MRI- and Histologic-Molecular-Based Radio-Genomics Nomogram for Preoperative Assessment of Risk Classes in Endometrial Cancer

SIMPLE SUMMARY: Our study showed the potential of whole tumor radio-genomic-based analysis for the preoperative evaluation of endometrial cancer (EC). Since radio-genomics can provide information regarding high-risk factors from standard preoperative MR images, radio-genomic-based models could be useful in preoperative risk stratification of EC patients and prediction of lymphatic-vascular infiltration (LVSI) before surgery. Predictive radio-genomics models based on T2WI and ADC texture features showed a medium-to-high diagnostic performance in predicting low-risk EC and LVSI. The innovative clinical impact of our investigation is to demonstrate how radio-genomic analysis can be supportive in the assessment of some parameters considered incomplete and inaccurate after a preoperative MRI and biopsy such as LVSI assessed only after post-surgical histologic analysis; myometrial infiltration, which is highly operator-dependent on MRI; and frequent discordance between preoperative and post-hysterectomy findings for tumor grade. Application of predictive models in clinical practice would lead to significant advantages in the preoperative selection of individualized therapy and reductions in time/cost. ABSTRACT: High- and low-risk endometrial carcinoma (EC) differ in whether or not a lymphadenectomy is performed. We aimed to develop MRI-based radio-genomic models able to preoperatively assess lymph-vascular space invasion (LVSI) and discriminate between low- and high-risk EC according to the ESMO-ESGO-ESTRO 2020 guidelines, which include molecular risk classification proposed by “ProMisE”. This is a retrospective, multicentric study that included 64 women with EC who underwent 3T-MRI before a hysterectomy. Radiomics features were extracted from T2WI images and apparent diffusion coefficient maps (ADC) after manual segmentation of the gross tumor volume. We constructed a multiple logistic regression approach from the most relevant radiomic features to distinguish between low- and high-risk classes under the ESMO-ESGO-ESTRO 2020 guidelines. A similar approach was taken to assess LVSI. Model diagnostic performance was assessed via ROC curves, accuracy, sensitivity and specificity on training and test sets. The LVSI predictive model used a single feature from ADC as a predictor; the risk class model used two features as predictors from both ADC and T2WI. The low-risk predictive model showed an AUC of 0.74 with an accuracy, sensitivity, and specificity of 0.74, 0.76, 0.94; the LVSI model showed an AUC of 0.59 with an accuracy, sensitivity, and specificity of 0.60, 0.50, 0.61. MRI-based radio-genomic models are useful for preoperative EC risk stratification and may facilitate therapeutic management.