Skip to main content

A new computer-aided diagnostic tool for non-invasive characterisation of malignant ovarian masses: results of a multicentre validation study

Abstract

Objectives

To prospectively assess an innovative computer-aided diagnostic technology that quantifies characteristic features of backscattered ultrasound and theoretically allows transvaginal sonography (TVS) to discriminate benign from malignant adnexal masses.

Methods

Women (n = 264) scheduled for surgical removal of at least one ovary in five centres were included. Preoperative three-dimensional (3D)-TVS was performed and the voxel data were analysed by the new technology. The findings at 3D-TVS, serum CA125 levels and the TVS-based diagnosis were compared with histology. Cancer was deemed present when invasive or borderline cancerous processes were observed histologically.

Results

Among 375 removed ovaries, 141 cancers (83 adenocarcinomas, 24 borderline, 16 cases of carcinomatosis, nine of metastases and nine others) and 234 non-cancerous ovaries (107 normal, 127 benign tumours) were histologically diagnosed. The new computer-aided technology correctly identified 138/141 malignant lesions and 206/234 non-malignant tissues (98% sensitivity, 88% specificity). There were no false-negative results among the 47 FIGO stage I/II ovarian lesions. Standard TVS and CA125 had sensitivities/specificities of 94%/66% and 89%/75%, respectively. Combining standard TVS and the new technology in parallel significantly improved TVS specificity from 66% to 92% (p < 0.0001).

Conclusions

Computer-aided quantification of backscattered ultrasound is a highly sensitive for the diagnosis of malignant ovarian masses.

This is a preview of subscription content, access via your institution.

Fig. 1a, b
Fig. 2

References

  1. Ferlay J, Bray F, Pisani P, Parkin D (2004) GLOBOCAN 2002: cancer incidence, mortality and prevalence worldwide. IARC Press, Lyon

    Google Scholar 

  2. Engel J, Eckel R, Schubert-Fritschle G et al (2002) Moderate progress for ovarian cancer in the last 20 years: prolongation of survival, but no improvement in the cure rate. Eur J Cancer 38:2435–2445

    Article  CAS  PubMed  Google Scholar 

  3. Tingulstad S, Skjeldestad FE, Hagen B (2003) The effect of centralization of primary surgery on survival in ovarian cancer patients. Obstet Gynecol 102:499–505

    Article  PubMed  Google Scholar 

  4. Myers ER, Bastian LA, Havrilesky LJ et al (2006) Management of adnexal mass. Evid Rep Technol Assess (Full Rep) 130:1–145

    Google Scholar 

  5. ACOG Committee on Gynecologic Practice (2003) The role of the generalist obstetrician-gynecologist in the early detection of ovarian cancer. Int J Gynaecol Obstet 80:235–238

    Article  Google Scholar 

  6. Fenchel S, Grab D, Nuessle K et al (2002) Asymptomatic adnexal masses: correlation of FDG PET and histopathologic findings. Radiology 223:780–788

    Article  PubMed  Google Scholar 

  7. Grab D, Flock F, Stohr I et al (2000) Classification of asymptomatic adnexal masses by ultrasound, magnetic resonance imaging, and positron emission tomography. Gynecol Oncol 77:454–459

    Article  CAS  PubMed  Google Scholar 

  8. Huber S, Medl M, Baumann L, Czembirek H (2002) Value of ultrasound and magnetic resonance imaging in the preoperative evaluation of suspected ovarian masses. Anticancer Res 22:2501–2507

    PubMed  Google Scholar 

  9. Sohaib SA, Mills TD, Sahdev A et al (2005) The role of magnetic resonance imaging and ultrasound in patients with adnexal masses. Clin Radiol 60:340–348

    Article  CAS  PubMed  Google Scholar 

  10. Jacobs I, Oram D, Fairbanks J, Turner J, Frost C, Grudzinskas JG (1990) A risk of malignancy index incorporating CA 125, ultrasound and menopausal status for the accurate preoperative diagnosis of ovarian cancer. Br J Obstet Gynaecol 97:922–929

    CAS  PubMed  Google Scholar 

  11. Mol BW, Boll D, De Kanter M et al (2001) Distinguishing the benign and malignant adnexal mass: an external validation of prognostic models. Gynecol Oncol 80:162–167

    Article  CAS  PubMed  Google Scholar 

  12. Tailor A, Jurkovic D, Bourne TH, Collins WP, Campbell S (1999) Sonographic prediction of malignancy in adnexal masses using an artificial neural network. Br J Obstet Gynaecol 106:21–30

    CAS  PubMed  Google Scholar 

  13. Timmerman D, Verrelst H, Bourne TH et al (1999) Artificial neural network models for the preoperative discrimination between malignant and benign adnexal masses. Ultrasound Obstet Gynecol 13:17–25

    Article  CAS  PubMed  Google Scholar 

  14. Tingulstad S, Hagen B, Skjeldestad FE et al (1996) Evaluation of a risk of malignancy index based on serum CA125, ultrasound findings and menopausal status in the pre-operative diagnosis of pelvic masses. Br J Obstet Gynaecol 103:826–831

    CAS  PubMed  Google Scholar 

  15. Braeckman J, Autier P, Garbar C et al (2008) Computer-aided ultrasonography (HistoScanning): a novel technology for locating and characterizing prostate cancer. BJU Int 101:293–298

    Article  PubMed  Google Scholar 

  16. Braeckman J, Autier P, Soviany C et al (2008) The accuracy of transrectal ultrasonography supplemented with computer-aided ultrasonography for detecting small prostate cancers. BJU Int 102:1561–1565

    Article  Google Scholar 

  17. DePriest PD, Shenson D, Fried A et al (1993) A morphology index based on sonographic findings in ovarian cancer. Gynecol Oncol 51:7–11

    Article  CAS  PubMed  Google Scholar 

  18. DePriest PD, Varner E, Powell J et al (1994) The efficacy of a sonographic morphology index in identifying ovarian cancer: a multi-institutional investigation. Gynecol Oncol 55:174–178

    Article  CAS  PubMed  Google Scholar 

  19. Ferrazzi E, Zanetta G, Dordoni D, Berlanda N, Mezzopane R, Lissoni AA (1997) Transvaginal ultrasonographic characterization of ovarian masses: comparison of five scoring systems in a multicenter study. Ultrasound Obstet Gynecol 10:192–197

    Article  CAS  PubMed  Google Scholar 

  20. Lerner JP, Timor-Tritsch IE, Federman A, Abramovich G (1994) Transvaginal ultrasonographic characterization of ovarian masses with an improved, weighted scoring system. Am J Obstet Gynecol 170:81–85

    CAS  PubMed  Google Scholar 

  21. Sassone AM, Timor-Tritsch IE, Artner A, Westhoff C, Warren WB (1991) Transvaginal sonographic characterization of ovarian disease: evaluation of a new scoring system to predict ovarian malignancy. Obstet Gynecol 78:70–76

    CAS  PubMed  Google Scholar 

  22. Alcazar JL, Ruiz-Perez ML, Errasti T (1996) Transvaginal color Doppler sonography in adnexal masses: which parameter performs best? Ultrasound Obstet Gynecol 8:114–119

    Article  CAS  PubMed  Google Scholar 

  23. Valentin L (1999) Prospective cross-validation of Doppler ultrasound examination and gray-scale ultrasound imaging for discrimination of benign and malignant pelvic masses. Ultrasound Obstet Gynecol 14:273–283

    Article  CAS  PubMed  Google Scholar 

  24. Granberg S, Wikland M, Jansson I (1989) Macroscopic characterization of ovarian tumors and the relation to the histological diagnosis: criteria to be used for ultrasound evaluation. Gynecol Oncol 35:139–144

    Article  CAS  PubMed  Google Scholar 

  25. Franchi M, Beretta P, Ghezzi F, Zanaboni F, Goddi A, Salvatore S (1995) Diagnosis of pelvic masses with transabdominal color Doppler, CA 125 and ultrasonography. Acta Obstet Gynecol Scand 74:734–739

    Article  CAS  PubMed  Google Scholar 

  26. Guerriero S, Alcazar JL, Coccia ME et al (2002) Complex pelvic mass as a target of evaluation of vessel distribution by color Doppler sonography for the diagnosis of adnexal malignancies: results of a multicenter European study. J Ultrasound Med 21:1105–1111

    PubMed  Google Scholar 

  27. Menon U, Talaat A, Rosenthal AN et al (2000) Performance of ultrasound as a second line test to serum CA125 in ovarian cancer screening. BJOG 107:165–169

    Article  CAS  PubMed  Google Scholar 

  28. Schelling M, Braun M, Kuhn W et al (2000) Combined transvaginal B-mode and color Doppler sonography for differential diagnosis of ovarian tumors: results of a multivariate logistic regression analysis. Gynecol Oncol 77:78–86

    Article  CAS  PubMed  Google Scholar 

  29. Bruning J, Becker R, Entezami M et al (1997) Knowledge-based system ADNEXPERT to assist the sonographic diagnosis of adnexal tumors. Methods Inf Med 36:201–206

    CAS  PubMed  Google Scholar 

  30. Biagiotti R, Desii C, Vanzi E, Gacci G (1999) Predicting ovarian malignancy: application of artificial neural networks to transvaginal and color Doppler flow US. Radiology 210:399–403

    CAS  PubMed  Google Scholar 

  31. Krivanek A, Sonka M (1998) Ovarian ultrasound image analysis: follicle segmentation. IEEE Trans Med Imaging 17:935–944

    Article  CAS  PubMed  Google Scholar 

  32. Muzzolini R, Yang YH, Pierson R (1993) Multiresolution texture segmentation with application to diagnostic ultrasound images. IEEE Trans Med Imaging 12:108–123

    Article  CAS  PubMed  Google Scholar 

  33. Sarty GE, Liang W, Sonka M, Pierson RA (1998) Semiautomated segmentation of ovarian follicular ultrasound images using a knowledge-based algorithm. Ultrasound Med Biol 24:27–42

    Article  CAS  PubMed  Google Scholar 

  34. Zimmer Y, Tepper R, Akselrod S (2003) An automatic approach for morphological analysis and malignancy evaluation of ovarian masses using B-scans. Ultrasound Med Biol 29:1561–1570

    Article  PubMed  Google Scholar 

  35. Bazot M, Malzy P, Cortez A, Roseau G, Amouyal P, Darai E (2007) Accuracy of transvaginal sonography and rectal endoscopic sonography in the diagnosis of deep infiltrating endometriosis. Ultrasound Obstet Gynecol 30:994–1001

    Article  CAS  PubMed  Google Scholar 

  36. Bronshtein M, Yoffe N, Brandes JM, Blumenfeld Z (1991) Hair as a sonographic marker of ovarian teratomas: improved identification using transvaginal sonography and simulation model. J Clin Ultrasound 19:351–355

    Article  CAS  PubMed  Google Scholar 

Download references

Acknowledgements

The following investigators are members of the Ovarian HistoScanning Clinical Study Group:

B Lauratet B, JP Lefranc, PA Grenier: La Pitié—Salpêtrière Hospital, AP—HP, UPMC, Paris, France

K Schedvins K: Karolinska Hospital, Stockholm, Sweden

R di Pace R, D Franchi, M Bellomi, A Maggioni: European Institute of Oncology, Milan, Italy

R Mashiach, I Meizner: Rabin Medical Centre, Petah Tikva, Israel

A Schneider, J Lange: Hospital La Charité, Berlin, Germany

AS Absil, M Solnick, P Hennebert, AR Grivegnée: Jules Bordet Institute, Brussels, Belgium

R Nir, C Soviany: Advanced Medical Diagnostics, SA/NV, Drève Richelle, 161, 1410 Waterloo, Belgium

Author information

Authors and Affiliations

Authors

Consortia

Corresponding author

Correspondence to Olivier Lucidarme.

Additional information

Members of the Ovarian HistoScanning Clinical Study Group are listed in the Acknowledgements

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Lucidarme, O., Akakpo, JP., Granberg, S. et al. A new computer-aided diagnostic tool for non-invasive characterisation of malignant ovarian masses: results of a multicentre validation study. Eur Radiol 20, 1822–1830 (2010). https://doi.org/10.1007/s00330-010-1750-6

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00330-010-1750-6

Keywords

  • Ovarian cancer diagnosis
  • Ultrasound
  • Ovarian HistoScanning
  • Tissue characterisation