MRI-Based Radiomic Features Help Identify Lesions and Predict Histopathological Grade of Hepatocellular Carcinoma
Hepatocellular carcinoma (HCC) is the most common form of liver cancer. Radiomics is a promising tool that may increase the value of magnetic resonance imaging (MRI) in the management of HCC. The purpose of our study is to develop an MRI-based radiomics approach to preoperatively detect HCC and pred...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/12/5/1085 |
| _version_ | 1797500470328033280 |
|---|---|
| author | Valentina Brancato Nunzia Garbino Marco Salvatore Carlo Cavaliere |
| author_facet | Valentina Brancato Nunzia Garbino Marco Salvatore Carlo Cavaliere |
| author_sort | Valentina Brancato |
| collection | DOAJ |
| description | Hepatocellular carcinoma (HCC) is the most common form of liver cancer. Radiomics is a promising tool that may increase the value of magnetic resonance imaging (MRI) in the management of HCC. The purpose of our study is to develop an MRI-based radiomics approach to preoperatively detect HCC and predict its histological grade. Thirty-eight HCC patients at staging who underwent axial T2-weighted and dynamic contrast-enhanced MRI (DCE-MRI) were considered. Three-dimensional volumes of interest (VOIs) were manually placed on HCC lesions and normal hepatic tissue (HT) on arterial phase post-contrast images. Radiomic features from T2 images and arterial, portal and tardive post-contrast images from DCE-MRI were extracted by using Pyradiomics. Feature selection was performed using correlation filter, Wilcoxon-rank sum test and mutual information. Predictive models were constructed for HCC differentiation with respect to HT and HCC histopathologic grading used at each step an imbalance-adjusted bootstrap resampling (IABR) on 1000 samples. Promising results were obtained from radiomic prediction models, with best AUCs ranging from 71% to 96%. Radiomics MRI based on T2 and DCE-MRI revealed promising results concerning both HCC detection and grading. It may be a suitable tool for personalized treatment of HCC patients and could also be used to develop new prognostic biomarkers useful for HCC assessment without the need for invasive procedures. |
| first_indexed | 2024-03-10T03:03:20Z |
| format | Article |
| id | doaj.art-e052455a13c94030adbc4551f32040a4 |
| institution | Directory Open Access Journal |
| issn | 2075-4418 |
| language | English |
| last_indexed | 2024-03-10T03:03:20Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj.art-e052455a13c94030adbc4551f32040a42023-11-23T10:39:08ZengMDPI AGDiagnostics2075-44182022-04-01125108510.3390/diagnostics12051085MRI-Based Radiomic Features Help Identify Lesions and Predict Histopathological Grade of Hepatocellular CarcinomaValentina Brancato0Nunzia Garbino1Marco Salvatore2Carlo Cavaliere3IRCCS Synlab SDN, 80143 Naples, ItalyIRCCS Synlab SDN, 80143 Naples, ItalyIRCCS Synlab SDN, 80143 Naples, ItalyIRCCS Synlab SDN, 80143 Naples, ItalyHepatocellular carcinoma (HCC) is the most common form of liver cancer. Radiomics is a promising tool that may increase the value of magnetic resonance imaging (MRI) in the management of HCC. The purpose of our study is to develop an MRI-based radiomics approach to preoperatively detect HCC and predict its histological grade. Thirty-eight HCC patients at staging who underwent axial T2-weighted and dynamic contrast-enhanced MRI (DCE-MRI) were considered. Three-dimensional volumes of interest (VOIs) were manually placed on HCC lesions and normal hepatic tissue (HT) on arterial phase post-contrast images. Radiomic features from T2 images and arterial, portal and tardive post-contrast images from DCE-MRI were extracted by using Pyradiomics. Feature selection was performed using correlation filter, Wilcoxon-rank sum test and mutual information. Predictive models were constructed for HCC differentiation with respect to HT and HCC histopathologic grading used at each step an imbalance-adjusted bootstrap resampling (IABR) on 1000 samples. Promising results were obtained from radiomic prediction models, with best AUCs ranging from 71% to 96%. Radiomics MRI based on T2 and DCE-MRI revealed promising results concerning both HCC detection and grading. It may be a suitable tool for personalized treatment of HCC patients and could also be used to develop new prognostic biomarkers useful for HCC assessment without the need for invasive procedures.https://www.mdpi.com/2075-4418/12/5/1085hepatocellular carcinomaradiomicsMRI |
| spellingShingle | Valentina Brancato Nunzia Garbino Marco Salvatore Carlo Cavaliere MRI-Based Radiomic Features Help Identify Lesions and Predict Histopathological Grade of Hepatocellular Carcinoma Diagnostics hepatocellular carcinoma radiomics MRI |
| title | MRI-Based Radiomic Features Help Identify Lesions and Predict Histopathological Grade of Hepatocellular Carcinoma |
| title_full | MRI-Based Radiomic Features Help Identify Lesions and Predict Histopathological Grade of Hepatocellular Carcinoma |
| title_fullStr | MRI-Based Radiomic Features Help Identify Lesions and Predict Histopathological Grade of Hepatocellular Carcinoma |
| title_full_unstemmed | MRI-Based Radiomic Features Help Identify Lesions and Predict Histopathological Grade of Hepatocellular Carcinoma |
| title_short | MRI-Based Radiomic Features Help Identify Lesions and Predict Histopathological Grade of Hepatocellular Carcinoma |
| title_sort | mri based radiomic features help identify lesions and predict histopathological grade of hepatocellular carcinoma |
| topic | hepatocellular carcinoma radiomics MRI |
| url | https://www.mdpi.com/2075-4418/12/5/1085 |
| work_keys_str_mv | AT valentinabrancato mribasedradiomicfeatureshelpidentifylesionsandpredicthistopathologicalgradeofhepatocellularcarcinoma AT nunziagarbino mribasedradiomicfeatureshelpidentifylesionsandpredicthistopathologicalgradeofhepatocellularcarcinoma AT marcosalvatore mribasedradiomicfeatureshelpidentifylesionsandpredicthistopathologicalgradeofhepatocellularcarcinoma AT carlocavaliere mribasedradiomicfeatureshelpidentifylesionsandpredicthistopathologicalgradeofhepatocellularcarcinoma |