A multimodal fusion system predicting survival benefits of immune checkpoint inhibitors in unresectable hepatocellular carcinoma

Abstract Early identification of unresectable hepatocellular carcinoma (HCC) patients who may benefit from immune checkpoint inhibitors (ICIs) is crucial for optimizing outcomes. Here, we developed a multimodal fusion (MMF) system integrating CT-derived deep learning features and clinical data to pr...

Full description

Saved in:
Bibliographic Details
Main Authors: Jun Xu, Tengfei Wang, Junjun Li, Yong Wang, Zhangxiang Zhu, Xiao Fu, Junjie Wang, Zhenglin Zhang, Wei Cai, Ruipeng Song, Changlong Hou, Li-Zhuang Yang, Hongzhi Wang, Stephen T. C. Wong, Hai Li
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:npj Precision Oncology
Online Access:https://doi.org/10.1038/s41698-025-00979-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850222309642600448
author Jun Xu
Tengfei Wang
Junjun Li
Yong Wang
Zhangxiang Zhu
Xiao Fu
Junjie Wang
Zhenglin Zhang
Wei Cai
Ruipeng Song
Changlong Hou
Li-Zhuang Yang
Hongzhi Wang
Stephen T. C. Wong
Hai Li
author_facet Jun Xu
Tengfei Wang
Junjun Li
Yong Wang
Zhangxiang Zhu
Xiao Fu
Junjie Wang
Zhenglin Zhang
Wei Cai
Ruipeng Song
Changlong Hou
Li-Zhuang Yang
Hongzhi Wang
Stephen T. C. Wong
Hai Li
author_sort Jun Xu
collection DOAJ
description Abstract Early identification of unresectable hepatocellular carcinoma (HCC) patients who may benefit from immune checkpoint inhibitors (ICIs) is crucial for optimizing outcomes. Here, we developed a multimodal fusion (MMF) system integrating CT-derived deep learning features and clinical data to predict overall survival (OS) and progression-free survival (PFS). Using retrospective multicenter data (n = 859), the MMF combining an ensemble deep learning (Ensemble-DL) model with clinical variables achieved strong external validation performance (C-index: OS = 0.74, PFS = 0.69), outperforming radiomics (29.8% OS improvement), mRECIST (27.6% OS improvement), clinical benchmarks (C-index: OS = 0.67, p = 0.0011; PFS = 0.65, p = 0.033), and Ensemble-DL (C-index: OS = 0.69, p = 0.0028; PFS = 0.66, p = 0.044). The MMF system effectively stratified patients across clinical subgroups and demonstrated interpretability through activation maps and radiomic correlations. Differential gene expression analysis revealed enrichment of the PI3K/Akt pathway in patients identified by the MMF system. The MMF system provides an interpretable, clinically applicable approach to guide personalized ICI treatment in unresectable HCC.
format Article
id doaj-art-3ebd9e43fddb41eab60b110fcf252ee3
institution OA Journals
issn 2397-768X
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series npj Precision Oncology
spelling doaj-art-3ebd9e43fddb41eab60b110fcf252ee32025-08-20T02:06:23ZengNature Portfolionpj Precision Oncology2397-768X2025-06-019111610.1038/s41698-025-00979-6A multimodal fusion system predicting survival benefits of immune checkpoint inhibitors in unresectable hepatocellular carcinomaJun Xu0Tengfei Wang1Junjun Li2Yong Wang3Zhangxiang Zhu4Xiao Fu5Junjie Wang6Zhenglin Zhang7Wei Cai8Ruipeng Song9Changlong Hou10Li-Zhuang Yang11Hongzhi Wang12Stephen T. C. Wong13Hai Li14Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of SciencesHefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of SciencesDepartment of Radiology, The First Affiliated Hospital of University of Science and Technology of ChinaDepartment of Radiology, The First Affiliated Hospital of Wannan Medical College (Yijishan Hospital of Wannan Medical College)Department of Radiology, The First Affiliated Hospital of Anhui Medical UniversityHefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of SciencesHefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of SciencesHefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of SciencesDepartment of Hepatobiliary Surgery, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, the University of Science and Technology of China, Anhui Province Key Laboratory of Hepatopancreatobiliary Surgery, Anhui Provincial Clinical Research Center for Hepatobiliary DiseasesDepartment of Hepatobiliary Surgery, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, the University of Science and Technology of China, Anhui Province Key Laboratory of Hepatopancreatobiliary Surgery, Anhui Provincial Clinical Research Center for Hepatobiliary DiseasesDepartment of Interventional Radiology, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of ChinaHefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of SciencesHefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of SciencesDepartment of Systems Medicine and Bioengineering, Houston Methodist Neal Cancer Center, Houston Methodist HospitalHefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of SciencesAbstract Early identification of unresectable hepatocellular carcinoma (HCC) patients who may benefit from immune checkpoint inhibitors (ICIs) is crucial for optimizing outcomes. Here, we developed a multimodal fusion (MMF) system integrating CT-derived deep learning features and clinical data to predict overall survival (OS) and progression-free survival (PFS). Using retrospective multicenter data (n = 859), the MMF combining an ensemble deep learning (Ensemble-DL) model with clinical variables achieved strong external validation performance (C-index: OS = 0.74, PFS = 0.69), outperforming radiomics (29.8% OS improvement), mRECIST (27.6% OS improvement), clinical benchmarks (C-index: OS = 0.67, p = 0.0011; PFS = 0.65, p = 0.033), and Ensemble-DL (C-index: OS = 0.69, p = 0.0028; PFS = 0.66, p = 0.044). The MMF system effectively stratified patients across clinical subgroups and demonstrated interpretability through activation maps and radiomic correlations. Differential gene expression analysis revealed enrichment of the PI3K/Akt pathway in patients identified by the MMF system. The MMF system provides an interpretable, clinically applicable approach to guide personalized ICI treatment in unresectable HCC.https://doi.org/10.1038/s41698-025-00979-6
spellingShingle Jun Xu
Tengfei Wang
Junjun Li
Yong Wang
Zhangxiang Zhu
Xiao Fu
Junjie Wang
Zhenglin Zhang
Wei Cai
Ruipeng Song
Changlong Hou
Li-Zhuang Yang
Hongzhi Wang
Stephen T. C. Wong
Hai Li
A multimodal fusion system predicting survival benefits of immune checkpoint inhibitors in unresectable hepatocellular carcinoma
npj Precision Oncology
title A multimodal fusion system predicting survival benefits of immune checkpoint inhibitors in unresectable hepatocellular carcinoma
title_full A multimodal fusion system predicting survival benefits of immune checkpoint inhibitors in unresectable hepatocellular carcinoma
title_fullStr A multimodal fusion system predicting survival benefits of immune checkpoint inhibitors in unresectable hepatocellular carcinoma
title_full_unstemmed A multimodal fusion system predicting survival benefits of immune checkpoint inhibitors in unresectable hepatocellular carcinoma
title_short A multimodal fusion system predicting survival benefits of immune checkpoint inhibitors in unresectable hepatocellular carcinoma
title_sort multimodal fusion system predicting survival benefits of immune checkpoint inhibitors in unresectable hepatocellular carcinoma
url https://doi.org/10.1038/s41698-025-00979-6
work_keys_str_mv AT junxu amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT tengfeiwang amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT junjunli amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT yongwang amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT zhangxiangzhu amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT xiaofu amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT junjiewang amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT zhenglinzhang amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT weicai amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT ruipengsong amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT changlonghou amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT lizhuangyang amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT hongzhiwang amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT stephentcwong amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT haili amultimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT junxu multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT tengfeiwang multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT junjunli multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT yongwang multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT zhangxiangzhu multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT xiaofu multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT junjiewang multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT zhenglinzhang multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT weicai multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT ruipengsong multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT changlonghou multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT lizhuangyang multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT hongzhiwang multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT stephentcwong multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma
AT haili multimodalfusionsystempredictingsurvivalbenefitsofimmunecheckpointinhibitorsinunresectablehepatocellularcarcinoma