Epistemic-aware Vision-Language Foundation Model for Fetal Ultrasound Interpretation

[Submitted on 14 Oct 2025 (v1), last revised 30 Jul 2026 (this version, v4)]

Authors:Xiao He, Huangxuan Zhao, Guojia Wan, Jiancheng Pan, Yanxing Liu, Yong Luo, Juhua Liu, Yongchao Xu, Wei Zhou, Dacheng Tao, Bo Du

View PDF HTML (experimental)

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.

Submission history

From: Xiao He [view email]
[v1] Tue, 14 Oct 2025 19:57:03 UTC (7,528 KB)
[v2] Thu, 23 Oct 2025 03:45:15 UTC (1 KB) (withdrawn)
[v3] Tue, 27 Jan 2026 04:30:00 UTC (8,159 KB)
[v4] Thu, 30 Jul 2026 21:06:25 UTC (8,283 KB)