VascuSR: Iterative Anatomy-Aware Diffusion for CT Super-Resolution
VascuSR super-resolves CT vessels with 3D anatomy guidance, cutting false vessel connections.
VascuSR is an iterative anatomy-aware diffusion method for CT super-resolution that injects an explicit 3D vascular representation into the decoder and updates that guidance from each reconstructed volume. On re-annotated MSD Task08 and HVM datasets it beats interpolation and learning-based baselines on Dice, clDice, connectivity, and mean centerline distance while keeping image quality comparable to its SR backbone. Versus learning-based baselines it reduces class-averaged connected-component counts by over 20% on both datasets and mean centerline distance by over 10% on MSD.
- Guides CT diffusion super-resolution with an explicit 3D vascular model.
- Iterative feedback refreshes anatomy guidance from each new volume.
- Improves Dice, clDice, connectivity, and centerline distance.
- Cuts connected-component counts by over 20% versus learning baselines.
From the original article
1 min read at huggingface.co
Generative super-resolution (SR) can recover sharp detail in computed tomography (CT) images from severely downsampled observations, but the missing high-frequency content is not uniquely determined by the low-resolution input. Consequently, visually plausible reconstructions may contain anatomically unsupported vascular detail, such as missing, spurious, or incorrectly connected vessels.
By Hairong Ni, Jiahe Huang, Minghao Guo · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.