Runlong He

Forget expensive labels: CoRe-DA leverages contrastive learning and self-training to achieve state-of-the-art surgical skill assessment across diverse surgical environments without requiring target domain annotations.

By disentangling the morphological features of lacunes and enlarged perivascular spaces, this model significantly boosts lacunae detection precision, outperforming previous state-of-the-art methods.

Ditch the complex finite-element models: NICP offers a lightweight, accurate, and engineering-friendly alternative for deformable liver registration in surgical AR.