Intraoperative 3D reconstruction from sparse arbitrarily posed real X-rays

Sascha Jecklin, Aidana Massalimova, Ruyi Zha, Lilian Calvet, Christoph J. Laux, Mazda Farshad, Philipp Fürnstahl · 2025

Read Intraoperative 3D reconstruction from sparse arbitrarily posed real X-rays by Sascha Jecklin, Aidana Massalimova, Ruyi Zha, Lilian Calvet, Christoph J. Laux, Mazda Farshad, Philipp Fürnstahl (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12712066.txt.

Description

Sascha Jecklin and co-authors rebuild 3D spine images from a few loose X-rays during surgery in two thousand twenty-five. Spine surgery is risky and leans on image guidance, yet full 3D scans blast radiation. Learning methods can infer the volume from sparse shots but hunger for labeled data and stumble on new bodies.

Their route adapts Gaussian splatting, an instance method that needs no pretraining. A style-transfer step first evens out the look of real operating-room X-rays, an anatomy-guided standardization. On cadaver data the volumes held together well. Surgeon judges rated the rebuilds fit for navigation. The per-patient fit makes the method portable across anatomies.

Catalog record

CREATORSascha Jecklin, Aidana Massalimova, Ruyi Zha, Lilian Calvet, Christoph J. Laux, Mazda Farshad, Philipp Fürnstahl
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE127 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12712066

Browse the full library · About the Tower of Babel