Article Text

Download PDFPDF

2022-RA-610-ESGO Radiomics and transvaginal ultrasound in adnexal masses: is the next future of diagnostics here?
  1. Valentina Chiappa1,
  2. Matteo Interlenghi2,
  3. Christian Salvatore2,
  4. Robert Fruscio3,
  5. Simone Ferrero4,
  6. Federica Rosati5,
  7. Lucia de Meis6,
  8. Martino Rolla7,
  9. Umberto Leone Roberti Maggiore1,
  10. Silvia Ficarelli8,
  11. Chiara Coco1,
  12. Ludovica Spanò Bascio1,
  13. Isabella Castiglioni2 and
  14. Francesco Raspagliesi1
  1. 1Fondazione IRCCS Istituto Nazionale dei Tumori, Milano, Italy
  2. 2DeepTrace Technologies S.R.L., Milan, Italy
  3. 3Università degli Studi Milano-Bicocca, Monza, Italy
  4. 4Irccs Ospedale Policlinico San Martino, Genova, Italy
  5. 5Ospedale Infermi di Rimini, Rimini, Italy
  6. 6IRCCS Policlinico di Sant’Orsola, Bologna, Italy
  7. 7Ospedale Maggiore di Parma, Parma, Italy
  8. 8Spedali Civili di Brescia, Brescia, Italy


Introduction/Background Multicenter prospective clinical validation of the radiomic machine learning model (TRACE4OC) applied to transvaginal ultrasound (US) in predicting the risk of malignancy of adnexal masses.

Methodology From a multicenter prospective consecutive series of women scheduled for surgery of adnexal masses, we collected and evaluated, fully blinded, 230 preoperative US images of adnexal masses with the TRACE4OC radiomic model previously developed according to the International Biomarker Standardization Initiative guidelines, trained and externally validated on a retrospective study of 274 US images of adnexal masses using histopathology as reference standard. Figure 1 shows the distribution of a radiomic texture feature (entropy of the co-occurrence matrix of gray levels) in an ovarian cystic malignant mass (a mucinous borderline tumor).

Results TRACE4OC model showed 91.3% accuracy, 99.0% sensitivity, 86.4% specificity when tested on the prospective multicentric external datasets of 230 masses (resulting into 90 malignant and 140 benign lesions at final histology), achieving 82.4% positive predictive value (PPV). The model shows a high correlation with finali histology (Pearson r: 0.8425 (95%CI: 0.800–0.876);p<0.001). The discrepancy was 0.473 ((SD: 0.50) 95%CI: 0.408, 0.538).

Abstract 2022-RA-610-ESGO Figure 1

Conclusion The radiomic machine learning model can support clinicians in the diagnostic process of benignancy versus malignancy for adnexal masses, providing a strong reduction of the definite surgery rate for benign lesions still warranting very high sensitivity.

Statistics from

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.