Radiomics of Preoperative Multi-Sequence Magnetic Resonance Imaging Can Improve the Predictive Performance of Microvascular Invasion in Hepatocellular Carcinoma.
Wan Min Liu, Xing Yu Zhao, Meng Ting Gu, Kai Rong Song, Wei Zheng, Hui Yu, Hui Lin Chen, Xiao Wen Xu, Xiang Zhou, Ai E Liu, Ning Yang Jia, Pei Jun Wang
{"title":"Radiomics of Preoperative Multi-Sequence Magnetic Resonance Imaging Can Improve the Predictive Performance of Microvascular Invasion in Hepatocellular Carcinoma.","authors":"Wan Min Liu, Xing Yu Zhao, Meng Ting Gu, Kai Rong Song, Wei Zheng, Hui Yu, Hui Lin Chen, Xiao Wen Xu, Xiang Zhou, Ai E Liu, Ning Yang Jia, Pei Jun Wang","doi":"10.14740/wjon1731","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>The aim of the study is to demonstrate that radiomics of preoperative multi-sequence magnetic resonance imaging (MRI) can indeed improve the predictive performance of microvascular invasion (MVI) in hepatocellular carcinoma (HCC).</p><p><strong>Methods: </strong>A total of 206 patients with pathologically confirmed HCC who underwent preoperative enhanced MRI were retrospectively recruited. Univariate and multivariate logistic regression analysis identified the independent clinicoradiologic predictors of MVI present and constituted the clinicoradiologic model. Recursive feature elimination (RFE) was applied to select radiomics features (extracted from six sequence images) and constructed the radiomics model. Clinicoradiologic model plus radiomics model formed the clinicoradiomics model. Five-fold cross-validation was used to validate the three models. Discrimination, calibration, and clinical utility were used to evaluate the performance. Net reclassification improvement (NRI) and integrated discrimination improvement (IDI) were used to compare the prediction accuracy between models.</p><p><strong>Results: </strong>The clinicoradiologic model contained alpha-fetoprotein (AFP)_lg10, radiological capsule enhancement, enhancement pattern and arterial peritumoral enhancement, which were independent risk factors of MVI. There were 18 radiomics features related to MVI constructed the radiomics model. The mean area under the receiver operating curve (AUC) of clinicoradiologic, radiomics and clinicoradiomics model were 0.849, 0.925 and 0.950 in the training cohort and 0.846, 0.907 and 0.933 in the validation cohort, respectively. The three models' calibration curves fitted well, and decision curve analysis (DCA) confirmed the clinical usefulness. Compared with the clinicoradiologic model, the NRI of radiomics and clinicoradiomics model increased significantly by 0.575 and 0.825, respectively, and the IDI increased significantly by 0.280 and 0.398, respectively.</p><p><strong>Conclusions: </strong>Radiomics of preoperative multi-sequence MRI can improve the predictive performance of MVI in HCC.</p>","PeriodicalId":46797,"journal":{"name":"World Journal of Oncology","volume":null,"pages":null},"PeriodicalIF":2.1000,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10807913/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"World Journal of Oncology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.14740/wjon1731","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2023/12/9 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"ONCOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Background: The aim of the study is to demonstrate that radiomics of preoperative multi-sequence magnetic resonance imaging (MRI) can indeed improve the predictive performance of microvascular invasion (MVI) in hepatocellular carcinoma (HCC).
Methods: A total of 206 patients with pathologically confirmed HCC who underwent preoperative enhanced MRI were retrospectively recruited. Univariate and multivariate logistic regression analysis identified the independent clinicoradiologic predictors of MVI present and constituted the clinicoradiologic model. Recursive feature elimination (RFE) was applied to select radiomics features (extracted from six sequence images) and constructed the radiomics model. Clinicoradiologic model plus radiomics model formed the clinicoradiomics model. Five-fold cross-validation was used to validate the three models. Discrimination, calibration, and clinical utility were used to evaluate the performance. Net reclassification improvement (NRI) and integrated discrimination improvement (IDI) were used to compare the prediction accuracy between models.
Results: The clinicoradiologic model contained alpha-fetoprotein (AFP)_lg10, radiological capsule enhancement, enhancement pattern and arterial peritumoral enhancement, which were independent risk factors of MVI. There were 18 radiomics features related to MVI constructed the radiomics model. The mean area under the receiver operating curve (AUC) of clinicoradiologic, radiomics and clinicoradiomics model were 0.849, 0.925 and 0.950 in the training cohort and 0.846, 0.907 and 0.933 in the validation cohort, respectively. The three models' calibration curves fitted well, and decision curve analysis (DCA) confirmed the clinical usefulness. Compared with the clinicoradiologic model, the NRI of radiomics and clinicoradiomics model increased significantly by 0.575 and 0.825, respectively, and the IDI increased significantly by 0.280 and 0.398, respectively.
Conclusions: Radiomics of preoperative multi-sequence MRI can improve the predictive performance of MVI in HCC.
期刊介绍：
World Journal of Oncology, bimonthly, publishes original contributions describing basic research and clinical investigation of cancer, on the cellular, molecular, prevention, diagnosis, therapy and prognosis aspects. The submissions can be basic research or clinical investigation oriented. This journal welcomes those submissions focused on the clinical trials of new treatment modalities for cancer, and those submissions focused on molecular or cellular research of the oncology pathogenesis. Case reports submitted for consideration of publication should explore either a novel genomic event/description or a new safety signal from an oncolytic agent. The areas of interested manuscripts are these disciplines: tumor immunology and immunotherapy; cancer molecular pharmacology and chemotherapy; drug sensitivity and resistance; cancer epidemiology; clinical trials; cancer pathology; radiobiology and radiation oncology; solid tumor oncology; hematological malignancies; surgical oncology; pediatric oncology; molecular oncology and cancer genes; gene therapy; cancer endocrinology; cancer metastasis; prevention and diagnosis of cancer; other cancer related subjects. The types of manuscripts accepted are original article, review, editorial, short communication, case report, letter to the editor, book review.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
