Development and External Validation of a Radiomics Model Derived from Preoperative Gadoxetic Acid-Enhanced MRI for Predicting Histopathologic Grade of Hepatocellular Carcinoma
Histopathologic grade of hepatocellular carcinoma (HCC) is an important predictor of early recurrence and poor prognosis after curative treatments. This study aims to develop a radiomics model based on preoperative gadoxetic acid-enhanced MRI for predicting HCC histopathologic grade and to validate...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/13/3/413 |
| _version_ | 1797624868246650880 |
|---|---|
| author | Xiaojun Hu Changfeng Li Qiang Wang Xueyun Wu Zhiyu Chen Feng Xia Ping Cai Leida Zhang Yingfang Fan Kuansheng Ma |
| author_facet | Xiaojun Hu Changfeng Li Qiang Wang Xueyun Wu Zhiyu Chen Feng Xia Ping Cai Leida Zhang Yingfang Fan Kuansheng Ma |
| author_sort | Xiaojun Hu |
| collection | DOAJ |
| description | Histopathologic grade of hepatocellular carcinoma (HCC) is an important predictor of early recurrence and poor prognosis after curative treatments. This study aims to develop a radiomics model based on preoperative gadoxetic acid-enhanced MRI for predicting HCC histopathologic grade and to validate its predictive performance in an independent external cohort. Clinical and imaging data of 403 consecutive HCC patients were retrospectively collected from two hospitals (265 and 138, respectively). Patients were categorized into poorly differentiated HCC and non-poorly differentiated HCC groups. A total of 851 radiomics features were extracted from the segmented tumor at the hepatobiliary phase images. Three classifiers, logistic regression (LR), support vector machine, and Adaboost were adopted for modeling. The areas under the curve of the three models were 0.70, 0.67, and 0.61, respectively, in the external test cohort. Alpha-fetoprotein (AFP) was the only significant clinicopathological variable associated with HCC grading (odds ratio: 2.75). When combining AFP, the LR+AFP model showed the best performance, with an AUC of 0.71 (95%CI: 0.59–0.82) in the external test cohort. A radiomics model based on gadoxetic acid-enhanced MRI was constructed in this study to discriminate HCC with different histopathologic grades. Its good performance indicates a promise in the preoperative prediction of HCC differentiation levels. |
| first_indexed | 2024-03-11T09:48:48Z |
| format | Article |
| id | doaj.art-1e4355f8ce5849b583a42959d46e0c97 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-11T09:48:48Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-1e4355f8ce5849b583a42959d46e0c972023-11-16T16:24:22ZengMDPI AGDiagnostics2075-44182023-01-0113341310.3390/diagnostics13030413Development and External Validation of a Radiomics Model Derived from Preoperative Gadoxetic Acid-Enhanced MRI for Predicting Histopathologic Grade of Hepatocellular CarcinomaXiaojun Hu0Changfeng Li1Qiang Wang2Xueyun Wu3Zhiyu Chen4Feng Xia5Ping Cai6Leida Zhang7Yingfang Fan8Kuansheng Ma9The Department of General Surgery & Hepatobiliary Surgery, Zhujiang Hospital, Southern Medical University, Guangzhou 510280, ChinaInstitution of Hepatobiliary Surgery, Southwest Hospital, Army Medical University, Chongqing 400038, ChinaDivision of Medical Imaging and Technology, Department of Clinical Science, Intervention and Technology (CLINTEC), Karolinska Institutet, 14152 Stockholm, SwedenThe Department of General Surgery & Hepatobiliary Surgery, Zhujiang Hospital, Southern Medical University, Guangzhou 510280, ChinaInstitution of Hepatobiliary Surgery, Southwest Hospital, Army Medical University, Chongqing 400038, ChinaInstitution of Hepatobiliary Surgery, Southwest Hospital, Army Medical University, Chongqing 400038, ChinaDepartment of Radiology, Southwest Hospital, Army Medical University, Chongqing 400038, ChinaInstitution of Hepatobiliary Surgery, Southwest Hospital, Army Medical University, Chongqing 400038, ChinaThe Department of General Surgery & Hepatobiliary Surgery, Zhujiang Hospital, Southern Medical University, Guangzhou 510280, ChinaInstitution of Hepatobiliary Surgery, Southwest Hospital, Army Medical University, Chongqing 400038, ChinaHistopathologic grade of hepatocellular carcinoma (HCC) is an important predictor of early recurrence and poor prognosis after curative treatments. This study aims to develop a radiomics model based on preoperative gadoxetic acid-enhanced MRI for predicting HCC histopathologic grade and to validate its predictive performance in an independent external cohort. Clinical and imaging data of 403 consecutive HCC patients were retrospectively collected from two hospitals (265 and 138, respectively). Patients were categorized into poorly differentiated HCC and non-poorly differentiated HCC groups. A total of 851 radiomics features were extracted from the segmented tumor at the hepatobiliary phase images. Three classifiers, logistic regression (LR), support vector machine, and Adaboost were adopted for modeling. The areas under the curve of the three models were 0.70, 0.67, and 0.61, respectively, in the external test cohort. Alpha-fetoprotein (AFP) was the only significant clinicopathological variable associated with HCC grading (odds ratio: 2.75). When combining AFP, the LR+AFP model showed the best performance, with an AUC of 0.71 (95%CI: 0.59–0.82) in the external test cohort. A radiomics model based on gadoxetic acid-enhanced MRI was constructed in this study to discriminate HCC with different histopathologic grades. Its good performance indicates a promise in the preoperative prediction of HCC differentiation levels.https://www.mdpi.com/2075-4418/13/3/413radiomicsmagnetic resonance imagingpathologic gradegadoxetic acidhepatocellular carcinomamachine learning |
| spellingShingle | Xiaojun Hu Changfeng Li Qiang Wang Xueyun Wu Zhiyu Chen Feng Xia Ping Cai Leida Zhang Yingfang Fan Kuansheng Ma Development and External Validation of a Radiomics Model Derived from Preoperative Gadoxetic Acid-Enhanced MRI for Predicting Histopathologic Grade of Hepatocellular Carcinoma Diagnostics radiomics magnetic resonance imaging pathologic grade gadoxetic acid hepatocellular carcinoma machine learning |
| title | Development and External Validation of a Radiomics Model Derived from Preoperative Gadoxetic Acid-Enhanced MRI for Predicting Histopathologic Grade of Hepatocellular Carcinoma |
| title_full | Development and External Validation of a Radiomics Model Derived from Preoperative Gadoxetic Acid-Enhanced MRI for Predicting Histopathologic Grade of Hepatocellular Carcinoma |
| title_fullStr | Development and External Validation of a Radiomics Model Derived from Preoperative Gadoxetic Acid-Enhanced MRI for Predicting Histopathologic Grade of Hepatocellular Carcinoma |
| title_full_unstemmed | Development and External Validation of a Radiomics Model Derived from Preoperative Gadoxetic Acid-Enhanced MRI for Predicting Histopathologic Grade of Hepatocellular Carcinoma |
| title_short | Development and External Validation of a Radiomics Model Derived from Preoperative Gadoxetic Acid-Enhanced MRI for Predicting Histopathologic Grade of Hepatocellular Carcinoma |
| title_sort | development and external validation of a radiomics model derived from preoperative gadoxetic acid enhanced mri for predicting histopathologic grade of hepatocellular carcinoma |
| topic | radiomics magnetic resonance imaging pathologic grade gadoxetic acid hepatocellular carcinoma machine learning |
| url | https://www.mdpi.com/2075-4418/13/3/413 |
| work_keys_str_mv | AT xiaojunhu developmentandexternalvalidationofaradiomicsmodelderivedfrompreoperativegadoxeticacidenhancedmriforpredictinghistopathologicgradeofhepatocellularcarcinoma AT changfengli developmentandexternalvalidationofaradiomicsmodelderivedfrompreoperativegadoxeticacidenhancedmriforpredictinghistopathologicgradeofhepatocellularcarcinoma AT qiangwang developmentandexternalvalidationofaradiomicsmodelderivedfrompreoperativegadoxeticacidenhancedmriforpredictinghistopathologicgradeofhepatocellularcarcinoma AT xueyunwu developmentandexternalvalidationofaradiomicsmodelderivedfrompreoperativegadoxeticacidenhancedmriforpredictinghistopathologicgradeofhepatocellularcarcinoma AT zhiyuchen developmentandexternalvalidationofaradiomicsmodelderivedfrompreoperativegadoxeticacidenhancedmriforpredictinghistopathologicgradeofhepatocellularcarcinoma AT fengxia developmentandexternalvalidationofaradiomicsmodelderivedfrompreoperativegadoxeticacidenhancedmriforpredictinghistopathologicgradeofhepatocellularcarcinoma AT pingcai developmentandexternalvalidationofaradiomicsmodelderivedfrompreoperativegadoxeticacidenhancedmriforpredictinghistopathologicgradeofhepatocellularcarcinoma AT leidazhang developmentandexternalvalidationofaradiomicsmodelderivedfrompreoperativegadoxeticacidenhancedmriforpredictinghistopathologicgradeofhepatocellularcarcinoma AT yingfangfan developmentandexternalvalidationofaradiomicsmodelderivedfrompreoperativegadoxeticacidenhancedmriforpredictinghistopathologicgradeofhepatocellularcarcinoma AT kuanshengma developmentandexternalvalidationofaradiomicsmodelderivedfrompreoperativegadoxeticacidenhancedmriforpredictinghistopathologicgradeofhepatocellularcarcinoma |