Vision transformer-based model can optimize curative-intent treatment for patients with recurrent hepatocellular carcinoma

Ke Zhang, Jinyu Ru, Wenbo Wang, Qiuping Ma, Fengwei Gao, Jiapeng Wu, Zhifei Dai, Qingyun Xie, Lei Mu, Haoyan Zhang, Jinhua Pan, Liting Xie, Qiyu Zhao, Jie Tian, Jie Yu (), Ping Liang (), Hong Wu (), Kai Li (), Wei Yang (), Kun Wang () and Tianan Jiang ()
Additional contact information
Ke Zhang: Zhejiang University School of Medicine
Jinyu Ru: Chinese Academy of Sciences
Wenbo Wang: Peking University Cancer Hospital & Institute
Qiuping Ma: The Third Affiliated Hospital of Sun Yat-sen University
Fengwei Gao: Sichuan University and Collaborative Innovation Center of Biotherapy
Jiapeng Wu: Nankai University
Zhifei Dai: Peking University
Qingyun Xie: Sichuan University and Collaborative Innovation Center of Biotherapy
Lei Mu: Zhejiang University School of Medicine
Haoyan Zhang: Chinese Academy of Sciences
Jinhua Pan: Zhejiang University School of Medicine
Liting Xie: Zhejiang University School of Medicine
Qiyu Zhao: Zhejiang University School of Medicine
Jie Tian: Chinese Academy of Sciences
Jie Yu: Fifth Medical Center of Chinese PLA General Hospital
Ping Liang: Fifth Medical Center of Chinese PLA General Hospital
Hong Wu: Sichuan University and Collaborative Innovation Center of Biotherapy
Kai Li: The Third Affiliated Hospital of Sun Yat-sen University
Wei Yang: Peking University Cancer Hospital & Institute
Kun Wang: Chinese Academy of Sciences
Tianan Jiang: Zhejiang University School of Medicine

Nature Communications, 2025, vol. 16, issue 1, 1-14

Abstract: Abstract The treatment selection for recurrent hepatocellular carcinoma (rHCC) within Milan criteria after hepatectomy remains challenging. Here, we present HEROVision, a Vision Transformer-based model designed for personalized prognosis prediction and treatment optimization between thermal ablation (TA) and surgical resection (SR). HEROVision is trained on initial HCC cohorts (8492 images; 772 patients) and independently tested on rHCC cohorts (9163 images; 833 patients) from five centers. Propensity score matching (PSM) forms two groups of rHCC patients underwent TA and SR to fairly evaluate whether optimized treatment selection by HEROVision have clinical benefits. HEROVision significantly outperforms all six guideline staging systems in the external testing cohort, both in time-dependent concordance index and area under the curve (all P

Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-025-59197-0 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:16:y:2025:i:1:d:10.1038_s41467-025-59197-0

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-025-59197-0

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().