{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T18:55:18Z","timestamp":1788375318294,"version":"build-2803163510"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T00:00:00Z","timestamp":1780704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"vor","delay-in-days":73,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Endometrial health is a key determinant of female fertility and successful pregnancy outcomes, making the accurate diagnosis of endometrial lesions essential for the success of assisted reproductive technology. While hysteroscopy remains the gold standard for uterine cavity evaluation, interpretation can vary based on clinical expertise. To address this, we developed a deep learning-based clinical decision support system to classify hysteroscopic images from high-resolution (4\u00a0K) videos into three categories: normal endometrium, endometrial polyps, and endometritis. Endometritis cases were classified based on hysteroscopic features suggestive of inflammation; no histopathological confirmation was obtained. Utilizing a dataset of 1500 expert-annotated images from 200 clinical videos, we applied transfer learning across four architectures: VGG-16, VGG-19, DenseNet-121, and EfficientNet-B0. Our results show that the models achieved classification accuracies between 85 and 89%, with DenseNet-121 demonstrating superior performance, specifically achieving a sensitivity of 93% and an AUC of 98.8% for polyp detection, alongside a precision of 90% for endometritis. Furthermore, Grad-CAM visualization confirmed that the networks focused on clinically relevant morphological features, enhancing model interpretability. These findings suggest that deep learning may serve as a supportive tool to assist clinicians in hysteroscopic analysis, pending validation on external datasets and with pathologically confirmed labels.<\/jats:p>","DOI":"10.1038\/s41598-026-57032-0","type":"journal-article","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T14:45:29Z","timestamp":1780757129000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Deep learning-based automated classification of endometrial lesions in IVF patients using hysteroscopic images"],"prefix":"10.1038","volume":"16","author":[{"given":"Marah","family":"Barakat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rasha","family":"Massoud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marwan","family":"Alhalabi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,6]]},"reference":[{"key":"57032_CR1","doi-asserted-by":"publisher","first-page":"223","DOI":"10.4103\/fsr.fsr_45_20","volume":"7","author":"T Goel","year":"2020","unstructured":"Goel, T., Malik, S. & Talwar, S. Uterine cavity assessment prior to IVF: comparison of 2D, 3D ultrasound, and hysteroscopy. Fertility Sci. Res. 7, 223 (2020).","journal-title":"Fertility Sci. Res."},{"key":"57032_CR2","first-page":"8895","volume":"27","author":"CC Vaduva","year":"2023","unstructured":"Vaduva, C. C. et al. The association between endometrial polyps, chronic endometritis, and IVF outcomes. Eur. Rev. Med. Pharmacol. Sci. 27, 8895\u20138904 (2023).","journal-title":"Eur. Rev. Med. Pharmacol. Sci."},{"key":"57032_CR3","doi-asserted-by":"publisher","first-page":"2834","DOI":"10.3390\/ijms25052834","volume":"25","author":"V Lacconi","year":"2024","unstructured":"Lacconi, V. et al. When the Embryo meets the endometrium: Identifying the features required for successful embryo implantation. Int. J. Mol. Sci. 25, 2834 (2024).","journal-title":"Int. J. Mol. Sci."},{"key":"57032_CR4","first-page":"538","volume":"26","author":"N Singh","year":"2022","unstructured":"Singh, N. & Sethi, A. Endometritis\u2014diagnosis, treatment and its impact on fertility\u2014a scoping review. JBRA Assist. Reprod. 26, 538\u2013546 (2022).","journal-title":"JBRA Assist. Reprod."},{"key":"57032_CR5","doi-asserted-by":"publisher","first-page":"102182","DOI":"10.1016\/j.jogoh.2021.102182","volume":"50","author":"O Tsonis","year":"2021","unstructured":"Tsonis, O., Gkrozou, F., Dimitriou, E. & Paschopoulos, M. Hysteroscopic detection of chronic endometritis: Evaluating proposed hysteroscopic features suggestive of chronic endometritis. J. Gynecol. Obstet. Hum. Reprod. 50, 102182 (2021).","journal-title":"J. Gynecol. Obstet. Hum. Reprod."},{"key":"57032_CR6","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1016\/j.fertnstert.2019.03.004","volume":"112","author":"E Cicinelli","year":"2019","unstructured":"Cicinelli, E. et al. Unified diagnostic criteria for chronic endometritis at fluid hysteroscopy: proposal and reliability evaluation through an international randomized-controlled observer study. Fertil. Steril. 112, 162\u2013173e2 (2019).","journal-title":"Fertil. Steril."},{"key":"57032_CR7","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1111\/j.1447-0756.2003.00163.x","volume":"30","author":"TA Shokeir","year":"2004","unstructured":"Shokeir, T. A., Shalan, H. M. & El-Shafei, M. M. Significance of endometrial polyps detected hysteroscopically in eumenorrheic infertile women. J. Obstet. Gynecol. Res. 30, 84\u201389 (2004).","journal-title":"J. Obstet. Gynecol. Res."},{"key":"57032_CR8","doi-asserted-by":"crossref","unstructured":"Fang, J. et al. Is it necessary to perform a diagnostic hysteroscopy before the first embryo transfer?\u2014A retrospective study. Front Med. (Lausanne) 12, (2025).","DOI":"10.3389\/fmed.2025.1690944"},{"key":"57032_CR9","doi-asserted-by":"publisher","first-page":"1409","DOI":"10.3390\/diagnostics13081409","volume":"13","author":"A Zhao","year":"2023","unstructured":"Zhao, A. et al. Automated detection of endometrial polyps from hysteroscopic videos using deep learning. Diagnostics 13, 1409 (2023).","journal-title":"Diagnostics"},{"key":"57032_CR10","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1196\/annals.1310.020","volume":"1020","author":"JF Mccarthy","year":"2004","unstructured":"Mccarthy, J. F. et al. Applications of machine learning and high-dimensional visualization in cancer detection, diagnosis, and management. Ann. N Y Acad. Sci. 1020, 239\u2013262 (2004).","journal-title":"Ann. N Y Acad. Sci."},{"key":"57032_CR11","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015).","journal-title":"Nature"},{"key":"57032_CR12","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In IEEE International Conference on Computer Vision (ICCV) 1026\u20131034 (IEEE, 2015). 1026\u20131034 (IEEE, 2015). (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.123","DOI":"10.1109\/ICCV.2015.123"},{"key":"57032_CR13","doi-asserted-by":"publisher","first-page":"1033","DOI":"10.32604\/cmc.2021.013952","volume":"67","author":"S Yamin Siddiqui","year":"2021","unstructured":"Yamin Siddiqui, S. et al. Intelligent breast cancer prediction empowered with fusion and deep learning. Computers Mater. Continua. 67, 1033\u20131049 (2021).","journal-title":"Computers Mater. Continua"},{"key":"57032_CR14","doi-asserted-by":"publisher","first-page":"e0248526","DOI":"10.1371\/journal.pone.0248526","volume":"16","author":"Y Takahashi","year":"2021","unstructured":"Takahashi, Y. et al. Automated system for diagnosing endometrial cancer by adopting deep-learning technology in hysteroscopy. PLoS One. 16, e0248526 (2021).","journal-title":"PLoS One"},{"key":"57032_CR15","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/s12967-020-02660-x","volume":"19","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y. et al. Deep learning model for classifying endometrial lesions. J. Transl Med. 19, 10 (2021).","journal-title":"J. Transl Med."},{"key":"57032_CR16","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.3390\/cancers16071315","volume":"16","author":"D Raimondo","year":"2024","unstructured":"Raimondo, D. et al. Detection and classification of hysteroscopic images using deep learning. Cancers (Basel). 16, 1315 (2024).","journal-title":"Cancers (Basel)"},{"key":"57032_CR17","doi-asserted-by":"publisher","first-page":"185","DOI":"10.5653\/cerm.2016.43.4.185","volume":"43","author":"HJ Park","year":"2016","unstructured":"Park, H. J., Kim, Y. S., Yoon, T. K. & Lee, W. S. Chronic endometritis and infertility. Clin. Exp. Reprod. Med. 43, 185 (2016).","journal-title":"Clin. Exp. Reprod. Med."},{"key":"57032_CR18","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1016\/j.fertnstert.2018.12.007","volume":"111","author":"D Song","year":"2019","unstructured":"Song, D. et al. Correlation between hysteroscopy findings and chronic endometritis. Fertil. Steril. 111, 772\u2013779 (2019).","journal-title":"Fertil. Steril."},{"key":"57032_CR19","doi-asserted-by":"publisher","first-page":"1729","DOI":"10.1007\/s00464-019-06958-w","volume":"34","author":"M Dunstan","year":"2020","unstructured":"Dunstan, M. et al. Is 3D faster and safer than 4K laparoscopic cholecystectomy? A randomised-controlled trial. Surg. Endosc. 34, 1729\u20131735 (2020).","journal-title":"Surg. Endosc"},{"key":"57032_CR20","doi-asserted-by":"publisher","first-page":"101743","DOI":"10.1016\/j.artmed.2019.101743","volume":"101","author":"M Talo","year":"2019","unstructured":"Talo, M. Automated classification of histopathology images using transfer learning. Artif. Intell. Med. 101, 101743 (2019).","journal-title":"Artif. Intell. Med."},{"key":"57032_CR21","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O. et al. ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015).","journal-title":"Int. J. Comput. Vis."},{"key":"57032_CR22","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G. E. ImageNet classification with deep convolutional neural networks. Commun. ACM. 60, 84\u201390 (2017).","journal-title":"Commun. ACM"},{"key":"57032_CR23","unstructured":"Kadhem, A., Majeed, O. & Taima, A. DensNet121 and Improved hippopotamusoptimization algorithm to diagnosis thyroid nodules."},{"key":"57032_CR24","doi-asserted-by":"publisher","first-page":"489","DOI":"10.3390\/info15080489","volume":"15","author":"A Iqbal","year":"2024","unstructured":"Iqbal, A., Jaffar, M. A. & Jahangir, R. Enhancing brain tumour multi-classification using efficient-Net B0-based intelligent diagnosis for internet of medical things (IoMT) applications. Information 15, 489 (2024).","journal-title":"Information"},{"key":"57032_CR25","doi-asserted-by":"publisher","first-page":"012029","DOI":"10.1088\/1742-6596\/2273\/1\/012029","volume":"2273","author":"J Gupta","year":"2022","unstructured":"Gupta, J., Pathak, S. & Kumar, G. Deep learning (CNN) and transfer learning: A review. J. Phys. Conf. Ser. 2273, 012029 (2022).","journal-title":"J. Phys. Conf. Ser."},{"key":"57032_CR26","doi-asserted-by":"publisher","first-page":"4427","DOI":"10.3390\/s22124427","volume":"22","author":"F Zhu","year":"2022","unstructured":"Zhu, F., Liu, C., Yang, J. & Wang, S. An improved mobilenet network with wavelet energy and global average pooling for rotating machinery fault diagnosis. Sensors 22, 4427 (2022).","journal-title":"Sensors"},{"key":"57032_CR27","doi-asserted-by":"publisher","unstructured":"Park, S. & Kwak, N. Analysis on the dropout effect in convolutional neural networks. in 189\u2013204 (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_12","DOI":"10.1007\/978-3-319-54184-6_12"},{"key":"57032_CR28","doi-asserted-by":"publisher","first-page":"1070","DOI":"10.3390\/bioengineering10091070","volume":"10","author":"H Zhang","year":"2023","unstructured":"Zhang, H. & Ogasawara, K. Grad-CAM-Based explainable artificial intelligence related to medical text processing. Bioengineering 10, 1070 (2023).","journal-title":"Bioengineering"},{"key":"57032_CR29","doi-asserted-by":"publisher","first-page":"154172","DOI":"10.1109\/ACCESS.2025.3603272","volume":"13","author":"HC Yoon","year":"2025","unstructured":"Yoon, H. C. & Lin, L. P. Brain tumor classification in MRI: insights from LIME and Grad-CAM explainable AI techniques. IEEE Access. 13, 154172\u2013154202 (2025).","journal-title":"IEEE Access."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-57032-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-57032-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-57032-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:25:47Z","timestamp":1787012747000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-57032-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,6]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["57032"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-57032-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-9152635\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,6]]},"assertion":[{"value":"17 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Ethical approval for this study was granted by the Ethical Committee of Damascus University\u2019s Faculty of Mechanical and Electrical Engineering, Syria, under serial number (FMEE-051124-346). The study was conducted in accordance with the ethical standards of the Declaration of Helsinki. All participants provided informed consent to undergo the hysteroscopic procedure and for the use of the obtained images in this research, under the direct supervision of the responsible physician at the hospital.","order":2,"name":"Ethics","label":"Ethical approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":3,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"25853"}}