{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Zhang J"],"funding":["the Natural Science Foundation of Chongqing","the open project of Chongqing Research Center for Prevention & Control of Maternal and Child Diseases and Public Health","the open project of Chongqing Research Center for Prevention & Control of Maternal and Child Diseases and Public Health"],"pagination":["3115"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC12830614"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["16(1)"],"pubmed_abstract":["To overcome inter-observer variability in conventional antral follicle count (AFC) assessment and AMH testing limitations, we developed an AI-powered framework using routine 2D ultrasound to standardize ovarian-reserve evaluation in assisted reproductive technology (ART). This multicenter retrospective study analyzed 395 women with infertility from two affiliated hospitals. The cohort was divided into training (n = 210), internal-test (n = 91), and external-test (n = 94) cohorts. We established three prediction models: radiomics model, 674 IBSI-compliant features; deep-learning model, ResNet50-based feature extraction; fusion model, hybrid approach combining both modalities. Model performance was validated against the manual AFC and serum AMH levels. Sequential classification categorized p"],"journal":["Scientific reports"],"pubmed_title":["Ultrasound radiomics and deep learning for predicting antral follicle count and anti-Mullerian hormone."],"pmcid":["PMC12830614"],"funding_grant_id":["CQFYSJ01002","CSTB2023NSCQ-BHX0100"],"pubmed_authors":["Rong Y","Ran S","Zhang J","Zhong C","Ni D","Liu S"],"additional_accession":[]},"is_claimable":false,"name":"Ultrasound radiomics and deep learning for predicting antral follicle count and anti-Mullerian hormone.","description":"To overcome inter-observer variability in conventional antral follicle count (AFC) assessment and AMH testing limitations, we developed an AI-powered framework using routine 2D ultrasound to standardize ovarian-reserve evaluation in assisted reproductive technology (ART). This multicenter retrospective study analyzed 395 women with infertility from two affiliated hospitals. The cohort was divided into training (n = 210), internal-test (n = 91), and external-test (n = 94) cohorts. We established three prediction models: radiomics model, 674 IBSI-compliant features; deep-learning model, ResNet50-based feature extraction; fusion model, hybrid approach combining both modalities. Model performance was validated against the manual AFC and serum AMH levels. Sequential classification categorized p","dates":{"release":"2025-01-01T00:00:00Z","publication":"2025 Dec","modification":"2026-06-06T20:10:13.173Z","creation":"2026-06-04T03:14:18.704Z"},"accession":"S-EPMC12830614","cross_references":{"pubmed":["41422297"],"doi":["10.1038/s41598-025-33010-w"]}}