Magnetic resonance imaging-radiomics in endometrial cancer: a systematic review and meta-analysis

Objective Endometrial carcinoma is the most common gynecological tumor in developed countries. Clinicopathological factors and molecular subtypes are used to stratify the risk of recurrence and to tailor adjuvant treatment. The present study aimed to assess the role of radiomics analysis in pre-operatively predicting molecular or clinicopathological prognostic factors in patients with endometrial carcinoma. Methods Literature was searched for publications reporting radiomics analysis in assessing diagnostic performance of MRI for different outcomes. Diagnostic accuracy performance of risk prediction models was pooled using the metandi command in Stata. Results A search of MEDLINE (PubMed) resulted in 153 relevant articles. Fifteen articles met the inclusion criteria, for a total of 3608 patients. MRI showed pooled sensitivity and specificity 0.785 and 0.814, respectively, in predicting high-grade endometrial carcinoma, deep myometrial invasion (pooled sensitivity and specificity 0.743 and 0.816, respectively), lymphovascular space invasion (pooled sensitivity and specificity 0.656 and 0.753, respectively), and nodal metastasis (pooled sensitivity and specificity 0.831 and 0.736, respectively). Conclusions Pre-operative MRI-radiomics analyses in patients with endometrial carcinoma is a good predictor of tumor grading, deep myometrial invasion, lymphovascular space invasion, and nodal metastasis.