Research on an MRI radiomics-based diagnostic model for differentiating ovarian Cystadenoma and cystadenocarcinoma

TANG Yanan; LI Xiang; MA Yichuan

doi:10.12122/j.issn.1674-4500.2025.11.09

Abstract：Objective To identify the model with the highest diagnostic value for differentiating ovarian cystadenoma(OCA)from ovarian cystadenocarcinoma(OCAC)by extracting and selecting features from MRI imaging data to establish radiomics and traditional MRI diagnostic models.Methods A retrospective analysis was conducted on 173 patients(82 OCA cases and 91 OCAC cases)confirmed by pathology and preoperatively undergoing contrast-enhanced MRI scans at the First Affiliated Hospital of Bengbu Medical University from January 2020 to December 2024.Univariate and multivariate regression analyses were performed on traditional MRI features to identify diagnostic predictors for OCA and OCAC,and diagnostic models were developed and evaluated.Patients were randomly divided into training(n=121)and testing(n=52)cohorts at a 7:3 ratio.Regions of interest(ROI)were delineated on T1-weighted contrast-enhanced(T1WI-CE)and T2-weighted(T2WI)sequences using the United Imaging Intelligence Research Platform.Extracted radiomic features underwent max-min normalization,Select K Best,and Least Absolute Shrinkage and Selection Operator regression for dimensionality reduction and optimal feature selection.Logistic regression models were constructed for T1WI-CE,T2WI,and combined T1WI-CE+T2WI.Diagnostic performance was evaluated using the AUC,calibration curves,and decision curve analysis(DCA).Results The combined T1WI-CE+T2WI radiomics model demonstrated superior diagnostic efficacy(AUC=0.886)compared to individual T1WI-CE,T2WI,and traditional MRI models.Conclusion MRI radiomics-based diagnostic models can effectively differentiate OCA from OCAC,providing guidance for clinical treatment strategies.