Scholarlink

<p>Neuroblastoma is a leading cause of childhood cancer mortality, presenting persistent management challenges due to its biological heterogeneity and the limited accessibility of molecular profiling in routine practice. Here we present NEVA (<b>NE</b>uroblastoma Vision–language <b>A</b>I), a multimodal foundation model designed to address these barriers. Unlike conventional approaches that rely on frozen encoders and multiple instance learning, NEVA implements a pathologist-inspired hierarchical workflow with end-to-end optimization. Developed and evaluated in a large multi-institutional cohort of 1,238 patients across multiple centers, NEVA outperforms ten representative foundation models, including TITAN, UNI, and Virchow, across the majority of the 11 clinical tasks evaluated. The model demonstrates diagnostic capability, achieving Area Under the Receiver Operating Characteristic curves of 0.916 for subtype classification, 0.823 for Shimada classification, and 0.806 for risk group stratification. Furthermore, NEVA predicts key molecular alterations from routinely available pathology data, reaching an AUROC of 0.924 for <i>NMYC</i> amplification and 0.830 for 1p36 deletion, while enabling prognostic stratification for progression-free and overall survival across multiple test cohorts. By integrating interpretable attention maps that localize histologically relevant regions, NEVA establishes a scalable framework for neuroblastoma risk stratification and clinical decision support.</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

A unified vision-language model for precision oncology and biomarker prediction in neuroblastoma

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年7月9日

查看全文
  • Jin Zhu,
  • Ruizhen Hu,
  • Sen Yang,
  • Qing Sun,
  • Zhenzhen Zhao,
  • Juan Cao,
  • Peiying Pan,
  • Kun Wang,
  • Liyan Cui,
  • Hongping Tang,
  • Qianqian Fang,
  • Sijin Jiang,
  • Linli Lei,
  • Wenjian Zhang,
  • Jiajun Xie,
  • Shuo Kang,
  • Dongyuan Xiao,
  • Ming Xiao,
  • Xuan Zhai,
  • Yuntao Jia,
  • Junyang Chen,
  • Wei Yuan,
  • Xiao Han,
  • Le Lu,
  • Junhan Zhao,
  • Xiyue Wang,
  • Yi Li,
  • Jinxi Xiang,
  • Biyue Zhu

摘要

Neuroblastoma is a leading cause of childhood cancer mortality, presenting persistent management challenges due to its biological heterogeneity and the limited accessibility of molecular profiling in routine practice. Here we present NEVA (NEuroblastoma Vision–language AI), a multimodal foundation model designed to address these barriers. Unlike conventional approaches that rely on frozen encoders and multiple instance learning, NEVA implements a pathologist-inspired hierarchical workflow with end-to-end optimization. Developed and evaluated in a large multi-institutional cohort of 1,238 patients across multiple centers, NEVA outperforms ten representative foundation models, including TITAN, UNI, and Virchow, across the majority of the 11 clinical tasks evaluated. The model demonstrates diagnostic capability, achieving Area Under the Receiver Operating Characteristic curves of 0.916 for subtype classification, 0.823 for Shimada classification, and 0.806 for risk group stratification. Furthermore, NEVA predicts key molecular alterations from routinely available pathology data, reaching an AUROC of 0.924 for NMYC amplification and 0.830 for 1p36 deletion, while enabling prognostic stratification for progression-free and overall survival across multiple test cohorts. By integrating interpretable attention maps that localize histologically relevant regions, NEVA establishes a scalable framework for neuroblastoma risk stratification and clinical decision support.