An MR-based radiomics model for differentiation between hepatocellular carcinoma and focal nodular hyperplasia in non-cirrhotic liver
Abstract Purpose We aimed to develop and validate a radiomics model for differentiating hepatocellular carcinoma (HCC) from focal nodular hyperplasia (FNH) in non-cirrhotic livers using Gd-DTPA contrast-enhanced magnetic resonance imaging (MRI). Methods We retrospectively enrolled 149 HCC and 75 FNH...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2021-06-01
|
| Series: | World Journal of Surgical Oncology |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12957-021-02266-7 |
| _version_ | 1818928245324644352 |
|---|---|
| author | Zongren Ding Kongying Lin Jun Fu Qizhen Huang Guoxu Fang Yanyan Tang Wuyi You Zhaowang Lin Zhan Lin Xingxi Pan Yongyi Zeng |
| author_facet | Zongren Ding Kongying Lin Jun Fu Qizhen Huang Guoxu Fang Yanyan Tang Wuyi You Zhaowang Lin Zhan Lin Xingxi Pan Yongyi Zeng |
| author_sort | Zongren Ding |
| collection | DOAJ |
| description | Abstract Purpose We aimed to develop and validate a radiomics model for differentiating hepatocellular carcinoma (HCC) from focal nodular hyperplasia (FNH) in non-cirrhotic livers using Gd-DTPA contrast-enhanced magnetic resonance imaging (MRI). Methods We retrospectively enrolled 149 HCC and 75 FNH patients treated between May 2015 and May 2019 at our center. Patients were randomly allocated to a training (n=156) and validation set (n=68). In total, 2260 radiomics features were extracted from the arterial phase and portal venous phase of Gd-DTPA contrast-enhanced MRI. Using Max-Relevance and Min-Redundancy, random forest, least absolute shrinkage, and selection operator algorithm for dimensionality reduction, multivariable logistic regression was used to build the radiomics model. A clinical model and combined model were also established. The diagnostic performance of the models was compared. Results Eight radiomics features were chosen for the radiomics model, and four clinical factors (age, sex, HbsAg, and enhancement pattern) were chosen for the clinical model. A combined model was built using the factors from the previous models. The classification accuracy of the combined model differentiated HCC from FNH in both the training and validation sets (0.956 and 0.941, respectively). The area under the receiver operating characteristic curve of the combined model was significantly better than that of the clinical model for both the training (0.984 vs. 0.937, p=0.002) and validation (0.972 vs. 0.903, p=0.032) sets. Conclusions The combined model provided a non-invasive quantitative method for differentiating HCC from FNH in non-cirrhotic liver with high accuracy. Our model may assist clinicians in the clinical decision-making process. |
| first_indexed | 2024-12-20T03:25:50Z |
| format | Article |
| id | doaj.art-c3a628efcfcf413e986c0ba9bfad7a50 |
| institution | Directory Open Access Journal |
| issn | 1477-7819 |
| language | English |
| last_indexed | 2024-12-20T03:25:50Z |
| publishDate | 2021-06-01 |
| publisher | BMC |
| record_format | Article |
| series | World Journal of Surgical Oncology |
| spelling | doaj.art-c3a628efcfcf413e986c0ba9bfad7a502022-12-21T19:55:06ZengBMCWorld Journal of Surgical Oncology1477-78192021-06-0119111010.1186/s12957-021-02266-7An MR-based radiomics model for differentiation between hepatocellular carcinoma and focal nodular hyperplasia in non-cirrhotic liverZongren Ding0Kongying Lin1Jun Fu2Qizhen Huang3Guoxu Fang4Yanyan Tang5Wuyi You6Zhaowang Lin7Zhan Lin8Xingxi Pan9Yongyi Zeng10Department of Hepatopancreatobiliary Surgery, Mengchao Hepatobiliary Hospital of Fujian Medical UniversityDepartment of Hepatopancreatobiliary Surgery, Mengchao Hepatobiliary Hospital of Fujian Medical UniversityDepartment of Hepatopancreatobiliary Surgery, Mengchao Hepatobiliary Hospital of Fujian Medical UniversityDepartment of Hepatopancreatobiliary Surgery, Mengchao Hepatobiliary Hospital of Fujian Medical UniversityDepartment of Hepatopancreatobiliary Surgery, Mengchao Hepatobiliary Hospital of Fujian Medical UniversityDepartment of Radiology, Mengchao Hepatobiliary Hospital of Fujian Medical UniversityDepartment of Radiology, Mengchao Hepatobiliary Hospital of Fujian Medical UniversityDepartment of Radiology, Mengchao Hepatobiliary Hospital of Fujian Medical UniversityDepartment of Radiology, Mengchao Hepatobiliary Hospital of Fujian Medical UniversityDepartment of Oncology, Nanhai Hospital Affiliated to Southern Medical UniversityDepartment of Hepatopancreatobiliary Surgery, Mengchao Hepatobiliary Hospital of Fujian Medical UniversityAbstract Purpose We aimed to develop and validate a radiomics model for differentiating hepatocellular carcinoma (HCC) from focal nodular hyperplasia (FNH) in non-cirrhotic livers using Gd-DTPA contrast-enhanced magnetic resonance imaging (MRI). Methods We retrospectively enrolled 149 HCC and 75 FNH patients treated between May 2015 and May 2019 at our center. Patients were randomly allocated to a training (n=156) and validation set (n=68). In total, 2260 radiomics features were extracted from the arterial phase and portal venous phase of Gd-DTPA contrast-enhanced MRI. Using Max-Relevance and Min-Redundancy, random forest, least absolute shrinkage, and selection operator algorithm for dimensionality reduction, multivariable logistic regression was used to build the radiomics model. A clinical model and combined model were also established. The diagnostic performance of the models was compared. Results Eight radiomics features were chosen for the radiomics model, and four clinical factors (age, sex, HbsAg, and enhancement pattern) were chosen for the clinical model. A combined model was built using the factors from the previous models. The classification accuracy of the combined model differentiated HCC from FNH in both the training and validation sets (0.956 and 0.941, respectively). The area under the receiver operating characteristic curve of the combined model was significantly better than that of the clinical model for both the training (0.984 vs. 0.937, p=0.002) and validation (0.972 vs. 0.903, p=0.032) sets. Conclusions The combined model provided a non-invasive quantitative method for differentiating HCC from FNH in non-cirrhotic liver with high accuracy. Our model may assist clinicians in the clinical decision-making process.https://doi.org/10.1186/s12957-021-02266-7RadiomicsHepatocellular carcinomaFocal nodular hyperplasiaMagnetic resonance imagingZongren Ding, Kongying Lin, and Jun Fu contributed equally to this work. |
| spellingShingle | Zongren Ding Kongying Lin Jun Fu Qizhen Huang Guoxu Fang Yanyan Tang Wuyi You Zhaowang Lin Zhan Lin Xingxi Pan Yongyi Zeng An MR-based radiomics model for differentiation between hepatocellular carcinoma and focal nodular hyperplasia in non-cirrhotic liver World Journal of Surgical Oncology Radiomics Hepatocellular carcinoma Focal nodular hyperplasia Magnetic resonance imaging Zongren Ding, Kongying Lin, and Jun Fu contributed equally to this work. |
| title | An MR-based radiomics model for differentiation between hepatocellular carcinoma and focal nodular hyperplasia in non-cirrhotic liver |
| title_full | An MR-based radiomics model for differentiation between hepatocellular carcinoma and focal nodular hyperplasia in non-cirrhotic liver |
| title_fullStr | An MR-based radiomics model for differentiation between hepatocellular carcinoma and focal nodular hyperplasia in non-cirrhotic liver |
| title_full_unstemmed | An MR-based radiomics model for differentiation between hepatocellular carcinoma and focal nodular hyperplasia in non-cirrhotic liver |
| title_short | An MR-based radiomics model for differentiation between hepatocellular carcinoma and focal nodular hyperplasia in non-cirrhotic liver |
| title_sort | mr based radiomics model for differentiation between hepatocellular carcinoma and focal nodular hyperplasia in non cirrhotic liver |
| topic | Radiomics Hepatocellular carcinoma Focal nodular hyperplasia Magnetic resonance imaging Zongren Ding, Kongying Lin, and Jun Fu contributed equally to this work. |
| url | https://doi.org/10.1186/s12957-021-02266-7 |
| work_keys_str_mv | AT zongrending anmrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT kongyinglin anmrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT junfu anmrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT qizhenhuang anmrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT guoxufang anmrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT yanyantang anmrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT wuyiyou anmrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT zhaowanglin anmrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT zhanlin anmrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT xingxipan anmrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT yongyizeng anmrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT zongrending mrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT kongyinglin mrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT junfu mrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT qizhenhuang mrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT guoxufang mrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT yanyantang mrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT wuyiyou mrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT zhaowanglin mrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT zhanlin mrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT xingxipan mrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver AT yongyizeng mrbasedradiomicsmodelfordifferentiationbetweenhepatocellularcarcinomaandfocalnodularhyperplasiainnoncirrhoticliver |