ZODIAC Cuts 95% Hausdorff Error Up to 22% on Hardest Spinal Ultrasound Cases

maier_ak · x · 2026-09-08

Tested on 2 phantoms and 6 volunteers (3 hard cases), ZODIAC matched supervised methods on clean data and cut 95% Hausdorff error by up to 22% on the hardest cases while reducing variability by 80%. Caveats: validated on three scanners only, F1 dropped 15%, and all volunteers had healthy spines.

Related event: ZODIAC Uses Zero-Shot Diffusion Priors to Reconstruct Spinal Anatomy Hidden in Intraoperative Ultrasound(5 posts)→

Original post →

More from Research

• EmbodiedSkills: A Unified Framework for Orchestrating VLA Robot Agents — Wei Wang · 2026-09-08
• One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation — OVHaiLLM · 2026-09-08
• Fluid Regularity Landscape Moving Fast: Tao Says Smooth NS Now Looks Feasible — basedjensen · 2026-09-08
• Anandkumar Team Uses PINNs to Find Stable Singularity in 3D Euler — basedjensen · 2026-09-08
• CIRPIN trains equivariant GNNs on circular permutations to fix protein structure search blind spots — bravo_abad · 2026-09-08
• JapanFold launches: 8 open biology AI models served free for Japanese researchers — DavidBennett__ · 2026-09-08

Research channel →