Graph attention network enables multipurpose prediction of imaging mass cytometry in a hepatocellular carcinoma clinical trial

Hang Shi; Wei Shao; Jinyuan Song; Gang Che; Yaxing Zhao; Yangyang Shi; Junlei Zhang; Peng Wan; Qi Zhu; Daoqiang Zhang; Jianpeng Sheng

doi:10.1016/j.intonc.2025.10.001

您当前的位置：

首页 >

文章列表页 >

Graph attention network enables multipurpose prediction of imaging mass cytometry in a hepatocellular carcinoma clinical trial

Research Article | 更新时间：2026-06-03

- Graph attention network enables multipurpose prediction of imaging mass cytometry in a hepatocellular carcinoma clinical trial
- Graph attention network enables multipurpose prediction of imaging mass cytometry in a hepatocellular carcinoma clinical trial
- 智能肿瘤学 2025年第4期页码：326-340
- 作者机构：
  
  1. College of Artificial Intelligence, Nanjing University of Aeronautics and Astronautics,Jiangsu,Nanjing,China,211106
  2. Department of Hepatobiliary and Pancreatic Surgery, The First Affiliated Hospital, Zhejiang University School of Medicine,Zhejiang,Hangzhou,China,310002
  3. Zhejiang Provincial Key Laboratory of Pancreatic Disease, The First Affiliated Hospital, Zhejiang University School of Medicine,Zhejiang,Hangzhou,China,310002
  4. Zhejiang University Cancer Center, Zhejiang University,Zhejiang,Hangzhou,China,310002
  5. Infinity Scope Inc,Zhejiang,Hangzhou,China,310002
- 作者简介：
- 基金信息：
- DOI：10.1016/j.intonc.2025.10.001
  中图分类号：
- 收稿：2025-06-26，
  
  网络首发：2025-10-14，
  
  纸质出版：2025-11-03
- 稿件说明：
移动端阅览
Hang Shi, Wei Shao, Jinyuan Song, 等. Graph attention network enables multipurpose prediction of imaging mass cytometry in a hepatocellular carcinoma clinical trial[J]. 智能肿瘤学, 2025,(4):326-340.

Hang Shi, Wei Shao, Jinyuan Song, et al. Graph attention network enables multipurpose prediction of imaging mass cytometry in a hepatocellular carcinoma clinical trial[J]. Intelligent Oncology, 2025, (4): 326-340.
Hang Shi, Wei Shao, Jinyuan Song, 等. Graph attention network enables multipurpose prediction of imaging mass cytometry in a hepatocellular carcinoma clinical trial[J]. 智能肿瘤学, 2025,(4):326-340. DOI： 10.1016/j.intonc.2025.10.001.

Hang Shi, Wei Shao, Jinyuan Song, et al. Graph attention network enables multipurpose prediction of imaging mass cytometry in a hepatocellular carcinoma clinical trial[J]. Intelligent Oncology, 2025, (4): 326-340. DOI： 10.1016/j.intonc.2025.10.001.

摘要

Imaging mass cytometry (IMC) enables the high-resolution spatial profiling of tumor microenvironment

but its clinical utility for prospective prediction remains underdeveloped. In this study

we integrated IMC into a clinical trial of hepatocellular carcinoma (HCC) patients undergoing combination therapy with programmed death-1 blockade and transarterial chemoembolization. We analyzed 281 regions of interest from 43 patients using a custom 40-marker IMC panel and developed a novel superpixel-based graph attention network

IMCSGAT

to model spatial cell interactions within the tumor microenvironment. IMCSGAT enabled accurate multitask prediction of key clinical features

including Barcelona Clinic Liver Cancer stage

trabecular histologic subtype

and treatment response. Compared to state-of-the-art methods

IMCSGAT achieved superior performance across all classification tasks. Spatial interaction analysis revealed that resident macrophage–centered interactions

particularly those with NK and T cells

were enriched in responders and predictive of therapeutic outcome. These findings were validated in a murine HCC model

reinforcing the role of innate immune architecture in shaping the treatment response. This study establishes IMCSGAT as a powerful spatial learning framework for high-dimensional IMC data

with potential applications in clinical outcome prediction and personalized therapy design for HCC. Our results provide a blueprint for the broader use of spatial analytics in precision oncology.

Abstract

Imaging mass cytometry (IMC) enables the high-resolution spatial profiling of tumor microenvironment

but its clinical utility for prospective prediction remains underdeveloped. In this study

IMCSGAT

to model spatial cell interactions within the tumor microenvironment. IMCSGAT enabled accurate multitask prediction of key clinical features

including Barcelona Clinic Liver Cancer stage

trabecular histologic subtype

and treatment response. Compared to state-of-the-art methods

IMCSGAT achieved superior performance across all classification tasks. Spatial interaction analysis revealed that resident macrophage–centered interactions

particularly those with NK and T cells

were enriched in responders and predictive of therapeutic outcome. These findings were validated in a murine HCC model

reinforcing the role of innate immune architecture in shaping the treatment response. This study establishes IMCSGAT as a powerful spatial learning framework for high-dimensional IMC data

with potential applications in clinical outcome prediction and personalized therapy design for HCC. Our results provide a blueprint for the broader use of spatial analytics in precision oncology.

关键词

Keywords

references

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

TSMIL: Transformer-based structured low-rank end-to-end multi-instance learning network for renal cell carcinoma classification in whole-slide images

Capturing hallmarks of cancer through the lens of artificial intelligence

From morphology to function: Advances in multimodal imaging for pulmonary function prediction

Deep learning-based segmentation of small-volume brain metastases in lung cancer patients

AI-based diagnosis of clear-cell renal cell carcinoma based on non-contrast CT