Construction of a visual imaging decision model for prognosis of hepatocellular carcinoma interventional therapy based on MRI features
10.3969/j.issn.1002-1671.2025.11.030
- VernacularTitle:基于MRI征象的肝细胞肝癌介入治疗预后可视化影像决策模型构建
- Author:
Jinpeng FU
1
;
Nan ZHANG
1
;
Bo PENG
1
;
Gang ZHENG
1
Author Information
1. 大庆油田总医院放射介入科,黑龙江 大庆 163000
- Publication Type:Journal Article
- Keywords:
hepatocellular carcinoma;
interventional therapy;
prognosis;
magnetic resonance imaging;
visualization model
- From:
Journal of Practical Radiology
2025;41(11):1895-1898
- CountryChina
- Language:Chinese
-
Abstract:
Objective To construct a visual imaging decision model for evaluating the prognosis of hepatocellular carcinoma(HCC)patients treated with interventional therapy based on MRI features.Methods A total of 130 HCC patients were selected.All of them underwent MRI examination upon admission,and then the interventional therapy was implemented after clinical evaluation.The patients were followed up for 2 years after the last interventional therapy,and then were divided into poor prognosis group(50 cases)and good prognosis group(80 cases)according to the follow-up results.The risk factors affecting the poor prognosis of HCC patients treated with interventional therapy were screened.A nomogram model was constructed based on the risk factors,and its prediction efficiency was then evaluated.Results The incomplete capsule,unsmooth tumor margin,portal vein tumor thrombus,cirrhosis,apparent diffusion coefficient(ADC)value,red blood cell distribution width within 24 h after admission,and aspartate aminotransferase were significantly different between the poor prognosis group and the good prognosis group(P＜0.05),and these indicators were the risk factors affecting the poor prognosis of HCC patients treated with interventional therapy(P＜0.05).Based on the above risk factors,a nomogram model of poor prognosis risk for the HCC patients treated with interventional therapy was constructed,and the sensitivity,specificity,and area under the curve(AUC)for predicting poor prognosis of HCC patients treated with interventional therapy were 90.00％,81.80％and 0.899[95％confidence interval(CI)0.827-0.972],respectively.Conclusion The risk nomogram model of poor prognosis of HCC patients treated with interventional therapy based on incomplete capsule,unsmooth tumor margin,portal vein tumor thrombus,cirrhosis,ADC value,red blood cell distribution width,and aspartate aminotransferase has good predictive efficacy.
