Abstract

BackgroundEpithelial ovarian cancer (EOC) is the most malignant gynecological tumor in women. This study aimed to construct and compare radiomics-clinical nomograms based on MR images in EOC prognosis prediction.MethodsA total of 186 patients with pathologically proven EOC were enrolled and randomly divided into a training cohort (n = 130) and a validation cohort (n = 56). Clinical characteristics of each patient were retrieved from the hospital information system. A total of 1116 radiomics features were extracted from tumor body on T2-weighted imaging (T2WI), T1-weighted imaging (T1WI), diffusion weighted imaging (DWI) and contrast-enhanced T1-weighted imaging (CE-T1WI). Paired sequence signatures were constructed, selected and trained to build a prognosis prediction model. Radiomic-clinical nomogram was constructed based on multivariate logistic regression analysis with radiomics score and clinical features. The predictive performance was evaluated by receiver operating characteristic curve (ROC) analysis, decision curve analysis (DCA) and calibration curve.ResultsThe T2WI radiomic-clinical nomogram achieved a favorable prediction performance in the training and validation cohort with an area under ROC curve (AUC) of 0.866 and 0.818, respectively. The DCA showed that the T2WI radiomic-clinical nomogram was better than other models with a greater clinical net benefit.ConclusionMR-based radiomics analysis showed the high accuracy in prognostic estimation of EOC patients and could help to predict therapeutic outcome before treatment.

Highlights

  • Epithelial ovarian cancer (EOC) is the most malignant gynecological tumor in women [1]

  • We found that the radiomic features of T1-weighted imaging (T1WI) on the maximum lesion plane were most likely related to the clinical outcome [12]

  • The purpose of this study is twofold: firstly, we compared the correlation between preoperative most casesMagnetic resonance (MR)-based radiomic features and clinical outcomes in a large cohort sample; secondly, we evaluated the best predictor of MRI features and compared its performance in different acquisition sequences

Read more

Summary

Introduction

Epithelial ovarian cancer (EOC) is the most malignant gynecological tumor in women [1]. MR-based imaging informatics has been rapidly developed, which provides useful information for the classification of ovarian masses [10,11,12,13]. The authors used deep learning methods to extract computer tomography (CT) image features and reported the effective 3-year recurrence probability prediction from two institutions [15]. We found that the radiomic features of T1WI on the maximum lesion plane were most likely related to the clinical outcome [12]. Epithelial ovarian cancer (EOC) is the most malignant gynecological tumor in women. This study aimed to construct and compare radiomics-clinical nomograms based on MR images in EOC prognosis prediction

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call