看全文
  • Manabu Takamatsu,
  • Mariko Tanaka,
  • Yohei Masugi,
  • Yosuke Inoue,
  • Hiroko Nagano,
  • Tho Ngoc-Quynh Le,
  • Kenji Nishida,
  • Yui Sawa,
  • Kota Sugiura,
  • Yoshikuni Kawaguchi,
  • Yusuke Kazami,
  • Yousuke Nakai,
  • Tsuyoshi Hamada,
  • Tatsunori Suzuki,
  • Kensuke Hara,
  • Yutaka Kurebayashi,
  • Tsuyoshi Takeda,
  • Naoki Sasahira,
  • Yosuke Uematsu,
  • Sho Uemura,
  • Mitsuhiro Fujishiro,
  • Kiyoshi Hasegawa,
  • Minoru Kitago,
  • Yu Takahashi,
  • Shigeki Sekine,
  • Tetsuo Ushiku,
  • Kengo Takeuchi

摘要

Background

Prognostication for pancreatic ductal adenocarcinoma (PDAC) using histologic images is difficult due to tumor heterogeneity. We developed an artificial intelligence (AI) model to predict postoperative recurrence using histologic image patches.

Methods

We included 591 patients with resected PDAC to train an AI model for recurrence prediction at 12 or 24 months and validated it using external cohorts (n = 302 in total). Image patches from hematoxylin and eosin-stained slides were clustered via uniform manifold approximation and projection (UMAP) and used to train a random forest model. Predictive performance was evaluated using area under the receiver operating characteristic curve (AUC). Gene expression analysis was conducted to characterise survival-related clusters.

Results

Seventeen patch clusters were identified. Two were linked to high recurrence risk, and one to low risk. In external validation, the model achieved an AUC of up to 0.792. The random forest score independently predicted recurrence. Greater heterogeneity in patch composition correlated with shorter time to recurrence (P < 0.01). High-risk clusters showed elevated CSF3R expression; the low-risk cluster showed increased IGFBP3 expression.

Conclusions

Our AI model, using only archival histologic slides, accurately predicted postoperative recurrence in PDAC and revealed image features linked to outcomes and gene expression.