Artificial intelligence potential in ovarian endometriosis imaging: a comparative meta-analysis of transvaginal ultrasound-based AI models and human readers

Purpose Transvaginal ultrasound (TVUS) is widely used for diagnosing ovarian endometriosis but remains limited by significant operator dependency. This systematic review and meta-analysis evaluated the diagnostic accuracy of ultrasound-based artificial intelligence (AI) models for ovarian endometriosis and directly compared their performance with that of human readers.

We conducted a comprehensive search of five databases (PubMed, Embase, Scopus, Web of Science, and Cochrane Library) up to 5 December 2025 to identify studies reporting diagnostic metrics for AI models, compared with human readers, for detecting ovarian endometriomas. Pooled sensitivity, specificity, and area under the curve (AUC) were calculated using a bivariate random-effects model.

Seven studies with 2737 patients (6061 images) were included. AI models demonstrated a pooled sensitivity of 91% (confidence interval 81%-96%) and specificity of 95% (confidence interval 92%-96%). Human readers achieved a pooled sensitivity of 80% (95% confidence interval 65–90) and specificity of 85% (95% confidence interval 74–92). AI models significantly outperformed readers in specificity (p = 0.001) and overall diagnostic discrimination, with an AUC of 0.97 (95% confidence interval 0.95–0.98) compared with 0.84 (95% confidence interval 0.82–0.88) for human readers (p < 0.001), while sensitivity remained comparable (p = 0.10). Heterogeneity across included studies was minimal (0%).

AI algorithms show indications of promising but preliminary diagnostic performance relative to human readers in specificity and overall discrimination metrics. These results raise the possibility that AI might serve as a supplementary tool in sonographic evaluation of ovarian endometriosis, potentially contributing to more standardized interpretation and reduced false-positive diagnoses. Similar content being viewed by others Data availability No datasets were generated or analysed during the current study. Abbreviations - AUC: - Area under the curve - TVUS: - Transvaginal ultrasound - AI: - Artificial intelligence - RQS: - Radiomics quality score - QUADAS-C: - Quality assessment of diagnostic accuracy studies–comparative

Daniilidis A, Grigoriadis G, Dalakoura D, D’Alterio MN, Angioni S, Roman H. Transvaginal Ultrasound in the Diagnosis and Assessment of Endometriosis-An Overview: How, Why, and When. Diagnostics (Basel). 2022;12(12). doi: https://doi.org/10.3390/diagnostics12122912. Mick I, Freger SM, Marien M, Gholiof M, Leonardi M. Diagnostic Accuracy of Transvaginal Ultrasonography for Endometriosis According to the International Deep Endometriosis Analysis Consensus. O G Open. 2025;2(1):e061. doi: https://doi.org/10.1097/og9.0000000000000061. Moro F, Baima Poma C, Zannoni GF, Vidal Urbinati A, Pasciuto T, Ludovisi M, Moruzzi MC, Carinelli S, Franchi D, Scambia G, Testa AC. Imaging in gynecological disease (12): clinical and ultrasound features of invasive and non-invasive malignant serous ovarian tumors. Ultrasound Obstet Gynecol. 2017;50(6):788–99. doi: https://doi.org/10.1002/uog.17414. Moro F, Zannoni GF, Arciuolo D, Pasciuto T, Amoroso S, Mascilini F, Mainenti S, Scambia G, Testa AC. Imaging in gynecological disease (11): clinical and ultrasound features of mucinous ovarian tumors. Ultrasound Obstet Gynecol. 2017;50(2):261–70. doi: https://doi.org/10.1002/uog.17222. Di Legge A, Pollastri P, Mancari R, Ludovisi M, Mascilini F, Franchi D, Jurkovic D, Coccia ME, Timmerman D, Scambia G, Testa A, Valentin L. Clinical and ultrasound characteristics of surgically removed adnexal lesions with largest diameter ≤ 2.5 cm: a pictorial essay. Ultrasound Obstet Gynecol. 2017;50(5):648–56. doi: https://doi.org/10.1002/uog.17392. Giannini A, Massimello F, Caretto M, Cosimi G, Mannella P, Luisi S, Gadducci A, Simoncini T. Factors in malignant transformation of ovarian endometriosis: A narrative review. Gynecol Endocrinol. 2024;40(1):2409911. doi: https://doi.org/10.1080/09513590.2024.2409911. Daniilidis A, Grigoriadis G, Kalaitzopoulos DR, Angioni S, Kalkan Ü, Crestani A, Merlot B, Roman H. Surgical Management of Ovarian Endometrioma: Impact on Ovarian Reserve Parameters and Reproductive Outcomes. J Clin Med. 2023;12(16). doi: https://doi.org/10.3390/jcm12165324. Gałczyński K, Jóźwik M, Lewkowicz D, Semczuk-Sikora A, Semczuk A. Ovarian endometrioma - a possible finding in adolescent girls and young women: a mini-review. J Ovarian Res. 2019;12(1):104. doi: https://doi.org/10.1186/s13048-019-0582-5. Kanti FS, Gorak Savard R, Bergeron F, Zomahoun HTV, Netter A, Maheux-Lacroix S. Transvaginal ultrasound and magnetic resonance imaging in the diagnosis of endometrioma: a systematic review and meta-analysis of diagnostic test accuracy studies. J Obstet Gynaecol. 2024;44(1):2311664. doi: https://doi.org/10.1080/01443615.2024.2311664. Van den Bosch T, Van Schoubroeck D. Ultrasound diagnosis of endometriosis and adenomyosis: State of the art. Best Pract Res Clin Obstet Gynaecol. 2018;51:16–24. doi: https://doi.org/10.1016/j.bpobgyn.2018.01.013. Van Holsbeke C, Van Calster B, Guerriero S, Savelli L, Paladini D, Lissoni AA, Czekierdowski A, Fischerova D, Zhang J, Mestdagh G, Testa AC, Bourne T, Valentin L, Timmerman D. Endometriomas: their ultrasound characteristics. Ultrasound Obstet Gynecol. 2010;35(6):730–40. doi: https://doi.org/10.1002/uog.7668. Timmerman D, Planchamp F, Bourne T, Landolfo C, du Bois A, Chiva L, Cibula D, Concin N, Fischerova D, Froyman W, Gallardo Madueño G, Lemley B, Loft A, Mereu L, Morice P, Querleu D, Testa AC, Vergote I, Vandecaveye V, Scambia G, Fotopoulou C. ESGO/ISUOG/IOTA/ESGE Consensus Statement on pre-operative diagnosis of ovarian tumors. Int J Gynecol Cancer. 2021;31(7):961–82. doi: https://doi.org/10.1136/ijgc-2021-002565. Bruno M, Capanna G, Stanislao V, Ciuffreda R, Tabacco S, Fantasia I, Di Florio C, Stabile G, D’Alfonso A, Guido M, Ludovisi M. Ultrasound Features and Clinical Outcome of Patients with Ovarian Masses Diagnosed during Pregnancy: Experience of Single Gynecological Ultrasound Center. Diagnostics (Basel). 2023;13(20). doi: https://doi.org/10.3390/diagnostics13203247. Testa AC, Mascilini F, Quagliozzi L, Moro F, Bolomini G, Mirandola MT, Moruzzi MC, Scambia G, Fagotti A. Management of ovarian masses in pregnancy: patient selection for interventional treatment. Int J Gynecol Cancer. 2021;31(6):899–906. doi: https://doi.org/10.1136/ijgc-2020-001996. Keckstein J, Hoopmann M, Merz E, Grab D, Weichert J, Helmy-Bader S, Wölfler M, Bajka M, Mechsner S, Schäfer S, Krentel H, Hudelist G. Expert opinion on the use of transvaginal sonography for presurgical staging and classification of endometriosis. Arch Gynecol Obstet. 2023;307(1):5–19. doi: https://doi.org/10.1007/s00404-022-06766-z. Orlov S, Sladkevicius P, Rivano Eckerdal I, Jokubkiene L. Morphological changes of endometriomas during pregnancy and after delivery detected using ultrasound. Fertil Steril. 2025;123(2):211–20. doi: https://doi.org/10.1016/j.fertnstert.2024.08.355. Condous G, Gerges B, Thomassin-Naggara I, Becker C, Tomassetti C, Krentel H, van Herendael BJ, Malzoni M, Abrao MS, Saridogan E, Keckstein J, Hudelist G. Non-invasive imaging techniques for diagnosis of pelvic deep endometriosis and endometriosis classification systems: An International Consensus Statement. Eur J Radiol. 2024;176:111450. doi: https://doi.org/10.1016/j.ejrad.2024.111450. Savelli L, Fabbri F, Zannoni L, De Meis L, Di Donato N, Mollo F, Seracchioli R. Preoperative ultrasound diagnosis of deep endometriosis: importance of the examiner’s expertise and lesion size. Australas J Ultrasound Med. 2012;15(2):55–60. doi: https://doi.org/10.1002/j.2205-0140.2012.tb00227.x. Pascual MA, Vancraeynest L, Timmerman S, Ceusters J, Ledger A, Graupera B, Rodriguez I, Valero B, Landolfo C, Testa AC, Bourne T, Timmerman D, Valentin L, Van Calster B, Froyman W. Validation of ADNEX and IOTA two-step strategy and estimation of risk of complications during follow-up of adnexal masses in low-risk population. Ultrasound Obstet Gynecol. 2024;64(3):395–404. doi: https://doi.org/10.1002/uog.27642. Avery JC, Deslandes A, Freger SM, Leonardi M, Lo G, Carneiro G, Condous G, Hull ML. Noninvasive diagnostic imaging for endometriosis part 1: a systematic review of recent developments in ultrasound, combination imaging, and artificial intelligence. Fertil Steril. 2024;121(2):164–88. doi: https://doi.org/10.1016/j.fertnstert.2023.12.008. Mittal S, Tong A, Young S, Jha P. Artificial intelligence applications in endometriosis imaging. Abdom Radiol (NY). 2025;50(10):4901–13. doi: https://doi.org/10.1007/s00261-025-04897-w. Chiappa V, Bogani G, Interlenghi M, Salvatore C, Bertolina F, Sarpietro G, Signorelli M, Castiglioni I, Raspagliesi F. The Adoption of Radiomics and machine learning improves the diagnostic processes of women with Ovarian MAsses (the AROMA pilot study). J Ultrasound. 2021;24(4):429–37. doi: https://doi.org/10.1007/s40477-020-00503-5. Chiappa V, Bogani G, Interlenghi M, Vittori Antisari G, Salvatore C, Zanchi L, Ludovisi M, Leone Roberti Maggiore U, Calareso G, Haeusler E, Raspagliesi F, Castiglioni I. Using Radiomics and Machine Learning Applied to MRI to Predict Response to Neoadjuvant Chemotherapy in Locally Advanced Cervical Cancer. Diagnostics (Basel). 2023;13(19). doi: https://doi.org/10.3390/diagnostics13193139. Chiappa V, Interlenghi M, Salvatore C, Bertolina F, Bogani G, Ditto A, Martinelli F, Castiglioni I, Raspagliesi F. Using rADioMIcs and machine learning with ultrasonography for the differential diagnosis of myometRiAL tumors (the ADMIRAL pilot study). Radiomics and differential diagnosis of myometrial tumors. Gynecol Oncol. 2021;161(3):838–44. doi: https://doi.org/10.1016/j.ygyno.2021.04.004. Dungate B, Tucker DR, Goodwin E, Yong PJ. Assessing the Utility of artificial intelligence in endometriosis: Promises and pitfalls. Womens Health (Lond). 2024;20:17455057241248121. doi: https://doi.org/10.1177/17455057241248121. Deslandes A, Avery JC, Chen HT, Leonardi M, Knox S, Lo G, O’Hara R, Condous G, Hull ML. Intra- and interobserver agreement of proposed objective transvaginal ultrasound image-quality scoring system for use in artificial intelligence algorithm development. Ultrasound Obstet Gynecol. 2025;65(3):364–71. doi: https://doi.org/10.1002/uog.29178. Ștefan RA, Ștefan PA, Mihu CM, Csutak C, Melincovici CS, Crivii CB, Maluțan AM, Hîțu L, Lebovici A. Ultrasonography in the Differentiation of Endometriomas from Hemorrhagic Ovarian Cysts: The Role of Texture Analysis. J Pers Med. 2021;11(7). doi: https://doi.org/10.3390/jpm11070611. Hu P, Gao Y, Zhang Y, Sun K. Ultrasound image-based deep learning to differentiate tubal-ovarian abscess from ovarian endometriosis cyst. Front Physiol. 2023;14:1101810. doi: https://doi.org/10.3389/fphys.2023.1101810. Liu L, Cai W, Zhou C, Tian H, Wu B, Zhang J, Yue G, Hao Y. Ultrasound radiomics-based artificial intelligence model to assist in the differential diagnosis of ovarian endometrioma and ovarian dermoid cyst. Front Med (Lausanne). 2024;11:1362588. doi: https://doi.org/10.3389/fmed.2024.1362588. Miao K, Lv Q, Zhang L, Zhao N, Dong X. Discriminative diagnosis of ovarian endometriosis cysts and benign mucinous cystadenomas based on the ConvNeXt algorithm. Eur J Obstet Gynecol Reprod Biol. 2024;298:135–9. doi: https://doi.org/10.1016/j.ejogrb.2024.05.010. Li Y, Zhao B, Wen L, Huang R, Ni D. Multi-purposed diagnostic system for ovarian endometrioma using CNN and transformer networks in ultrasound. Biomedical Signal Processing and Control. 2024;91:105923. doi: https://doi.org/10.1016/j.bspc.2023.105923. Jung Y, Kim T, Han MR, Kim S, Kim G, Lee S, Choi YJ. Ovarian tumor diagnosis using deep convolutional neural networks and a denoising convolutional autoencoder. Sci Rep. 2022;12(1):17024. doi: https://doi.org/10.1038/s41598-022-20653-2. Wu M, Cui G, Lv S, Chen L, Tian Z, Yang M, Bai W. Deep convolutional neural networks for multiple histologic types of ovarian tumors classification in ultrasound images. Front Oncol. 2023;13:1154200. doi: https://doi.org/10.3389/fonc.2023.1154200. Rakić A, Đaković E, Milovanović Z, Ristić A, Nejković L, Đorđević A, Brakus J, Štulić J, Jurišić Ž, Jurišić A. Comparative Ultrasonographic Evaluation of Morphology and Vascularization in Endometriomas and Ovarian Mature Cystic Teratomas. J Clin Med. 2025;14(19). doi: https://doi.org/10.3390/jcm14196912. Ghosh S, Mann K, Nakrour N, Ray L, Movilla P, Harisinghani M, Kambadakone A, Shenoy-Bhangle A. Endometrioma: A Comprehensive Review of Its Varied Presentations, Complications, and Impact on Patient Management. Journal of Gastrointestinal and Abdominal Radiology. 2025. doi: https://doi.org/10.1055/s-0045-1809315. Sharma H, Drukker L, Chatelain P, Droste R, Papageorghiou AT, Noble JA. Knowledge representation and learning of operator clinical workflow from full-length routine fetal ultrasound scan videos. Med Image Anal. 2021;69:101973. doi: https://doi.org/10.1016/j.media.2021.101973.

We acknowledge the use of AI-based tools for grammar checking during the final stage of manuscript preparation. Author information Authors and Affiliations Contributions Alisa Mohebbi: Investigation, Formal analysis, Methodology, Validation, Visualization, Writing – original draft, Writing – review and editing; Mehrad Zare: Investigation, Formal analysis, Methodology, Validation, Writing – original draft, Writing – review; Afshin Mohammadi: Investigation, Validation, Visualization, Writing – original draft, Writing – review and editing; Gernot Hudelist: Methodology, Validation, Visualization, Writing – original draft, Writing – review and editing; Pawel Basta: Methodology, Validation, Visualization, Writing – original draft, Writing – review and editing; Balint Balogh: Investigation, Validation, Visualization, Writing – original draft, Writing – review and editing; U Rajendra Acharya: Methodology, Validation, Visualization, Writing – original draft, Writing – review and editing; Ali Abbasian Ardakani: Conceptualization, Methodology, Investigation, Validation, Supervision, Writing – original draft, Writing – review and editing; Sepideh Hatamikia: Methodology, Validation, Visualization, Writing – original draft, Writing – review and editing. Corresponding author Ethics declarations Competing interests The authors declare no competing interests. Additional information Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations. Supplementary Information Below is the link to the electronic supplementary material. Rights and permissions Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law. About this article Cite this article Mohebbi, A., Zare, M., Mohammadi, A. et al. Artificial intelligence potential in ovarian endometriosis imaging: a comparative meta-analysis of transvaginal ultrasound-based AI models and human readers. Abdom Radiol (2026). https://doi.org/10.1007/s00261-026-05570-6 Received: Revised: Accepted: Published: Version of record: DOI: https://doi.org/10.1007/s00261-026-05570-6