Predicting tumor micronecrosis in hepatocellular carcinoma using pretreatment contrast-enhanced CT radiomics model: a multi-center study
Tumor micronecrosis is a validated malignancy biomarker with poor prognosis in hepatocellular carcinoma (HCC), but currently lacks reliable preoperative detection methods. We developed a radiomics model for predicting tumor micronecrosis using preoperative contrast-enhanced computed tomography (CECT). The study included 1017 patients with histopathologically confirmed HCC across three centers, allocated to development, internal test, external test, and application sets. Radiomics features were extracted from tumor regions, with model training via a stratified 5-fold cross-validation framework. The model yield area under the curve values of 0.80 and 0.75 in the internal and external test sets, respectively. Survival curves for histologic and radiomics-predicted micronecrosis groups demonstrated close alignment. For patients treated with tyrosine kinase inhibitor and anti-PD-(L)1 immunotherapy, radiomics-predicted micronecrosis(-) and micronecrosis(+) groups showed comparable survival (P = 0.312). Mass cytometry demonstrated significant correlations between micronecrosis-associated radiomics features and peripheral CD24<sup>+</sup> B cells and neutrophils. The radiomics model shows promise for preoperative micronecrosis assessment.
Authors
- Shenghong Ju (ORCID: https://orcid.org/0000-0001-5041-7865)
- Hongkan Wang
- Rujia Zheng
- Jingsong Li (ORCID: https://orcid.org/0000-0002-1064-637X)
- Tianyi Xia (ORCID: https://orcid.org/0000-0001-9341-7742)
- Hongbin Ge
- Wanyue Cao (ORCID: https://orcid.org/0009-0004-2232-5065)
- Chao‐Yuan Huang (ORCID: https://orcid.org/0000-0002-9322-6062)
- Yu Tian (ORCID: https://orcid.org/0009-0005-0614-9572)
- Xu Sun (ORCID: https://orcid.org/0000-0002-6102-6293)
- Q. Zhang (ORCID: https://orcid.org/0009-0005-1196-7756)
- Xue Xing (ORCID: https://orcid.org/0000-0003-4492-7206)
- Enliang Li (ORCID: https://orcid.org/0000-0003-2988-0323)
- Zhihang Cai
- Yuquan Zhang (ORCID: https://orcid.org/0000-0003-3818-8339)
- Mao Ye (ORCID: https://orcid.org/0000-0002-5178-6950)
- Yiting Xu (ORCID: https://orcid.org/0000-0002-9928-2487)
- Yan Zhu (ORCID: https://orcid.org/0000-0002-3765-0643)
- Tingting Lü (ORCID: https://orcid.org/0000-0003-1339-9877)
- Peijun Hu (ORCID: https://orcid.org/0000-0002-5593-1553)
- Ke Sun (ORCID: https://orcid.org/0000-0002-3789-3143)
- Haonan Ding
- Yangyang Wang (ORCID: https://orcid.org/0009-0006-9428-2433)
- Tingbo Liang (ORCID: https://orcid.org/0000-0003-0143-3353)
- Qitai Chen
- Yiwei Gao
- Cao Chen (ORCID: https://orcid.org/0000-0002-2183-9855)
Institutions
- Nanchang University (CN)
- RTI International (US)
- Shanghai Jiao Tong University (CN)
- Zhejiang Cancer Hospital (CN)
- Huzhou Central Hospital (CN)
- Zhongda Hospital Southeast University (CN)
- Second Affiliated Hospital of Nanchang University (CN)
- Zhejiang Lab (CN)
- Shanghai Clinical Research Center (CN)
- Zhejiang Medicine (China) (CN)
- First Affiliated Hospital Zhejiang University (CN)
- Zhejiang University (CN)
- European Automobile Manufacturers Association (BE)
Publication Details
- Journal
- npj Precision Oncology
- Published
- 2025-11-14
- DOI
- https://doi.org/10.1038/s41698-025-01133-y
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- National Science and Technology Major Project
- Zhejiang Traditional Chinese Medicine Administration