Discrimination of benign and malignant ovarian sex cord-stromal tumors through the analysis of clinical features, MR imaging, and MR-based radiomics - Report - MDSpire
Advertisement
Discrimination of benign and malignant ovarian sex cord-stromal tumors through the analysis of clinical features, MR imaging, and MR-based radiomics
Clinical Report: Differentiating Benign from Malignant Ovarian SCSTs
Overview
This study evaluates the diagnostic performance of clinical parameters, conventional MRI, and radiomic signatures in differentiating benign from malignant ovarian sex cord-stromal tumors (SCSTs). A combined nomogram integrating these modalities demonstrated optimal predictive performance and clinical net benefit.
Background
Ovarian sex cord-stromal tumors (SCSTs) are rare neoplasms that account for 7-8% of all ovarian tumors, presenting significant diagnostic challenges due to their histopathological heterogeneity. Accurate preoperative identification is crucial for guiding therapeutic strategies, particularly in younger women where conservative surgical approaches are prioritized. Advanced imaging techniques, including MRI and radiomics, are being explored to enhance diagnostic accuracy.
Data Highlights
Model
Training AUC (95% CI)
Validation AUC (95% CI)
Traditional Model
0.880 (0.807-0.946)
0.908 (0.797-0.989)
T2&DWI Model
0.887 (0.802-0.955)
0.843 (0.684-0.963)
Combined Model
0.945 (0.892-0.985)
0.914 (0.798-0.988)
Key Findings
The study included 113 patients with 123 pathologically confirmed SCSTs (42 malignant, 81 benign).
The traditional model achieved the highest AUCs among conventional methods.
The combined nomogram integrated radiomic scores with clinical and MRI predictors for enhanced performance.
Decision curve analysis confirmed greater clinical net benefit of the combined model across threshold probabilities.
Radiomics features were extracted from fat-suppressed T2-weighted imaging and diffusion-weighted imaging sequences.
Clinical Implications
The combined nomogram developed in this study may assist clinicians in accurately differentiating between benign and malignant SCSTs, potentially guiding more personalized therapeutic management. Enhanced diagnostic accuracy is particularly important for younger women where preserving reproductive function is a priority.
Conclusion
The combined model demonstrates optimal predictive performance for differentiating SCSTs, highlighting the potential of integrating clinical, MRI, and radiomic data in clinical practice.
