Application of a denoising Doppler algorithm in adnexal mass ultrasound: impact on color score assignment and perceived image quality

Abstract

Purpose

Vascularization assessment is crucial for the diagnosis of ovarian masses. However, its subjectivity often results in suboptimal interobserver agreement. This study evaluated the impact of the OvAi denoising algorithm on IOTA color score assignment and perceived image quality in adnexal mass ultrasound.

Materials and Methods

In this multicenter prospective study (May 2018–August 2022), color/power Doppler videos of 100 adnexal masses from 100 women were acquired in 2 outpatient clinics. Six experts, 5 moderately experienced, and 8 beginner examiners assessed IOTA color score and image quality before and after applying the denoising algorithm. Interobserver agreement regarding color score assignments was measured using Fleiss’ Kappa, and perceived image quality changes were tested via Chi-square.

Results

Interobserver agreement regarding color score assignment was fair across all observer groups (κ: 0.296–0.396) and remained unchanged post-denoising. In benign lesions, CS1 increased (+14.9%), while CS2–CS4 decreased. In malignant cases, CS1 and CS2 increased (+76.2% and +30.8%), with a smaller reduction in CS3 (–3.7%) and CS4 (–21.4%). The CS4 decrease was less marked in malignant than in benign lesions (–21.4% vs. –38.3%). A significant improvement in perceived image quality was observed in all observer groups (p < 0.05).

Conclusion

The OvAi algorithm improved perceived image quality without significantly impacting interobserver agreement. Continued development may enable more objective and automated color score assignments, potentially reducing interobserver variability and supporting diagnostic reliability.

Zusammenfassung

Ziel

Die Beurteilung der Vaskularisierung ist für die Diagnose von Ovarialtumoren von entscheidender Bedeutung. Ihre Subjektivität führt jedoch häufig zu einer suboptimalen Inter-Observer-Übereinstimmung. In dieser Studie wurde der Einfluss des OvAi-Rauschunterdrückungs-Algorithmus auf die IOTA-Farbwert-Zuordnung und die wahrgenommene Bildqualität bei der Ultraschalldiagnostik von Adnex-Befunden untersucht.

Material und Methoden

In dieser multizentrischen prospektiven Studie (Mai 2018–August 2022) wurden Farb-/Power-Doppler-Videos von 100 Adnex-Befunden von 100 Frauen in 2 Ambulanzen aufgenommen. Sechs Experten, 5 Untersucher mit mittlerer Erfahrung und 8 Anfänger beurteilten den IOTA-Farbwert und die Bildqualität vor und nach Anwendung des Rauschunterdrückungs-Algorithmus. Die Inter-Observer-Übereinstimmung bei der Farbwert-Zuordnung wurde mit Fleiss‘ Kappa gemessen; die wahrgenommenen Veränderungen der Bildqualität wurden mit dem Chi-Quadrat-Test untersucht.

Ergebnisse

Die Inter-Observer-Übereinstimmung hinsichtlich der Farbwert-Zuordnung war in allen Beobachtergruppen ausreichend (κ: 0,296–0,396) und blieb nach der Rauschunterdrückung unverändert. Bei benignen Läsionen stieg CS1 (+14,9%), während CS2–CS4 sanken. Bei malignen Fällen stiegen CS1 und CS2 (+76,2% und +30,8%), während CS3 (–3,7 %) und CS4 (–21,4 %) weniger stark sanken. Der CS4-Abfall war bei malignen Läsionen weniger ausgeprägt als bei benignen Läsionen (–21,4% gegenüber –38,3%). Bei allen Beobachtergruppen wurde eine signifikante Verbesserung der wahrgenommenen Bildqualität beobachtet (p<0,05).

Schlussfolgerung

Der OvAi-Algorithmus verbesserte die wahrgenommene Bildqualität, ohne die Inter-Observer-Übereinstimmung signifikant zu beeinträchtigen. Eine kontinuierliche Weiterentwicklung könnte eine objektivere und automatisierte Vergabe von Farbwerten ermöglichen, die Inter-Observer-Variabilität reduzieren und die diagnostische Reliabilität verbessern.

Keywords

sonography - ovarian tumors - vascularization - Doppler - denoising algorithm

Publication History

Received: 05 July 2025

Accepted after revision: 06 October 2025

Accepted Manuscript online:
06 October 2025

Article published online:
21 January 2026

• References

• 1 Alcázar JL, Guerriero S, Laparte C. et al. Contribution of power Doppler blood flow mapping to gray-scale ultrasound for predicting malignancy of adnexal masses in symptomatic and asymptomatic women. Eur J Obstet Gynecol Reprod Biol 2011; 155: 99-105
• 2 Valentin L. Prospective cross-validation of Doppler ultrasound examination and gray-scale ultrasound imaging for discrimination of benign and malignant pelvic masses. Ultrasound Obstet Gynecol 1999; 14: 273-283
• 3 Alcázar JL. Re: Intra- and interobserver reproducibility of assessment of Doppler ultrasound findings in adnexal masses. Ultrasound Obstet Gynecol 2013; 42: 4-5
• 4 Valentin L. Gray scale sonography, subjective evaluation of the color Doppler image and measurement of blood flow velocity for distinguishing benign and malignant tumors of suspected adnexal origin. Eur J Obstet Gynecol Reprod Biol 1997; 72: 63-72
• 5 Timmerman D, Valentin L, Bourne TH. et al. Terms, definitions and measurements to describe the sonographic features of adnexal tumors: a consensus opinion from the International Ovarian Tumor Analysis (IOTA) Group. Ultrasound Obstet Gynecol 2000; 16: 500-505
• 6 Timmerman D. The use of mathematical models to evaluate pelvic masses; can they beat an expert operator?. Best Pract Res Clin Obstet Gynaecol 2004; 18: 91-104
• 7 Viora E, Piovano E, Baima Poma C. et al. The ADNEX model to triage adnexal masses: An external validation study and comparison with the IOTA two-step strategy and subjective assessment by an experienced ultrasound operator. Eur J Obstet Gynecol Reprod Biol 2020; 247: 207-211
• 8 Zannoni L, Savelli L, Jokubkiene L. et al. Intra- and interobserver reproducibility of assessment of Doppler ultrasound findings in adnexal masses. Ultrasound Obstet Gynecol 2013; 42: 93-101
• 9 Sladkevicius P, Valentin L. Intra- and interobserver agreement when describing adnexal masses using the International Ovarian Tumor Analysis terms and definitions: A study on three dimensional ultrasound volumes. Ultrasound Obstet Gynecol 2013; 41: 318-327 PubMed
• 10 Xholli A, Londero AP, Cavalli E. et al. The Benefit of Transvaginal Elastography in Detecting Deep Endometriosis: A Feasibility Study. Ultraschall in Med 2024; 45 (01) 69-76
• 11 Mohd Sagheer SV, George SN. A review on medical image denoising algorithms. Biomed Signal Process Control 2020; 61: 102036
• 12 SynDiag s.r.l. OvAi website. Accessed September 15, 2025 at: https://ovai.syndiag.ai/
• 13 von Elm E, Altman DG, Egger M. et al. The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) Statement: Guidelines for Reporting Observational Studies. BMJ 2007; 335: 806-808
• 14 Lizzi FL, Feleppa EJ. Image processing and pre-processing for medical ultrasound. In: Proceedings of the 29th Applied Imagery Pattern Recognition Workshop. Washington, DC: IEEE; 2000: 187-192
• 15 Ibraheem NA, Hasan MM, Khan RZ. et al. Understanding color models: a review. ARPN Journal of science and technology 2012; 2 (03) 265-275
• 16 Fleiss JL. Measuring nominal scale agreement among many raters. Psychol Bull 1971; 76: 378-382 PubMed
• 17 Fleiss JL, Levin B, Paik MC. Statistical Methods for Rates and Proportions. In: . New York: Wiley; 1981: 212-236
• 18 Guerriero S, Saba L, Ajossa S. et al. Assessing the reproducibility of the IOTA simple ultrasound rules for classifying adnexal masses as benign or malignant using stored 3D volumes. Eur J Obstet Gynecol Reprod Biol 2013; 171: 157-160
• 19 Guerriero S, Alcázar JL, Pascual MA. et al. The diagnosis of ovarian cancer: Is color Doppler imaging reproducible and accurate in examiners with different degrees of experience?. J Women‘s Health 2011; 20: 273-277
• 20 Pineda L, Salcedo E, Vilhena C. et al. Interobserver agreement in assigning IOTA color score to adnexal masses using three-dimensional volumes or digital videoclips: potential implications for training. Ultrasound Obstet Gynecol 2014; 44: 361-364
• 21 Grab D, Merz E, Eichhorn KH. et al. Basic Gynecologic Ultrasound Examination (Level I): DEGUM, ÖGUM, and SGUM Recommendations. Ultraschall in Med 2023; 44 (02) 151-161
• 22 Sladkevicius P, Valentin L. Interobserver agreement in describing the ultrasound appearance of adnexal masses and in calculating the risk of malignancy using logistic regression models. Clin Cancer Res 2015; 21: 594-601
• 23 Sladkevicius P, Valentin L. Interobserver agreement in the results of Doppler examinations of extrauterine pelvic tumors. Ultrasound Obstet Gynecol 1995; 6: 91-96
• 24 Tekay A, Jouppila P. Intraobserver variation in transvaginal Doppler blood flow measurements in benign ovarian tumors. Ultrasound Obstet Gynecol 1997; 9: 120-124
• 25 Jokubkiene L, Sladkevicius P, Valentin L. Does three-dimensional power Doppler ultrasound help in discrimination between benign and malignant ovarian masses?. Ultrasound Obstet Gynecol 2007; 29: 215-225
• 26 Sladkevicius P, Jokubkiene L, Valentin L. Contribution of morphological assessment of the vessel tree by three-dimensional ultrasound to a correct diagnosis of malignancy in ovarian masses. Ultrasound Obstet Gynecol 2007; 30: 874-882
• 27 Alcázar JL, Cabrera C, Galván R. et al. Three-dimensional power Doppler vascular network assessment of adnexal masses: Intraobserver and interobserver agreement analysis. J Ultrasound Med 2008; 27: 997-1001
• 28 Massobrio R, Mariani LL, Conti D. et al. Ultrasonographic diagnosis of adnexal masses: interobserver agreement in the interpretation of videos, using IOTA terminology. Arch Gynecol Obstet 2024; 309: 211-218
• 29 Alcázar JL, Rodriguez D, Royo P. et al. Intraobserver and interobserver reproducibility of 3-dimensional power Doppler vascular indices in assessment of solid and cystic-solid adnexal masses. J Ultrasound Med 2008; 27: 1-6