Evaluation of inter-reader reproducibility of radiomic features in multiparametric magnetic resonance imaging of endometrial cancer

Objective: The aim of our study is to evaluate the inter-reader agreement of radiomic features extracted from different sequences of multiparametric magnetic resonance imaging (mpMRI) in endometrial cancer, thereby contributing to the development of radiomic models with higher reproducibility and facilitating their integration into clinical practice. Materials and Methods: This single-center, retrospective study included 59 patients with pathologically confirmed, untreated endometrial cancer. The MRI scans of the patients were obtained from both in-house and external PACS (Picture Archiving and Communication System) databases. Segmentations and radiomic analyses were performed on these images. Results: The median ICC values per sequence were calculated as follows: T2WS: 0.91 (0.61–0.99), T2WC: 0.91 (0.60–0.99), T2WA: 0.87 (0.45–0.99), T1CES: 0.92 (0.65–0.99), DWI: 0.91 (0.33–0.99), and ADC: 0.89 (0.28–0.99). The percentage of radiomic features with excellent agreement (ICC ≥ 0.90) was 58.9% for T2WS, 54.2% for T2WC, 44.9% for T2WA, 57.9% for T1CES, 54.2% for DWI, and 45.8% for ADC. Different levels of agreement were observed both among T2-weighted planes and between sequences. Conclusion: Among T2-weighted planes, the highest inter-reader agreement was observed in the sagittal plane (T2WS), while the lowest was found in the axial plane (T2WA). Among all sequences, T2WS and T1CES showed the highest agreement, whereas T2WA and ADC demonstrated the lowest. In the subclasses of radiomic features, the highest agreement is observed in Shape and GLDM, while the lowest agreement is seen in NGTDM and GLCM. Keywords: Magnetic Resonance Imaging, Endometrial Cancer, Radiomics, Reproducibility, Manuel Segmentation