MRI radiomics combined with clinical indices and LI-RADS features for predicting tumor response after transarterial chemoembolization in patients with intermediate and advanced hepatocellular carcinoma

Zhang Pengwei; Wei Min; Yang Chaofeng; Li Yang

doi:null

您当前的位置：

首页 >

文章列表页 >

MRI radiomics combined with clinical indices and LI-RADS features for predicting tumor response after transarterial chemoembolization in patients with intermediate and advanced hepatocellular carcinoma

更新时间：2025-09-29

- MRI radiomics combined with clinical indices and LI-RADS features for predicting tumor response after transarterial chemoembolization in patients with intermediate and advanced hepatocellular carcinoma
- Journal of Chongqing Medical University Pages: 1-12(2025)
- 作者机构：
  
  川北医学院附属医院放射科，南充 637000
- 作者简介：
- 基金信息：
- DOI：
  CLC： R445.3
- Received：27 March 2025，
  
  Published Online：29 September 2025，
- 稿件说明：
移动端阅览
张朋伟,魏敏,杨朝凤等.MRI影像组学联合临床指标及LI-RADS特征预测中晚期肝细胞癌TACE术后的肿瘤反应[J].重庆医科大学学报,

Zhang Pengwei,Wei Min,Yang Chaofeng,et al.MRI radiomics combined with clinical indices and LI-RADS features for predicting tumor response after transarterial chemoembolization in patients with intermediate and advanced hepatocellular carcinoma[J].Journal of Chongqing Medical University,
张朋伟,魏敏,杨朝凤等.MRI影像组学联合临床指标及LI-RADS特征预测中晚期肝细胞癌TACE术后的肿瘤反应[J].重庆医科大学学报, DOI：10.13406/j.cnki.cyxb..

Zhang Pengwei,Wei Min,Yang Chaofeng,et al.MRI radiomics combined with clinical indices and LI-RADS features for predicting tumor response after transarterial chemoembolization in patients with intermediate and advanced hepatocellular carcinoma[J].Journal of Chongqing Medical University, DOI：10.13406/j.cnki.cyxb..

摘要

目的

探讨术前磁共振成像（magnetic resonance imaging，MRI）影像组学特征联合临床指标及肝脏影像报告和数据系统（liver imaging reporting and data system，LI-RADS）特征预测中晚期肝细胞癌（hepatocellular carcinoma，HCC）患者经动脉化疗栓塞术（transarterial chemoembolization，TACE）术后肿瘤反应的价值。

方法

回顾性收集2020年1月至2024年7月于川北医学院附属医院接受TACE治疗的169例中晚期HCC患者的临床和影像学资料，按7∶3比例分为训练集（118例）和验证集（51例）。在术前MRI的轴位抑脂T2加权成像（fat suppression T2 weighted，FS-T

WI）、动脉期和门静脉期图像上勾画肿瘤感兴趣区（region of interest，ROI）并提取影像组学特征。通过一致性分析和Spearman相关性检验剔除不稳定和冗余的影像组学特征，随后使用最小绝对收缩和选择算子（least absolute shrinkage and selection operator，LASSO）回归对特征进一步降维，并计算每位患者的影像组学评分（Rad-score）。采用单因素和多因素logistic回归筛选出与肿瘤反应明显相关的临床指标及LI-RADS特征。然后，分别构建影像组学模型、临床模型和联合模型。通过受试者工作特征曲线下面积（area under the curve，AUC）、校准曲线、临床决策曲线分析（decision curve analysis，DCA）评价各模型预测性能和临床实用性。最后利用列线图对模型进行可视化展示。

结果

本研究共纳入169例患者，其中有肿瘤反应患者106例，无肿瘤反应患者63例。最终共筛选出10个影像组学特征，并基于这些特征计算Rad-score。血小板与淋巴细胞比率（platelet-to-lymphocyte ratio，PLR）、肿瘤最大径和晕状强化是与肿瘤反应明显相关的独立预测因素。在训练集和验证集中，影像组学模型AUC分别为0.810、0.742，临床模型AUC分别为0.771、0.680，联合模型AUC分别为0.846、0.811，联合模型性能最优。校准曲线和DCA证实联合模型具有良好的校准度和临床实用性，采用列线图对联合模型进行可视化。

结论

术前MRI影像组学联合临床指标及LI-RADS特征能有效预测中晚期HCC患者TACE术后的肿瘤反应。

Abstract

Objective

To investigate the value of preoperative MRI radiomic features combined with clinical indices and LI-RADS features in predicting tumor response after transarterial chemoembolization（TACE） in patients with intermediate and advanced hepatocellular carcinoma（HCC）.

Methods

A retrospective analysis was performed for the clinical and imaging data of 169 patients with intermediate and advanced HCC who underwent TACE in Affiliated Hospital of North Sichuan Medical College from January 2020 to July 2024，and the patients were divided into a training set （118 patients） and a validation set（51 patients） at a ratio of 7∶3. Regions of interest （ROIs） of the tumor were delineated on preoperative MRI images，including FS-T

WI，arterial phase，and portal venous phase images，and radiomic features were extracted. Consistency analysis and Spearman correlation analysis were used to exclude unstable and redundant radiomic features，then a least absolute shrinkage and selection operator（LASSO） regression analysis was used for further dimension reduction，and a radiomics score（Rad-score） was calculated for each patient. Univariate and multivariate logistic regression analyses were used to identify the clinical indices and LI-RADS features that were significantly associated with tumor response，and a radiomics model，a clinical model，and a combined model were constructed. The area under the receiver operating characteristic curve（AUC），the calibration curve，and the decision curve analysis（DCA） were used to assess the predictive performance and clinical practicability of each model. Finally，a nomogram was developed for visualization.

Results

A total of 169 patients were included in this study，among whom there were 106 patients with tumor response and 63 with no tumor response. A total of 10 radiomic features were selected，and the Rad-score was calculated based on these features. Platelet-to-lymphocyte ratio（PLR），maximum tumor diameter，and halo enhancement were identified as independent predictive factors that were significantly associated with tumor response. In the training and validation sets，the radiomics model had an AUC of 0.810 and 0.742，respectively，the clinical model had an AUC of 0.771 and 0.680，respectively，and the combined model had an AUC of 0.846 and 0.811，respectively，suggesting that the combined model had the best performance. The calibration curve and DCA showed that the combined model had good calibration and clinical practicability. A nomogram was employed to visualize the combined model.

Conclusion

Preoperative MRI radiomics combined with clinical indices and LI-RADS features can effectively predict tumor response after TACE in patients with intermediate and advanced HCC.

关键词

Keywords

references

Bray F ， Laversanne M ， Sung H ， et al . Global cancer statistics 2022：GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries [J ] . CA Cancer J Clin ， 2024 ， 74 （ 3 ）： 229 - 263 .

Rumgay H ， Arnold M ， Ferlay J ， et al . Global burden of primary liver cancer in 2020 and predictions to 2040 [J ] . J Hepatol ， 2022 ， 77 （ 6 ）： 1598 - 1606 ．

Benson AB ， D’Angelica MI ， Abbott DE ， et al . Hepatobiliary cancers，version 2.2021，NCCN clinical practice guidelines in oncology [J ] . J Natl Compr Canc Netw ， 2021 ， 19 （ 5 ）： 541 - 565 ．

Abdelrahim M ， Esmail A ， Hibi T ， et al . Focal update on immunotherapy and liver transplantation in the era of transplant oncology [J ] . Curr Oncol ， 2024 ， 31 （ 9 ）： 5021 - 5026 ．

Reig M ， Forner A ， Rimola J ， et al . BCLC strategy for prognosis prediction and treatment recommendation：The 2022 update [J ] . J Hepatol ， 2022 ， 76 （ 3 ）： 681 - 693 ．

中华人民共和国国家卫生健康委员会医政司 . 原发性肝癌诊疗指南（2024年版） [J ] . 协和医学杂志， 2024 ， 15 （ 3 ）： 532 - 559 .

Ministry of Health of the People's Republic of China，Department of Medical Administration . Primary Liver Cancer Diagnosis and Treatment Guidelines （2024 Edition） [J ] . Peking Union Medical College Journal ， 2024 ， 15 （ 03 ）： 532 - 559 .

Piscaglia F ， Ogasawara S . Patient selection for transarterial chemoembolization in hepatocellular carcinoma：importance of benefit/risk assessment [J ] . Liver Cancer ， 2018 ， 7 （ 1 ）： 104 - 119 ．

Kotsifa E ， Vergadis C ， Vailas M ， et al . Transarterial chemoembolization for hepatocellular carcinoma：why，when，how? [J ] . J Pers Med ， 2022 ， 12 （ 3 ）： 436 ．

Jung Y ， Choi MJ ， Kim BM ， et al . Transarterial embolization for sporadic renal angiomyolipoma：patient selection and technical considerations for optimal therapeutic outcomes [J ] . Taehan Yongsang Uihakhoe Chi ， 2022 ， 83 （ 3 ）： 559 - 581 ．

Rhee H ， Park YN ， Choi JY . Advances in understanding hepatocellular carcinoma vasculature：implications for diagnosis，prognostication，and treatment [J ] . Korean J Radiol ， 2024 ， 25 （ 10 ）： 887 - 901 ．

Kudo M ， Han KH ， Ye SL ， et al . A changing paradigm for the treatment of intermediate-stage hepatocellular carcinoma：Asia-Pacific primary liver cancer expert consensus statements [J ] . Liver Cancer ， 2020 ， 9 （ 3 ）： 245 - 260 ．

Feng Z ， Zhao H ， Guan S ， et al . Diagnostic performance of MRI using extracellular contrast agents versus gadoxetic acid for hepatocellular carcinoma：a systematic review and meta-analysis [J ] . Liver Int ， 2021 ， 41 （ 5 ）： 1117 - 1128 ．

Lambin P ， Leijenaar RTH ， Deist TM ， et al . Radiomics：the bridge between medical imaging and personalized medicine [J ] . Nat Rev Clin Oncol ， 2017 ， 14 （ 12 ）： 749 - 762 ．

Gao WY ， Wang WT ， Song DJ ， et al . A predictive model integrating deep and radiomics features based on gadobenate dimeglumine-enhanced MRI for postoperative early recurrence of hepatocellular carcinoma [J ] . La Radiol Med ， 2022 ， 127 （ 3 ）： 259 - 271 ．

Gerena M ， Molvar C ， Masciocchi M ， et al . LI-RADS treatment response assessment of combination locoregional therapy for HCC [J ] . Abdom Radiol ， 2021 ， 46 （ 8 ）： 3634 - 3647 ．

Saito N ， Nishiofuku H ， Sato T ， et al . Predictive factors of complete response to transarterial chemoembolization in intermediate stage hepatocellular carcinoma beyond up-to-7 criteria [J ] . Cancers （Basel）， 2023 ， 15 （ 9 ）： 2609 ．

Ogasawara S ， Chiba T ， Ooka Y ， et al . A prognostic score for patients with intermediate-stage hepatocellular carcinoma treated with transarterial chemoembolization [J ] . PLoS One ， 2015 ， 10 （ 4 ）： e0125244 ．

Sheng Y ， Wang Q ， Liu HF ， et al . Preoperative nomogram incorporating clinical factors，serological markers and LI-RADS MRI features to predict early recurrence of hepatocellular carcinoma treated with transarterial chemoembolization [J ] . Acad Radiol ， 2023 ， 30 （ 7 ）： 1288 - 1297 ．

Zhang K ， Zhang L ， Li WC ， et al . Radiomics nomogram for the prediction of microvascular invasion of HCC and patients' benefit from postoperative adjuvant TACE：a multi-center study [J ] . Eur Radiol ， 2023 ， 33 （ 12 ）： 8936 - 8947 ．

Li J ， Zhou M ， Tong Y ， et al . Tumor growth pattern and intra- and peritumoral radiomics combined for prediction of initial TACE outcome in patients with primary hepatocellular carcinoma [J ] . J Hepatocell Carcinoma ， 2024 ， 11 ： 1927 - 1944 ．

Lencioni R ， Llovet JM . Modified RECIST （mRECIST） assessment for hepatocellular carcinoma [J ] . Semin Liver Dis ， 2010 ， 30 （ 1 ）： 52 - 60 ．

Riley RD ， Snell KI ， Ensor J ， et al . Minimum sample size for developing a multivariable prediction model：PART II - binary and time-to-event outcomes [J ] . Stat Med ， 2019 ， 38 （ 7 ）： 1276 - 1296 ．

Davnall F ， Yip CSP ， Ljungqvist G ， et al . Assessment of tumor heterogeneity：an emerging imaging tool for clinical practice? [J ] . Insights Imag ， 2012 ， 3 （ 6 ）： 573 - 589 ．

Zhou M ， Zhang P ， Mao Q ， et al . Multisequence MRI-based radiomic features combined with inflammatory indices for predicting the overall survival of HCC patients after TACE [J ] . J Hepatocell Carcinoma ， 2024 ， 11 ： 2049 - 2061 ．

Gillies RJ ， Kinahan PE ， Hricak H . Radiomics：images are more than pictures，they are data [J ] . Radiology ， 2016 ， 278 （ 2 ）： 563 - 577 ．

Bonin S ， Stanta G . Pre-analytics and tumor heterogeneity [J ] . New Biotechnol ， 2020 ， 55 ： 30 - 35 ．

Vitale I ， Shema E ， Loi S ， et al . Intratumoral heterogeneity in cancer progression and response to immunotherapy [J ] . Nat Med ， 2021 ， 27 （ 2 ）： 212 - 224 ．

Bharath K ， Kurtek S ， Rao A ， et al . Radiologic image-based statistical shape analysis of brain TumoursFree [J ] . J. R. Stat. Soc. Ser. C. Appl. Stat．， 2018 ， 67 （ 5 ）： 1357 - 1378 ．

Cannella R ， Cammà C ， Matteini F ， et al . Radiomics analysis on gadoxetate disodium-enhanced MRI predicts response to transarterial embolization in patients with HCC [J ] . Diagnostics （Basel）， 2022 ， 12 （ 6 ）： 1308 ．

Liu A ， Liu B ， Duan X ， et al . Development of a novel combined nomogram model integrating Rad-score，age and ECOG to predict the survival of patients with hepatocellular carcinoma treated by transcatheter arterial chemoembolization [J ] . J Gastrointest Oncol ， 2022 ， 13 （ 4 ）： 1889 - 1897 ．

Templeton AJ ， Ace O ， McNamara MG ， et al . Prognostic role of platelet to lymphocyte ratio in solid tumors：a systematic review and meta-analysis [J ] . Cancer Epidemiol Biomarkers Prev ， 2014 ， 23 （ 7 ）： 1204 - 1212 ．

Schobert IT ， Savic LJ ， Chapiro J ， et al . Neutrophil-to-lymphocyte and platelet-to-lymphocyte ratios as predictors of tumor response in hepatocellular carcinoma after DEB-TACE [J ] . Eur Radiol ， 2020 ， 30 （ 10 ）： 5663 - 5673 ．

Truffi M ， Sottotetti F ， Gafni N ， et al . Prognostic potential of immune inflammatory biomarkers in breast cancer patients treated with neoadjuvant chemotherapy [J ] . Cancers （Basel）， 2022 ， 14 （ 21 ）： 5287 ．

Guo Y ， Wu W ， Sun B ， et al . Prognostic value of platelet-to-lymphocyte ratio in patients with unresectable hepatocellular carcinoma undergoing transarterial chemoembolization and tyrosine kinase inhibitors plus immune checkpoints inhibitors [J ] . Front Oncol ， 2024 ， 14 ： 1293680 ．

Goubran HA ， Burnouf T ， Radosevic M ， et al . The platelet-cancer loop [J ] . Eur J Intern Med ， 2013 ， 24 （ 5 ）： 393 - 400 ．

Guo PT ， Li YM ， Zhu Z ， et al . Prognostic value of tumor size in gastric cancer：an analysis of 2，379 patients [J ] . Tumor Biol ， 2013 ， 34 （ 2 ）： 1027 - 1035 ．

Xiao J ， Shen K ， Fan H ， et al . Prognostic value of tumor size in gastric cancer：a retrospective cohort study based on SEER database [J ] . Int J Surg Pathol ， 2023 ， 31 （ 7 ）： 1273 - 1282 ．

Prateepchaiboon T ， Chang A ， Pungpipattrakul N ， et al . Factors affecting prognosis in hepatocellular carcinoma patients post-transarterial chemoembolization [J ] . Indian J Gastroenterol ， 2022 ， 41 （ 4 ）： 352 - 361 ．

Chernyak V ， Fowler KJ ， Kamaya A ， et al . Liver imaging reporting and data system （LI-RADS） version 2018：imaging of hepatocellular carcinoma in at-risk patients [J ] . Radiology ， 2018 ， 289 （ 3 ）： 816 - 830 ．

Wang L ， Ma X ， Feng B ， et al . Multi-sequence MR-based radiomics signature for predicting early recurrence in solitary hepatocellular carcinoma ≤5 cm [J ] . Front Oncol ， 2022 ， 12 ： 899404 ．

Kuang YN ， Li RZ ， Jia P ， et al . MRI-Based Radiomics：Nomograms predicting the short-term response after transcatheter arterial chemoembolization （TACE） in hepatocellular carcinoma patients with diameter less than 5cm [J ] . Abdom Radiol ， 2021 ， 46 （ 8 ）： 3772 - 3789 ．

Liu Y ， Liu Z ， Li X ， et al . Non-invasive assessment of response to transcatheter arterial chemoembolization for hepatocellular carcinoma with the deep neural networks-based radiomics nomogram [J ] . Acta Radiol ， 2024 ， 65 （ 6 ）： 535 - 545 ．

Kong C ， Zhao Z ， Chen W ， et al . Prediction of tumor response via a pretreatment MRI radiomics-based nomogram in HCC treated with TACE [J ] . Eur Radiol ， 2021 ， 31 （ 10 ）： 7500 - 7511 ．

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Predictive value of a nomogram based on enhanced T1WI radiomics and clinico-MRIomics for aggressive histological types of endometrial cancer before surgery

Research advances in yttrium-90 microsphere selective internal radiation therapy in treatment of hepatocellular carcinoma

Advances in the application of ultrasound combined with radiomics and artificial intelligence in the diagnosis and prognostic evaluation of gastrointestinal stromal tumors

Effect of DExH-box helicase 9 O-GlcNAc modification on the proliferation of HBV-associated hepatoma cells

Clinical prediction of benefits from preoperative maximum androgen blocking therapy in high-risk localized prostate cancer

Related Author

Lin Qingxiu

Li Jinbeibei

He Zikun

Ling Rennan

Zhao Yongle

Chen Honglin

Zhang Han

Zhu Xinyue

Related Institution

Department of Radiology，The First Affiliated Hospital of Southern University of Science and Technology

Shenzhen Baoan Clinical Medical College，Guangdong Medical University

Shantou University Medical College

Department of Gastroenterology， The Second Affiliated Hospital of Chongqing Medical University

Department of Ultrasound，The First Affiliated Hospital of Chongqing Medical University

⁰