Adnexal masses and risk of malignancy by radiomics: the future is now

Prospective multicentre validation of TRACE4OC (DeepTrace Technologies Srl) diagnostic model, implementation of TRACE4OC+ for the triage of adnexal masses at ultrasound (US) examination and comparison with the risk of malignancy calculated with ADNEX IOTA score and management defined by O-RADS. From a multicentre consecutive series of women scheduled for surgery, we collected and evaluated 859 US images of adnexal masses with TRACE4OC. All the masses were divided into 3 homogeneous groups: solid, cystic and motley and then tested with TRACE4OC platform; the variables to proceed with the analysis were CA125, menopausal status, presence of shadows at US. We then improved the previous model (TRACE4OC+) to better stratify cystic masses with ground glass echogenicity suspicious for endometriomas, often defined as medium-high risk with TRACE4OC. The risk of malignancy of the masses was calculated also with ADNEX IOTA score and the proposed management was evaluated with O-RADS classes. The performances for both the diagnostic strategies were evaluated. TRACE4OC model showed 98.3% sensitivity and 79.5% specificity when tested on the retrospective and prospective multicentric external data sets of masses (357 malignant and 502 benign lesions at final histology), achieving 77.3% positive predictive value (PPV). TRACE4OC+ model showed 97.8% sensitivity, 82.9%specificity and 80.2% PPV. ADNEX IOTA model showed 97.2% sensitivity, 79.3% and 76.9% PPV. Performance between the 3 models did not result in statistically significant differences (p-value > 0.05). Radiomics and machine learning can play a promising and practical role as a decision support tool for the clinician in the diagnostic workup of adnexal masses thus providing a reduction of the surgery rate for benign lesions still warranting very high sensitivity. Assessment with TRACE4OC and TRACE4OC+ were not shown to be inferior to ADNEX/O-RADS, however requiring less information and less examiner training, representing an effective tool for the triage of adnexal masses.