Scholarlink

<p>Surgical resection is the primary curative treatment for intrahepatic cholangiocarcinoma (ICC), yet high postoperative recurrence rates pose a significant challenge. We developed an interpretable, transformer-based deep-learning pipeline that integrates multimodal data—including clinical variables, radiomic features, and whole-slide pathology images—by fusing a pre-trained encoder with a transformer network. To biologically validate our model, we leveraged spatial transcriptomics and proteomics to decipher the attention mechanisms underlying its predictions. It demonstrated robust performance in predicting 2-year overall survival, with area under the curve (AUC) values of 0.952 (95% CI: 0.909–0.983), 0.924 (95% CI: 0.804–1.000), and 0.924 (95% CI: 0.828–0.993) in three independent validation cohorts. Interrogation via spatial multi-omics revealed that the model’s attention was preferentially focused on regions histologically and molecularly associated with tumor invasion and aggressive behavior. We present a novel, interpretable multimodal deep-learning framework that achieves superior postoperative risk stratification for ICC patients.</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

Interpretable multimodal deep learning improves postoperative risk stratification in intrahepatic cholangiocarcinoma in multicentre cohorts

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年12月29日

查看全文
  • Mingyu Wan,
  • Yongfeng Ding,
  • Yanli Wang,
  • Yunlu Jia,
  • Siqi Wu,
  • Wenxin Qu,
  • Yifan Xu,
  • Wenguang Fu,
  • Michael P. Timko,
  • Ledong Wan,
  • Le Ying,
  • Chanqi Ye,
  • Ruyin Chen,
  • Qiong Li,
  • Yuqing He,
  • Keyi Xu,
  • Nong Xu,
  • Jinzhang Chen,
  • Dayong Zheng,
  • Yifei Shen,
  • Jian Ruan

摘要

Surgical resection is the primary curative treatment for intrahepatic cholangiocarcinoma (ICC), yet high postoperative recurrence rates pose a significant challenge. We developed an interpretable, transformer-based deep-learning pipeline that integrates multimodal data—including clinical variables, radiomic features, and whole-slide pathology images—by fusing a pre-trained encoder with a transformer network. To biologically validate our model, we leveraged spatial transcriptomics and proteomics to decipher the attention mechanisms underlying its predictions. It demonstrated robust performance in predicting 2-year overall survival, with area under the curve (AUC) values of 0.952 (95% CI: 0.909–0.983), 0.924 (95% CI: 0.804–1.000), and 0.924 (95% CI: 0.828–0.993) in three independent validation cohorts. Interrogation via spatial multi-omics revealed that the model’s attention was preferentially focused on regions histologically and molecularly associated with tumor invasion and aggressive behavior. We present a novel, interpretable multimodal deep-learning framework that achieves superior postoperative risk stratification for ICC patients.