364 RadiOmics and molecular classification in endometrial cancer (the ROME study): a step forward to a simplified precision medicine

Introduction/Background* Molecular/genomic profiling is the most accurate method to assess prognosis of endometrial cancer patients. Similarly, the adoption of radiomics showed important results for screening, diagnosis and prognosis, across various radiological systems and oncologic specialties. Here, we aim to correlate radiomic features obtained from ultrasound images with the molecular/genomic profiling to identify new hallmarks for stratification of endometrial cancer patients into different classes of risk. Methodology This prospective single-arm observational study Patients with newly diagnosed endometrial cancer will have ultrasonographic evaluation and radiomic analysis of the ultrasonographic images. Then patients will have surgery followed by molecular/genomic evaluation. We will correlate radiomic features with molecular/genomic profiling to classify prognosis. Major Inclusion/Exclusion Criteria : Consecutive patients (aged 18 years or more) with newly diagnosed endometrial cancer. Patients should have preoperative ultrasonographic evaluation followed by surgery. Result(s)* The central hypothesis is that combining radiomic features with molecular features might allow identifying various classes of risk for endometrial cancer, e.g. predicting unfavorable molecular/genomic profiling. The rationale for the proposed research is that once validated, radiomics applied to ultrasonographic images would be an effective, innovative and cheap method for tailor operative and postoperative treatment modality in endometrial cancer. Primary Endpoint : The main endpoints will: (i) to define the mechanism by which radiomic features predict the classification of endometrial cancer into various classes of risk e.g. predicting unfavorable molecular/genomic profiling as defined by molecular classification; (ii) to determinate the scaled impact of radiomic features assessed on ultrasonographic images of endometrial tumors; and (iii) to assess the intraobserver and interobserver reproducibility of radiomic features on ultrasonographic images of endometrial tumors. Overall, 100 patients for study cohort and 40 for the validation cohort. Conclusion* We expect that the radiomic analysis of ultrasonographic images by means of radiomic classifier of risks will provide comparable results to molecular/genomic. (Trial Registration: GR-2019-12370566 Bando per la Ricerca Finalizzata 2019, Ministero della 24 Salute, Repubblica Italiana)