Skip to content
DraconiticResearch
Search Sources API
201,683 studies31 sourcesUpdated 38 min ago
Peer-reviewedCC BY-NCJournal of hepatocellular carcinoma

Multimodal AI in Hepatocellular Carcinoma: Bridging Diagnosis, Therapy and Prognosis Toward Precision Oncology.

  • Xinyi Chen1
  • Fazhao Li1
  • Yan Xu2,3,4
  • Ziao Hu5
  • Baoye Sun1
  • Dongni Pei1
5 affiliations
  1. 1Department of General Surgery, the Second Xiangya Hospital, Central South University, Changsha, Hunan, 410011, People's Republic of China.
  2. 2Department of Ultrasonography, The Second Xiangya Hospital, Central South University, Changsha, Hunan, 410011, People's Republic of China.
  3. 3Research Center of Ultrasonography, The Second Xiangya Hospital, Central South University, Changsha, Hunan, 410011, People's Republic of China.
  4. 4Clinical Research Center for Ultrasound Diagnosis and Treatment in Hunan Province, Changsha, Hunan, 410011, People's Republic of China.
  5. 5Department of Ophthalmology, The Second Xiangya Hospital of Central South University, Changsha, Hunan, 410011, People's Republic of China.
Read full textPDFDOICite

Abstract

Background

This narrative review summarizes recent advances in multimodal AI for hepatocellular carcinoma (HCC), a highly heterogeneous malignancy. Traditional singlemodal data (eg imaging, serology, pathology) are insufficient for accurate diagnosis and personalized treatment. Multimodal technology, which integrates four categories of data (imaging, pathology, molecular, and clinical) through artificial intelligence (AI), has emerged as a promising solution. This review aims to summarize the sources, characteristics, and standardization of multimodal data in HCC, and to comprehensively update its clinical applications in diagnosis, treatment decision-making, and prognosis prediction.Methods

We searched the literature in PubMed, Web of Science, Cochrane Library, and China National Knowledge Infrastructure (CNKI) for articles on multimodal AI applications in HCC published up to 2025. We also critically appraised the included studies based on study design (retrospective vs prospective), validation strategies (internal vs external), sample size, multicenter status, and risk of bias (eg data leakage, overfitting, class imbalance).Results

Multimodal models have shown promising performance across key clinical tasks, including the diagnosis of early-stage and atypical HCC, preoperative prediction of microvascular invasion (MVI), and assessment of treatment response. In prognostic evaluation, multimodal integration has also demonstrated potential in predicting early recurrence and overall survival. However, challenges remain, including multicenter data heterogeneity, limited model interpretability, and a lack of prospective validation. Notably, no prospective studies or randomized controlled trials have yet been conducted to validate the clinical benefit of multimodal AI in HCC, highlighting a critical gap between current research and clinical implementation.Conclusion

Multimodal AI shows substantial promise in improving HCC management, including earlier detection, more accurate risk stratification, and individualized treatment planning. However, most current evidence remains retrospective, and prospective validation is needed before routine clinical adoption. Going forward, we should focus on deeper integration across different data types, building standardized datasets, advancing digital twin technology, and facilitating translation of these tools into clinical care to ultimately improve patient outcomes.

Related

  1. A glycolysis-associated four-gene risk model for prognosis and immune microenvironment characterization in hepatocellular carcinoma
    Shaohua Xu, Huiyao Xiang, Ming Xiang +3
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textGeneral medicineCrossref
  2. Molecular biomarkers for diagnosis, prognosis, precision therapy, and immunotherapy in cholangiocarcinoma, cHCC-CCA, and HCC
    Jingguo Sun, Yingjie Lu, Lu Chang +4
    Hepatology communicationsPeer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMC
  3. Primary pulmonary NUT carcinoma: pathological features, clinical diagnosis, treatment, and prognosis — An extended review
    Shan Wu, Miao Zhang, Hui Wang
    Oncology reviewsPeer-reviewedCC BYFull textGeneral medicineEurope PMC
  4. Precision surgical oncology for hepatocellular carcinoma
    Takehiro Okabayashi, Motoyasu Tabuchi, Teppei Tokumaru +2
    Frontiers in oncologyPeer-reviewedCC BYFull textOncologyEurope PMC
  5. The Rationale for Tissue Biopsy in the Era of Precision Hepatocellular Carcinoma Management
    Ioanna-Maria Grypari, Dina G. Tiniakos, Maria Kalafateli +1
    CancersPeer-reviewedCC BYFull textOncologyEurope PMC

Cite

BibTeXRIS
BibTeX
@article{chen2026multimodal,
  title = {{Multimodal AI in Hepatocellular Carcinoma: Bridging Diagnosis, Therapy and Prognosis Toward Precision Oncology.}},
  author = {Xinyi Chen and Fazhao Li and Yan Xu and Ziao Hu and Baoye Sun and Dongni Pei},
  journal = {Journal of hepatocellular carcinoma},
  year = {2026},
  month = oct,
  doi = {10.2147/jhc.s636212},
  url = {https://europepmc.org/article/MED/42936163},
  note = {CC BY-NC},
}
RIS
TY  - JOUR
TI  - Multimodal AI in Hepatocellular Carcinoma: Bridging Diagnosis, Therapy and Prognosis Toward Precision Oncology.
AU  - Xinyi Chen
AU  - Fazhao Li
AU  - Yan Xu
AU  - Ziao Hu
AU  - Baoye Sun
AU  - Dongni Pei
PY  - 2026
DA  - 2026/10/22
JO  - Journal of hepatocellular carcinoma
DO  - 10.2147/jhc.s636212
UR  - https://europepmc.org/article/MED/42936163
AB  - Background  This narrative review summarizes recent advances in multimodal AI for hepatocellular carcinoma (HCC), a highly heterogeneous malignancy. Traditional singlemodal data (eg imaging, serology, pathology) are insufficient for accurate diagnosis and personalized treatment. Multimodal technology, which integrates four categories of data (imaging, pathology, molecular, and clinical) through artificial intelligence (AI), has emerged as a promising solution. This review aims to summarize the sources, characteristics, and standardization of multimodal data in HCC, and to comprehensively update its clinical applications in diagnosis, treatment decision-making, and prognosis prediction.Methods  We searched the literature in PubMed, Web of Science, Cochrane Library, and China National Knowledge Infrastructure (CNKI) for articles on multimodal AI applications in HCC published up to 2025. We also critically appraised the included studies based on study design (retrospective vs prospective), validation strategies (internal vs external), sample size, multicenter status, and risk of bias (eg data leakage, overfitting, class imbalance).Results  Multimodal models have shown promising performance across key clinical tasks, including the diagnosis of early-stage and atypical HCC, preoperative prediction of microvascular invasion (MVI), and assessment of treatment response. In prognostic evaluation, multimodal integration has also demonstrated potential in predicting early recurrence and overall survival. However, challenges remain, including multicenter data heterogeneity, limited model interpretability, and a lack of prospective validation. Notably, no prospective studies or randomized controlled trials have yet been conducted to validate the clinical benefit of multimodal AI in HCC, highlighting a critical gap between current research and clinical implementation.Conclusion  Multimodal AI shows substantial promise in improving HCC management, including earlier detection, more accurate risk stratification, and individualized treatment planning. However, most current evidence remains retrospective, and prospective validation is needed before routine clinical adoption. Going forward, we should focus on deeper integration across different data types, building standardized datasets, advancing digital twin technology, and facilitating translation of these tools into clinical care to ultimately improve patient outcomes.
SN  - 2253-5969
ER  -