{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T13:05:50Z","timestamp":1779714350444,"version":"3.53.1"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T00:00:00Z","timestamp":1779667200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Reprod. Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Endometriosis is a common gynecologic condition in which pelvic MRI plays an important role in diagnosis and preoperative assessment. AI-enabled automated uterus segmentation on pelvic MRI could support endometriosis care by enabling standardized volumetric measurements and quantitative imaging analyses. However, developing robust AI models for this task is challenging because endometriosis often distorts pelvic anatomy through adhesions, uterine displacement, and coexisting fibroids or adenomyosis. Although promptable medical vision foundation models, such as MedSAM-2, provide a promising framework for interactive segmentation, their zero-shot performance on endometriosis MRI remains limited.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop Endo-MedSAM, a uterus-focused adaptation of MedSAM-2 for pelvic MRI in endometriosis, and to systematically evaluate its segmentation performance across institutions and prompting strategies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We used a pelvic MRI dataset comprising 74 subjects and 3,449 T2-weighted slices from two institutions (D1, multicenter; D2, single-center). Endo-MedSAM was initialized with MedSAM-2 weights and fine-tuned by training the prompt encoder and mask decoder while unfreezing the final layers of the image encoder. Slice-wise predictions were then reconstructed into 3D volumes for volumetric evaluation. Performance was assessed using slice-level and 3D Dice scores and the 95th percentile Hausdorff distance (HD95).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Endo-MedSAM was evaluated in three configurations: training on the single-center D2 cohort and testing on the multicenter D1 cohort, training on D1 and testing on D2, and using a mixed D1\u2009+\u2009D2 split with 75% of patients for training and 25% for testing. Across these settings, Endo-MedSAM achieved mean 3D Dice scores of 0.81\u20130.88 with bounding-box prompts and 0.68\u20130.76 with 1-click and 2-click point prompts. Compared with zero-shot MedSAM-2, this represented absolute 3D Dice improvements of approximately 0.27\u20130.34 for bounding-box prompting. Endo-MedSAM also showed markedly better performance across all prompting modes, with the largest gains observed for bounding-box prompting.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Endo-MedSAM achieved robust uterus segmentation on endometriosis pelvic MRI, consistently outperforming zero-shot MedSAM-2 across both multicenter and single-center settings while supporting bounding-box and low-interaction point prompting. Clinically, this can enable faster and more reproducible uterus delineation, reduce manual contouring burden, standardize measurements across scanners and sites, and support downstream quantitative imaging workflows in endometriosis care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frph.2026.1790980","type":"journal-article","created":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T13:00:03Z","timestamp":1779714003000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Endo-MedSAM: a promptable vision foundation model adaptation for uterus segmentation on pelvic MRI in endometriosis"],"prefix":"10.3389","volume":"8","author":[{"given":"Rawan","family":"AlSaad","sequence":"first","affiliation":[{"name":"Weill Cornell Medicine-Qatar","place":["Doha, Qatar"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shima","family":"Albasha","sequence":"additional","affiliation":[{"name":"Weill Cornell Medicine-Qatar","place":["Doha, Qatar"]},{"name":"Division of Reproductive Medicine, Hamad Medical Corporation","place":["Doha, Qatar"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajat","family":"Thomas","sequence":"additional","affiliation":[{"name":"Weill Cornell Medicine-Qatar","place":["Doha, Qatar"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,25]]},"reference":[{"key":"B1","year":"2025"},{"key":"B2","doi-asserted-by":"publisher","first-page":"e0337074","DOI":"10.1371\/journal.pone.0335548","article-title":"Global, regional, and national burden of endometriosis among women of reproductive age, 1990-2021: insights from the global burden of disease study 2021","volume":"20","author":"Zhang","year":"2025","journal-title":"PLoS One"},{"key":"B3","doi-asserted-by":"publisher","first-page":"5927","DOI":"10.1097\/JS9.0000000000002647","article-title":"Global, regional, and national burden of endometriosis among women of childbearing age from 1990 to 2021: a cross-sectional analysis from the 2021 global burden of disease study","volume":"111","author":"Xu","year":"2025","journal-title":"Int J Surg"},{"key":"B4","doi-asserted-by":"publisher","first-page":"519","DOI":"10.1186\/s12905-025-04043-0","article-title":"Global, regional, and national burden and trends of endometriosis, 1990-2021: an analysis of the global burden of disease study 2021 and forecast to 2050","volume":"25","author":"Wang","year":"2025","journal-title":"BMC Womens Health"},{"key":"B5","doi-asserted-by":"publisher","first-page":"110610","DOI":"10.1016\/j.ejrad.2022.110610","article-title":"Endometriosis: a multimodal imaging review","volume":"158","author":"Quesada","year":"2023","journal-title":"Eur J Radiol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"43","DOI":"10.3390\/ai7020043","article-title":"Artificial intelligence in endometriosis imaging: a scoping review","volume":"7","author":"AlSaad","year":"2026","journal-title":"AI"},{"key":"B7","doi-asserted-by":"publisher","first-page":"7028","DOI":"10.1002\/mp.15268","article-title":"Fully automated multiorgan segmentation of female pelvic magnetic resonance images with coarse-to-fine convolutional neural network","volume":"48","author":"Zabihollahy","year":"2021","journal-title":"Med Phys"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1525","DOI":"10.3390\/diagnostics13091525","article-title":"An instance segmentation model based on deep learning for intelligent diagnosis of uterine myomas in MRI","volume":"13","author":"Pan","year":"2023","journal-title":"Diagnostics"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13244-022-01342-0","article-title":"Deep learning enables automated MRI-based estimation of uterine volume also in patients with uterine fibroids undergoing high-intensity focused ultrasound therapy","volume":"14","author":"Theis","year":"2023","journal-title":"Insights Imaging"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e14296","DOI":"10.1002\/acm2.14296","article-title":"Semi-supervised auto-segmentation method for pelvic organ-at-risk in magnetic resonance images based on deep-learning","volume":"25","author":"Li","year":"2024","journal-title":"J Appl Clin Med Phys"},{"key":"B11","doi-asserted-by":"publisher","first-page":"100230","DOI":"10.1016\/j.ibmed.2025.100230","article-title":"Deep learning based detection of endometriosis lesions in laparoscopic images with 5-fold cross-validation","volume":"11","author":"Zaidi","year":"2025","journal-title":"Intell Based Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"63","DOI":"10.3390\/biomedinformatics5040063","article-title":"Explainable deep learning for endometriosis classification in laparoscopic images","volume":"5","author":"Zhu","year":"2025","journal-title":"BioMedInformatics"},{"key":"B13","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1186\/s13036-024-00466-9","article-title":"Identification and verification of diagnostic biomarkers for deep infiltrating endometriosis based on machine learning algorithms","volume":"18","author":"Shi","year":"2024","journal-title":"J Biol Eng"},{"key":"B14","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1007\/s00261-025-04942-8","article-title":"Advancing endometriosis detection in daily practice: a deep learning-enhanced multi-sequence MRI analytical model","volume":"51","author":"Moassefi","year":"2025","journal-title":"Abdom Radiol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1254","DOI":"10.3390\/diagnostics15101254","article-title":"Object detection in laparoscopic surgery: a comparative study of deep learning models on a custom endometriosis dataset","volume":"15","author":"Bondarenko","year":"2025","journal-title":"Diagnostics"},{"key":"B16","author":"Ravi","year":"2024"},{"key":"B17","doi-asserted-by":"publisher","first-page":"102473","DOI":"10.1016\/j.compmedimag.2024.102473","article-title":"A review of the segment anything model (SAM) for medical image analysis: accomplishments and perspectives","volume":"119","author":"Ali","year":"2025","journal-title":"Comput Med Imaging Graph"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1109\/TMI.2025.3530097","article-title":"Learnable prompting SAM-induced knowledge distillation for semi-supervised medical image segmentation","volume":"44","author":"Huang","year":"2025","journal-title":"IEEE Trans Med Imaging"},{"key":"B19","doi-asserted-by":"publisher","first-page":"8954","DOI":"10.1109\/JBHI.2025.3540306","article-title":"MediViSTA: medical video segmentation via temporal fusion SAM adaptation for echocardiography","volume":"29","author":"Kim","year":"2025","journal-title":"IEEE J Biomed Health Inform"},{"key":"B20","doi-asserted-by":"publisher","first-page":"3909","DOI":"10.1109\/TMI.2025.3532084","article-title":"Stitching, fine-tuning, and re-training: a SAM-enabled framework for semi-supervised 3D medical image segmentation","volume":"44","author":"Li","year":"2025","journal-title":"IEEE Trans Med Imaging"},{"key":"B21","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1186\/s12880-024-01401-6","article-title":"Medical image analysis using improved SAM-Med2D: segmentation and classification perspectives","volume":"24","author":"Sun","year":"2024","journal-title":"BMC Med Imaging"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2161","DOI":"10.1007\/s11517-025-03310-4","article-title":"Integrating multi-scale information and diverse prompts in large model SAM-Med2D for accurate left ventricular ejection fraction estimation","volume":"63","author":"Wu","year":"2025","journal-title":"Med Biol Eng Comput"},{"key":"B23","author":"Zhu","year":"2024"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1292","DOI":"10.1038\/s41597-025-05623-3","article-title":"A multi-modal pelvic MRI dataset for deep learning-based pelvic organ segmentation in endometriosis","volume":"12","author":"Liang","year":"2025","journal-title":"Sci Data"},{"key":"B25","author":"Isensee","year":"2024"},{"key":"B26","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat Methods"}],"container-title":["Frontiers in Reproductive Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frph.2026.1790980\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,25]],"date-time":"2026-05-25T13:00:05Z","timestamp":1779714005000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frph.2026.1790980\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,25]]},"references-count":26,"alternative-id":["10.3389\/frph.2026.1790980"],"URL":"https:\/\/doi.org\/10.3389\/frph.2026.1790980","relation":{},"ISSN":["2673-3153"],"issn-type":[{"value":"2673-3153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,25]]},"article-number":"1790980"}}