aiqbench analysis
This research introduces FetalMind, a specialized vision-language model designed to address the unique challenges of fetal ultrasound interpretation through Salient Epistemic Disentanglement (SED). By integrating expert-curated bipartite graphs with reinforcement learning, the system effectively decouples view-disease associations and aligns inference logic with clinical obstetric workflows. The approach demonstrates significant performance gains on a newly curated dataset while maintaining efficiency across diverse gestational stages.
Epistemic-aware Vision-Language Foundation Model for Fetal Ultrasound Interpretation
arXiv:2510.12953v4 Announce Type: replace-cross Abstract: Recent medical vision-language models have shown promise on tasks such as VQA, report generation, and anomaly detection. However, most are adapted to structured adult imaging and underperform in fetal ultrasound, which poses challenges of multi-view image reasoning, numerous diseases, and image diversity. To bridge this gap, we introduce FetalMind, a medical AI system tailored to fetal ultrasound for both report generation and diagnosis. Guided by clinical workflow, we propose Salient Epistemic Disentanglement (SED), which injects an expert-curated bipartite graph into the model to decouple view-disease associations and to steer preference selection along clinically faithful steps via reinforcement learning. This design mitigates variability across diseases and heterogeneity across views, reducing learning bottlenecks while aligning the model's inference with obstetric practice. To train FetalMind at scale, we curate FetalSigma-1M dataset, the first large-scale fetal ultrasound report corpus, comprising 20K reports from twelve medical centers, addressing the scarcity of domain data. Extensive experiments show that FetalMind outperforms open- and closed-source baselines across all gestational stages, achieving +14% average gains and +61.2% higher accuracy on critical conditions while remaining efficient, stable, and scalable. Project Page: https://hexiao0275.github.io/FetalMind.
Abstract:Recent medical vision-language models have shown promise on tasks such as VQA, report generation, and anomaly detection. However, most are adapted to structured adult imaging and underperform in fetal ultrasound, which poses challenges of multi-view image reasoning, numerous diseases, and image diversity. To bridge this gap, we introduce FetalMind, a medical AI system tailored to fetal ultrasound for both report generation and diagnosis. Guided by clinical workflow, we propose Salient Epistemic Disentanglement (SED), which injects an expert-curated bipartite graph into the model to decouple view-disease associations and to steer preference selection along clinically faithful steps via reinforcement learning. This design mitigates variability across diseases and heterogeneity across views, reducing learning bottlenecks while aligning the model's inference with obstetric practice. To train FetalMind at scale, we curate FetalSigma-1M dataset, the first large-scale fetal ultrasound report corpus, comprising 20K reports from twelve medical centers, addressing the scarcity of domain data. Extensive experiments show that FetalMind outperforms open- and closed-source baselines across all gestational stages, achieving +14% average gains and +61.2% higher accuracy on critical conditions while remaining efficient, stable, and scalable. Project Page: this https URL.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Multimedia (cs.MM)
arXiv:2510.12953
arXiv:2510.12953 [cs.CV]
(or arXiv:2510.12953v4 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2510.12953 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.48550/arXiv.2510.12953 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 298 words
Related coverage
FADA: Accessible fetal ultrasound interpretation and annotation with a selectively distilled unified vision-language model
arXiv · Jun 10, 2026
Cross-Modal Ultrasound-MRI Learning for Fetal Brain Ventricular Volumetry and Abnormality Screening
arXiv · Aug 19, 2026
Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI
Latent Space · Sep 21, 2026
Biomedical Imaging's Real Bottleneck Is the Data, Not the Model
Databricks · Oct 8, 2026