Assessment of a multivariable model using MRI-radiomics, age and sex for the classification of hepatocellular adenoma subtypes
Objectives: Non-invasive subtyping of hepatocellular adenomas (HCA) remains challenging for several subtypes, thus carrying different levels of risks and management. The goal of this study is to devise a multivariable diagnostic model based on basic clinical features (age and sex) combined with MRI-...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-06-01
|
| Series: | Research in Diagnostic and Interventional Imaging |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772652524000073 |
| _version_ | 1797220450485403648 |
|---|---|
| author | Guillaume Declaux Baudouin Denis de Senneville Hervé Trillaud Paulette Bioulac-Sage Charles Balabaud Jean-Frédéric Blanc Laurent Facq Nora Frulio |
| author_facet | Guillaume Declaux Baudouin Denis de Senneville Hervé Trillaud Paulette Bioulac-Sage Charles Balabaud Jean-Frédéric Blanc Laurent Facq Nora Frulio |
| author_sort | Guillaume Declaux |
| collection | DOAJ |
| description | Objectives: Non-invasive subtyping of hepatocellular adenomas (HCA) remains challenging for several subtypes, thus carrying different levels of risks and management. The goal of this study is to devise a multivariable diagnostic model based on basic clinical features (age and sex) combined with MRI-radiomics and to evaluate its diagnostic performance. Methods: This single-center retrospective case-control study included all consecutive patients with HCA identified within the pathological database from our institution from January 2003 to April 2018 with MRI examination (T2, T1-no injection/injection-arterial-portal); volumes of interest were manually delineated in adenomas and 38 textural features were extracted (LIFEx, v5.10). Qualitative (i.e., visual on MRI) and automatic (computer-assisted) analysis were compared. The prognostic scores of a multivariable diagnostic model based on basic clinical features (age and sex) combined with MRI-radiomics (tumor volume and texture features) were assessed using a cross-validated Random Forest algorithm. Results: Via visual MR-analysis, HCA subgroups could be classified with balanced accuracies of 80.8 % (I-HCA or ß-I-HCA, the two being indistinguishable), 81.8 % (H-HCA) and 74.4 % (sh-HCA or ß-HCA also indistinguishable). Using a model including age, sex, volume and texture variables, HCA subgroups were predicted (multivariate classification) with an averaged balanced accuracy of 58.6 %, best=73.8 % (sh-HCA) and 71.9 % (ß-HCA). I-HCA and ß-I-HCA could be also distinguished (binary classification) with a balanced accuracy of 73 %. Conclusion: Multiple HCA subtyping could be improved using machine-learning algorithms including two clinical features, i.e., age and sex, combined with MRI-radiomics. Future HCA studies enrolling more patients will further test the validity of the model. |
| first_indexed | 2024-04-24T12:49:44Z |
| format | Article |
| id | doaj.art-2aa22bbc0a55433fb262bbc569dae134 |
| institution | Directory Open Access Journal |
| issn | 2772-6525 |
| language | English |
| last_indexed | 2024-04-24T12:49:44Z |
| publishDate | 2024-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Research in Diagnostic and Interventional Imaging |
| spelling | doaj.art-2aa22bbc0a55433fb262bbc569dae1342024-04-06T04:40:45ZengElsevierResearch in Diagnostic and Interventional Imaging2772-65252024-06-0110100046Assessment of a multivariable model using MRI-radiomics, age and sex for the classification of hepatocellular adenoma subtypesGuillaume Declaux0Baudouin Denis de Senneville1Hervé Trillaud2Paulette Bioulac-Sage3Charles Balabaud4Jean-Frédéric Blanc5Laurent Facq6Nora Frulio7Service d'imagerie diagnostique et Interventionnelle, centre médicochirurgical Magellan, hôpital Saint-André, centre hospitalier universitaire de Bordeaux, 33000, Bordeaux, FranceUniversité de Bordeaux, CNRS, Inria, Bordeaux INP, IMB, UMR 5251, 33400, Talence, France; Corresponding author.Service d'imagerie diagnostique et Interventionnelle, centre médicochirurgical Magellan, hôpital Saint-André, centre hospitalier universitaire de Bordeaux, 33000, Bordeaux, France; Université de Bordeaux, CNRS, Inria, Bordeaux INP, IMB, UMR 5251, 33400, Talence, FranceService de pathologie, hôpital Pellegrin, centre hospitalier universitaire de Bordeaux, Bordeaux, France; Université de Bordeaux, Bordeaux Research in Translational Oncology, Bordeaux, FranceUniversité de Bordeaux, Bordeaux Research in Translational Oncology, Bordeaux, France; Service d'hépato-gastroentérologie et oncologie digestive, centre médicochirurgical Magellan, hôpital Haut-Lévêque, centre hospitalier universitaire de Bordeaux, Bordeaux, FranceService d'hépato-gastroentérologie et oncologie digestive, centre médicochirurgical Magellan, hôpital Haut-Lévêque, centre hospitalier universitaire de Bordeaux, Bordeaux, FranceUniversité de Bordeaux, CNRS, Inria, Bordeaux INP, IMB, UMR 5251, 33400, Talence, FranceService d'imagerie diagnostique et Interventionnelle, centre médicochirurgical Magellan, hôpital Saint-André, centre hospitalier universitaire de Bordeaux, 33000, Bordeaux, FranceObjectives: Non-invasive subtyping of hepatocellular adenomas (HCA) remains challenging for several subtypes, thus carrying different levels of risks and management. The goal of this study is to devise a multivariable diagnostic model based on basic clinical features (age and sex) combined with MRI-radiomics and to evaluate its diagnostic performance. Methods: This single-center retrospective case-control study included all consecutive patients with HCA identified within the pathological database from our institution from January 2003 to April 2018 with MRI examination (T2, T1-no injection/injection-arterial-portal); volumes of interest were manually delineated in adenomas and 38 textural features were extracted (LIFEx, v5.10). Qualitative (i.e., visual on MRI) and automatic (computer-assisted) analysis were compared. The prognostic scores of a multivariable diagnostic model based on basic clinical features (age and sex) combined with MRI-radiomics (tumor volume and texture features) were assessed using a cross-validated Random Forest algorithm. Results: Via visual MR-analysis, HCA subgroups could be classified with balanced accuracies of 80.8 % (I-HCA or ß-I-HCA, the two being indistinguishable), 81.8 % (H-HCA) and 74.4 % (sh-HCA or ß-HCA also indistinguishable). Using a model including age, sex, volume and texture variables, HCA subgroups were predicted (multivariate classification) with an averaged balanced accuracy of 58.6 %, best=73.8 % (sh-HCA) and 71.9 % (ß-HCA). I-HCA and ß-I-HCA could be also distinguished (binary classification) with a balanced accuracy of 73 %. Conclusion: Multiple HCA subtyping could be improved using machine-learning algorithms including two clinical features, i.e., age and sex, combined with MRI-radiomics. Future HCA studies enrolling more patients will further test the validity of the model.http://www.sciencedirect.com/science/article/pii/S2772652524000073AdenomaHepatocellularBiomarker |
| spellingShingle | Guillaume Declaux Baudouin Denis de Senneville Hervé Trillaud Paulette Bioulac-Sage Charles Balabaud Jean-Frédéric Blanc Laurent Facq Nora Frulio Assessment of a multivariable model using MRI-radiomics, age and sex for the classification of hepatocellular adenoma subtypes Research in Diagnostic and Interventional Imaging Adenoma Hepatocellular Biomarker |
| title | Assessment of a multivariable model using MRI-radiomics, age and sex for the classification of hepatocellular adenoma subtypes |
| title_full | Assessment of a multivariable model using MRI-radiomics, age and sex for the classification of hepatocellular adenoma subtypes |
| title_fullStr | Assessment of a multivariable model using MRI-radiomics, age and sex for the classification of hepatocellular adenoma subtypes |
| title_full_unstemmed | Assessment of a multivariable model using MRI-radiomics, age and sex for the classification of hepatocellular adenoma subtypes |
| title_short | Assessment of a multivariable model using MRI-radiomics, age and sex for the classification of hepatocellular adenoma subtypes |
| title_sort | assessment of a multivariable model using mri radiomics age and sex for the classification of hepatocellular adenoma subtypes |
| topic | Adenoma Hepatocellular Biomarker |
| url | http://www.sciencedirect.com/science/article/pii/S2772652524000073 |
| work_keys_str_mv | AT guillaumedeclaux assessmentofamultivariablemodelusingmriradiomicsageandsexfortheclassificationofhepatocellularadenomasubtypes AT baudouindenisdesenneville assessmentofamultivariablemodelusingmriradiomicsageandsexfortheclassificationofhepatocellularadenomasubtypes AT hervetrillaud assessmentofamultivariablemodelusingmriradiomicsageandsexfortheclassificationofhepatocellularadenomasubtypes AT paulettebioulacsage assessmentofamultivariablemodelusingmriradiomicsageandsexfortheclassificationofhepatocellularadenomasubtypes AT charlesbalabaud assessmentofamultivariablemodelusingmriradiomicsageandsexfortheclassificationofhepatocellularadenomasubtypes AT jeanfredericblanc assessmentofamultivariablemodelusingmriradiomicsageandsexfortheclassificationofhepatocellularadenomasubtypes AT laurentfacq assessmentofamultivariablemodelusingmriradiomicsageandsexfortheclassificationofhepatocellularadenomasubtypes AT norafrulio assessmentofamultivariablemodelusingmriradiomicsageandsexfortheclassificationofhepatocellularadenomasubtypes |