🛰️ Daily AI Frontier
‹ back to 2026-08-29

Anatomy-Guided Foundation Model Adaptation with Within-Case Prototype Supervision for Standard Plane Detection in Fetal Ultrasound Blind Sweeps

Research Medical/Healthcare AI

Ranking

Overall 79
Content 95
Popularity 42

Observed public metrics from 1 member.

Representative image for Anatomy-Guided Foundation Model Adaptation with Within-Case Prototype Supervision for Standard Plane Detection in Fetal Ultrasound Blind Sweeps

Merged summary

TL;DR - AnatoProto adapts a frozen BiomedCLIP encoder to detect rare fetal abdominal standard-plane frames in ultrasound blind sweeps. It achieves 67.72 F1 on ACOUSLIC-AI, outperforming the strongest reported foundation-model baseline by 13.20 points.

  • Anatomy-weighted pooling uses nnU-Net abdominal-region probabilities to focus BiomedCLIP patch features on clinically relevant anatomy.
  • Within-case prototype supervision pulls frame embeddings toward the mean positive-frame embedding from the same sweep.
  • A frame-to-segment-to-case cascade and hybrid stability/boundary head reduce structurally implausible and boundary false positives.
  • Prototype supervision improves recall only when paired with anatomy-guided pooling, suggesting that accurate within-case prototypes are critical.

Sources (1)

Anatomy-Guided Foundation Model Adaptation with Within-Case Prototype Supervision for Standard Plane Detection in Fetal Ultrasound Blind Sweeps

arXiv cs.CV Yuzhe Zhao 2026-08-27 arXiv:2608.27051
Public signals Semantic Scholar citations 0 · Semantic Scholar influential citations 0
Providers: Hugging Face · N/A OpenAlex · N/A Publisher · N/A Semantic Scholar · Citations 0 · Influential citations 0 X · N/A Fetched 2026-09-22 14:29:41.511271 UTC

TL;DR - AnatoProto adapts a frozen BiomedCLIP encoder to detect rare fetal abdominal standard-plane frames in ultrasound blind sweeps. It achieves 67.72 F1 on ACOUSLIC-AI, outperforming the strongest reported foundation-model baseline by 13.20 points.

  • Anatomy-weighted pooling uses nnU-Net abdominal-region probabilities to focus BiomedCLIP patch features on clinically relevant anatomy.
  • Within-case prototype supervision pulls frame embeddings toward the mean positive-frame embedding from the same sweep.
  • A frame-to-segment-to-case cascade and hybrid stability/boundary head reduce structurally implausible and boundary false positives.
  • Prototype supervision improves recall only when paired with anatomy-guided pooling, suggesting that accurate within-case prototypes are critical.
item →