Gd-EOB-DTPA-enhanced MRI radiomics and deep learning models to predict microvascular invasion in hepatocellular carcinoma: a multicenter study

Abstract Background Microvascular invasion (MVI) is an important risk factor for early postoperative recurrence of hepatocellular carcinoma (HCC). Based on gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) images, we developed a novel...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhu Zhu, Kaiying Wu, Jian Lu, Sunxian Dai, Dabo Xu, Wei Fang, Yixing Yu, Wenhao Gu
Format: Article
Language:English
Published: BMC 2025-03-01
Series:BMC Medical Imaging
Subjects:
Online Access:https://doi.org/10.1186/s12880-025-01646-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849769676787154944
author Zhu Zhu
Kaiying Wu
Jian Lu
Sunxian Dai
Dabo Xu
Wei Fang
Yixing Yu
Wenhao Gu
author_facet Zhu Zhu
Kaiying Wu
Jian Lu
Sunxian Dai
Dabo Xu
Wei Fang
Yixing Yu
Wenhao Gu
author_sort Zhu Zhu
collection DOAJ
description Abstract Background Microvascular invasion (MVI) is an important risk factor for early postoperative recurrence of hepatocellular carcinoma (HCC). Based on gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) images, we developed a novel radiomics model. It combined bi-regional features and two machine learning algorithms. The aim of this study was to validate its potential value for preoperative prediction of MVI. Methods This retrospective study included 304 HCC patients (training cohort, 216 patients; testing cohort, 88 patients) from three hospitals. Intratumoral and peritumoral volumes of interest were delineated in arterial phase, portal venous phase, and hepatobiliary phase images. Conventional radiomics (CR) and deep learning radiomics (DLR) features were extracted based on FeAture Explorer software and the 3D ResNet-18 extractor, respectively. Clinical variables were selected using univariate and multivariate analyses. Clinical, CR, DLR, CR-DLR, and clinical-radiomics (Clin-R) models were built using support vector machines. The predictive capacity of the models was assessed by the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Results The bi-regional CR-DLR model showed more gains and gave better predictive performance than the single-regional models or single-machine learning models. Its AUC, accuracy, sensitivity, and specificity were 0.844, 76.9%, 87.8%, and 69.1% in the training cohort and 0.740, 73.9%, 50%, and 84.5% in the testing cohort. Alpha-fetoprotein (odds ratio was 0.32) and maximum tumor diameter (odds ratio was 1.270) were independent predictors. The AUCs of the clinical model and the Clin-R model were 0.655 and 0.672, respectively. There was no significant difference in the AUCs between all the models (P > 0.005). Conclusion Based on Gd-EOB-DTPA-enhanced MRI images, we focused on developing a radiomics model that combines bi-regional features and two machine learning algorithms (CR and DLR). The application of the new model will provide a more accurate and non-invasive diagnostic solution for medical imaging. It will provide valuable information for clinical personalized treatment, thereby improving patient prognosis. Clinical trial number Not applicable.
format Article
id doaj-art-d353b6ba850e456db7b5de25f4fda059
institution DOAJ
issn 1471-2342
language English
publishDate 2025-03-01
publisher BMC
record_format Article
series BMC Medical Imaging
spelling doaj-art-d353b6ba850e456db7b5de25f4fda0592025-08-20T03:03:20ZengBMCBMC Medical Imaging1471-23422025-03-0125111310.1186/s12880-025-01646-9Gd-EOB-DTPA-enhanced MRI radiomics and deep learning models to predict microvascular invasion in hepatocellular carcinoma: a multicenter studyZhu Zhu0Kaiying Wu1Jian Lu2Sunxian Dai3Dabo Xu4Wei Fang5Yixing Yu6Wenhao Gu7Department of Radiology, The First People’s Hospital of Taicang, Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First People’s Hospital of Taicang, Affiliated Hospital of Soochow UniversityDepartment of Radiology, The Third Affiliated Hospital of Nantong University, The Third People’s Hospital of NantongSoochow universityDepartment of Radiology, The First People’s Hospital of Taicang, Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First People’s Hospital of Taicang, Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First Affiliated Hospital of Soochow UniversityDepartment of Radiology, The First People’s Hospital of Taicang, Affiliated Hospital of Soochow UniversityAbstract Background Microvascular invasion (MVI) is an important risk factor for early postoperative recurrence of hepatocellular carcinoma (HCC). Based on gadolinium-ethoxybenzyl-diethylenetriamine pentaacetic acid (Gd-EOB-DTPA)-enhanced magnetic resonance imaging (MRI) images, we developed a novel radiomics model. It combined bi-regional features and two machine learning algorithms. The aim of this study was to validate its potential value for preoperative prediction of MVI. Methods This retrospective study included 304 HCC patients (training cohort, 216 patients; testing cohort, 88 patients) from three hospitals. Intratumoral and peritumoral volumes of interest were delineated in arterial phase, portal venous phase, and hepatobiliary phase images. Conventional radiomics (CR) and deep learning radiomics (DLR) features were extracted based on FeAture Explorer software and the 3D ResNet-18 extractor, respectively. Clinical variables were selected using univariate and multivariate analyses. Clinical, CR, DLR, CR-DLR, and clinical-radiomics (Clin-R) models were built using support vector machines. The predictive capacity of the models was assessed by the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. Results The bi-regional CR-DLR model showed more gains and gave better predictive performance than the single-regional models or single-machine learning models. Its AUC, accuracy, sensitivity, and specificity were 0.844, 76.9%, 87.8%, and 69.1% in the training cohort and 0.740, 73.9%, 50%, and 84.5% in the testing cohort. Alpha-fetoprotein (odds ratio was 0.32) and maximum tumor diameter (odds ratio was 1.270) were independent predictors. The AUCs of the clinical model and the Clin-R model were 0.655 and 0.672, respectively. There was no significant difference in the AUCs between all the models (P > 0.005). Conclusion Based on Gd-EOB-DTPA-enhanced MRI images, we focused on developing a radiomics model that combines bi-regional features and two machine learning algorithms (CR and DLR). The application of the new model will provide a more accurate and non-invasive diagnostic solution for medical imaging. It will provide valuable information for clinical personalized treatment, thereby improving patient prognosis. Clinical trial number Not applicable.https://doi.org/10.1186/s12880-025-01646-9Hepatocellular carcinomaMicrovascular invasionConventional radiomicsDeep learning radiomicsMagnetic resonance imagingGd-EOB-DTPA
spellingShingle Zhu Zhu
Kaiying Wu
Jian Lu
Sunxian Dai
Dabo Xu
Wei Fang
Yixing Yu
Wenhao Gu
Gd-EOB-DTPA-enhanced MRI radiomics and deep learning models to predict microvascular invasion in hepatocellular carcinoma: a multicenter study
BMC Medical Imaging
Hepatocellular carcinoma
Microvascular invasion
Conventional radiomics
Deep learning radiomics
Magnetic resonance imaging
Gd-EOB-DTPA
title Gd-EOB-DTPA-enhanced MRI radiomics and deep learning models to predict microvascular invasion in hepatocellular carcinoma: a multicenter study
title_full Gd-EOB-DTPA-enhanced MRI radiomics and deep learning models to predict microvascular invasion in hepatocellular carcinoma: a multicenter study
title_fullStr Gd-EOB-DTPA-enhanced MRI radiomics and deep learning models to predict microvascular invasion in hepatocellular carcinoma: a multicenter study
title_full_unstemmed Gd-EOB-DTPA-enhanced MRI radiomics and deep learning models to predict microvascular invasion in hepatocellular carcinoma: a multicenter study
title_short Gd-EOB-DTPA-enhanced MRI radiomics and deep learning models to predict microvascular invasion in hepatocellular carcinoma: a multicenter study
title_sort gd eob dtpa enhanced mri radiomics and deep learning models to predict microvascular invasion in hepatocellular carcinoma a multicenter study
topic Hepatocellular carcinoma
Microvascular invasion
Conventional radiomics
Deep learning radiomics
Magnetic resonance imaging
Gd-EOB-DTPA
url https://doi.org/10.1186/s12880-025-01646-9
work_keys_str_mv AT zhuzhu gdeobdtpaenhancedmriradiomicsanddeeplearningmodelstopredictmicrovascularinvasioninhepatocellularcarcinomaamulticenterstudy
AT kaiyingwu gdeobdtpaenhancedmriradiomicsanddeeplearningmodelstopredictmicrovascularinvasioninhepatocellularcarcinomaamulticenterstudy
AT jianlu gdeobdtpaenhancedmriradiomicsanddeeplearningmodelstopredictmicrovascularinvasioninhepatocellularcarcinomaamulticenterstudy
AT sunxiandai gdeobdtpaenhancedmriradiomicsanddeeplearningmodelstopredictmicrovascularinvasioninhepatocellularcarcinomaamulticenterstudy
AT daboxu gdeobdtpaenhancedmriradiomicsanddeeplearningmodelstopredictmicrovascularinvasioninhepatocellularcarcinomaamulticenterstudy
AT weifang gdeobdtpaenhancedmriradiomicsanddeeplearningmodelstopredictmicrovascularinvasioninhepatocellularcarcinomaamulticenterstudy
AT yixingyu gdeobdtpaenhancedmriradiomicsanddeeplearningmodelstopredictmicrovascularinvasioninhepatocellularcarcinomaamulticenterstudy
AT wenhaogu gdeobdtpaenhancedmriradiomicsanddeeplearningmodelstopredictmicrovascularinvasioninhepatocellularcarcinomaamulticenterstudy