{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"omics_type":["Unknown"],"volume":["12(4)"],"submitter":["Lin CY"],"pubmed_abstract":["This study aimed to build machine learning prediction models for predicting pathological subtypes of prevascular mediastinal tumors (PMTs). The candidate predictors were clinical variables and dynamic contrast-enhanced MRI (DCE-MRI)-derived perfusion parameters. The clinical data and preoperative DCE-MRI images of 62 PMT patients, including 17 patients with lymphoma, 31 with thymoma, and 14 with thymic carcinoma, were retrospectively analyzed. Six perfusion parameters were calculated as candidate predictors. Univariate receiver-operating-characteristic curve analysis was performed to evaluate the performance of the prediction models. A predictive model was built based on multi-class classification, which detected lymphoma, thymoma, and thymic carcinoma with sensitivity of 52.9%, 74.2%, and"],"journal":["Diagnostics (Basel, Switzerland)"],"pagination":["889"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC9026802"],"repository":["biostudies-literature"],"pubmed_title":["An MRI-Based Clinical-Perfusion Model Predicts Pathological Subtypes of Prevascular Mediastinal Tumors."],"pmcid":["PMC9026802"],"pubmed_authors":["Fang YD","Chang CC","Tseng YL","Lai CH","Yen YT","Huang WL","Chen YY","Huang LT","Chen TY","Tang SY","Lin CY","Liu YS"],"additional_accession":[]},"is_claimable":false,"name":"An MRI-Based Clinical-Perfusion Model Predicts Pathological Subtypes of Prevascular Mediastinal Tumors.","description":"This study aimed to build machine learning prediction models for predicting pathological subtypes of prevascular mediastinal tumors (PMTs). The candidate predictors were clinical variables and dynamic contrast-enhanced MRI (DCE-MRI)-derived perfusion parameters. The clinical data and preoperative DCE-MRI images of 62 PMT patients, including 17 patients with lymphoma, 31 with thymoma, and 14 with thymic carcinoma, were retrospectively analyzed. Six perfusion parameters were calculated as candidate predictors. Univariate receiver-operating-characteristic curve analysis was performed to evaluate the performance of the prediction models. A predictive model was built based on multi-class classification, which detected lymphoma, thymoma, and thymic carcinoma with sensitivity of 52.9%, 74.2%, and","dates":{"release":"2022-01-01T00:00:00Z","publication":"2022 Apr","modification":"2025-04-06T19:49:19.602Z","creation":"2025-04-06T19:49:19.602Z"},"accession":"S-EPMC9026802","cross_references":{"pubmed":["35453937"],"doi":["10.3390/diagnostics12040889"]}}