Multilayer perceptron deep learning radiomics model based on Gd-BOPTA MRI to identify vessels encapsulating tumor clusters in hepatocellular carcinoma: a multi-center study
Abstract Objectives The purpose of this study is to mainly develop a predictive model based on clinicoradiological and radiomics features from preoperative gadobenate-enhanced (Gd-BOPTA) magnetic resonance imaging (MRI) using multilayer perceptron (MLP) deep learning to predict vessels encapsulating...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-07-01
|
| Series: | Cancer Imaging |
| Online Access: | https://doi.org/10.1186/s40644-025-00895-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849332314602995712 |
|---|---|
| author | Mengting Gu Wenjie Zou Huilin Chen Ruilin He Xingyu Zhao Ningyang Jia Wanmin Liu Peijun Wang |
| author_facet | Mengting Gu Wenjie Zou Huilin Chen Ruilin He Xingyu Zhao Ningyang Jia Wanmin Liu Peijun Wang |
| author_sort | Mengting Gu |
| collection | DOAJ |
| description | Abstract Objectives The purpose of this study is to mainly develop a predictive model based on clinicoradiological and radiomics features from preoperative gadobenate-enhanced (Gd-BOPTA) magnetic resonance imaging (MRI) using multilayer perceptron (MLP) deep learning to predict vessels encapsulating tumor clusters (VETC) in hepatocellular carcinoma (HCC) patients. Methods A total of 230 patients with histopathologically confirmed HCC who underwent preoperative Gd-BOPTA MRI before hepatectomy were retrospectively enrolled from three hospitals (144, 54, and 32 in training, test, and validation set, respectively). Univariate and multivariate logistic regression analyses were used to determine independent clinicoradiological predictors significantly associated with VETC, which then constituted the clinicoradiological model. Regions of interest (ROIs) included four modes, intratumoral (Tumor), peritumoral area ≤ 2 mm (Peri2mm), intratumoral + peritumoral area ≤ 2 mm (Tumor + Peri2mm) and intratumoral integrated with peritumoral ≤ 2 mm as a whole (TumorPeri2mm). A total of 7322 radiomics features were extracted respectively for ROI(Tumor), ROI(Peri2mm), ROI(TumorPeri2mm) and 14644 radiomics features for ROI(Tumor + Peri2mm). Least absolute shrinkage and selection operator (LASSO) and univariate logistic regression analysis were used to select the important features. Seven different machine learning classifiers respectively combined the radiomics signatures selected from four ROIs to constitute different models, and compare the performance between them in three sets and then select the optimal combination to become the radiomics model we need. Then a radiomics score (rad-score) was generated, which combined significant clinicoradiological predictors to constituted the fusion model through multivariate logistic regression analysis. After comparing the performance of the three models using area under receiver operating characteristic curve (AUC), integrated discrimination index (IDI) and net reclassification index (NRI), choose the optimal predictive model for VETC prediction. Result Arterial peritumoral enhancement and peritumoral hypointensity on hepatobiliary phase (HBP) were independent risk factors for VETC, and constituted the Radiology model, without any clinical variables. Arterial peritumoral enhancement defined as the enhancement outside the tumor boundary in the late stage of arterial phase or early stage of portal phase, extensive contact with the tumor edge, which becomes isointense during the DP. MLP deep learning algorithm integrated radiomics features selected from ROI TumorPeri2mm was the best combination, which constituted the radiomics model (MLP model). A MLP score (MLP_score) was calculated then, which combining the two radiology features composed the fusion model (Radiology MLP model), with AUCs of 0.871, 0.894, 0.918 in the training, test and validation sets. Compared with the two models aforementioned, the Radiology MLP model demonstrated a 33.4%-131.3% improvement in NRI and a 9.3%-50% improvement in IDI, showing better discrimination, calibration and clinical usefulness in three sets, which was selected as the optimal predictive model. Conclusion We mainly developed a fusion model (Radiology MLP model) that integrated radiology and radiomics features using MLP deep learning algorithm to predict vessels encapsulating tumor clusters (VETC) in hepatocellular carcinoma (HCC) patients, which yield an incremental value over the radiology and the MLP model. |
| format | Article |
| id | doaj-art-83533fbf6fac4f1baab670213c14bd14 |
| institution | Kabale University |
| issn | 1470-7330 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | BMC |
| record_format | Article |
| series | Cancer Imaging |
| spelling | doaj-art-83533fbf6fac4f1baab670213c14bd142025-08-20T03:46:13ZengBMCCancer Imaging1470-73302025-07-0125111410.1186/s40644-025-00895-9Multilayer perceptron deep learning radiomics model based on Gd-BOPTA MRI to identify vessels encapsulating tumor clusters in hepatocellular carcinoma: a multi-center studyMengting Gu0Wenjie Zou1Huilin Chen2Ruilin He3Xingyu Zhao4Ningyang Jia5Wanmin Liu6Peijun Wang7Department of Radiology, Tongji Hospital, School of Medicine, Tongji UniversityDepartment of Radiology, Tongji Hospital, School of Medicine, Tongji UniversitySchool of Health Science and Engineering, University of Shanghai for Science and TechnologySchool of Health Science and Engineering, University of Shanghai for Science and TechnologyDepartment of Radiology, Tongji Hospital, School of Medicine, Tongji UniversityDepartment of Radiology, Eastern Hepatobiliary Surgery Hospital, The Third Affiliated Hospital of Naval Medical UniversityDepartment of Radiology, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Radiology, Tongji Hospital, School of Medicine, Tongji UniversityAbstract Objectives The purpose of this study is to mainly develop a predictive model based on clinicoradiological and radiomics features from preoperative gadobenate-enhanced (Gd-BOPTA) magnetic resonance imaging (MRI) using multilayer perceptron (MLP) deep learning to predict vessels encapsulating tumor clusters (VETC) in hepatocellular carcinoma (HCC) patients. Methods A total of 230 patients with histopathologically confirmed HCC who underwent preoperative Gd-BOPTA MRI before hepatectomy were retrospectively enrolled from three hospitals (144, 54, and 32 in training, test, and validation set, respectively). Univariate and multivariate logistic regression analyses were used to determine independent clinicoradiological predictors significantly associated with VETC, which then constituted the clinicoradiological model. Regions of interest (ROIs) included four modes, intratumoral (Tumor), peritumoral area ≤ 2 mm (Peri2mm), intratumoral + peritumoral area ≤ 2 mm (Tumor + Peri2mm) and intratumoral integrated with peritumoral ≤ 2 mm as a whole (TumorPeri2mm). A total of 7322 radiomics features were extracted respectively for ROI(Tumor), ROI(Peri2mm), ROI(TumorPeri2mm) and 14644 radiomics features for ROI(Tumor + Peri2mm). Least absolute shrinkage and selection operator (LASSO) and univariate logistic regression analysis were used to select the important features. Seven different machine learning classifiers respectively combined the radiomics signatures selected from four ROIs to constitute different models, and compare the performance between them in three sets and then select the optimal combination to become the radiomics model we need. Then a radiomics score (rad-score) was generated, which combined significant clinicoradiological predictors to constituted the fusion model through multivariate logistic regression analysis. After comparing the performance of the three models using area under receiver operating characteristic curve (AUC), integrated discrimination index (IDI) and net reclassification index (NRI), choose the optimal predictive model for VETC prediction. Result Arterial peritumoral enhancement and peritumoral hypointensity on hepatobiliary phase (HBP) were independent risk factors for VETC, and constituted the Radiology model, without any clinical variables. Arterial peritumoral enhancement defined as the enhancement outside the tumor boundary in the late stage of arterial phase or early stage of portal phase, extensive contact with the tumor edge, which becomes isointense during the DP. MLP deep learning algorithm integrated radiomics features selected from ROI TumorPeri2mm was the best combination, which constituted the radiomics model (MLP model). A MLP score (MLP_score) was calculated then, which combining the two radiology features composed the fusion model (Radiology MLP model), with AUCs of 0.871, 0.894, 0.918 in the training, test and validation sets. Compared with the two models aforementioned, the Radiology MLP model demonstrated a 33.4%-131.3% improvement in NRI and a 9.3%-50% improvement in IDI, showing better discrimination, calibration and clinical usefulness in three sets, which was selected as the optimal predictive model. Conclusion We mainly developed a fusion model (Radiology MLP model) that integrated radiology and radiomics features using MLP deep learning algorithm to predict vessels encapsulating tumor clusters (VETC) in hepatocellular carcinoma (HCC) patients, which yield an incremental value over the radiology and the MLP model.https://doi.org/10.1186/s40644-025-00895-9 |
| spellingShingle | Mengting Gu Wenjie Zou Huilin Chen Ruilin He Xingyu Zhao Ningyang Jia Wanmin Liu Peijun Wang Multilayer perceptron deep learning radiomics model based on Gd-BOPTA MRI to identify vessels encapsulating tumor clusters in hepatocellular carcinoma: a multi-center study Cancer Imaging |
| title | Multilayer perceptron deep learning radiomics model based on Gd-BOPTA MRI to identify vessels encapsulating tumor clusters in hepatocellular carcinoma: a multi-center study |
| title_full | Multilayer perceptron deep learning radiomics model based on Gd-BOPTA MRI to identify vessels encapsulating tumor clusters in hepatocellular carcinoma: a multi-center study |
| title_fullStr | Multilayer perceptron deep learning radiomics model based on Gd-BOPTA MRI to identify vessels encapsulating tumor clusters in hepatocellular carcinoma: a multi-center study |
| title_full_unstemmed | Multilayer perceptron deep learning radiomics model based on Gd-BOPTA MRI to identify vessels encapsulating tumor clusters in hepatocellular carcinoma: a multi-center study |
| title_short | Multilayer perceptron deep learning radiomics model based on Gd-BOPTA MRI to identify vessels encapsulating tumor clusters in hepatocellular carcinoma: a multi-center study |
| title_sort | multilayer perceptron deep learning radiomics model based on gd bopta mri to identify vessels encapsulating tumor clusters in hepatocellular carcinoma a multi center study |
| url | https://doi.org/10.1186/s40644-025-00895-9 |
| work_keys_str_mv | AT mengtinggu multilayerperceptrondeeplearningradiomicsmodelbasedongdboptamritoidentifyvesselsencapsulatingtumorclustersinhepatocellularcarcinomaamulticenterstudy AT wenjiezou multilayerperceptrondeeplearningradiomicsmodelbasedongdboptamritoidentifyvesselsencapsulatingtumorclustersinhepatocellularcarcinomaamulticenterstudy AT huilinchen multilayerperceptrondeeplearningradiomicsmodelbasedongdboptamritoidentifyvesselsencapsulatingtumorclustersinhepatocellularcarcinomaamulticenterstudy AT ruilinhe multilayerperceptrondeeplearningradiomicsmodelbasedongdboptamritoidentifyvesselsencapsulatingtumorclustersinhepatocellularcarcinomaamulticenterstudy AT xingyuzhao multilayerperceptrondeeplearningradiomicsmodelbasedongdboptamritoidentifyvesselsencapsulatingtumorclustersinhepatocellularcarcinomaamulticenterstudy AT ningyangjia multilayerperceptrondeeplearningradiomicsmodelbasedongdboptamritoidentifyvesselsencapsulatingtumorclustersinhepatocellularcarcinomaamulticenterstudy AT wanminliu multilayerperceptrondeeplearningradiomicsmodelbasedongdboptamritoidentifyvesselsencapsulatingtumorclustersinhepatocellularcarcinomaamulticenterstudy AT peijunwang multilayerperceptrondeeplearningradiomicsmodelbasedongdboptamritoidentifyvesselsencapsulatingtumorclustersinhepatocellularcarcinomaamulticenterstudy |