Deformable alignment method improves ultrasound and ct image matching
Deformable CT-US Registration via Anatomy-Aware Implicit Neural Representations
Computer Vision and Pattern Recognition
Summary
Ultrasound images taken during surgery need to be matched up correctly with pre-surgery CT scans to help doctors see soft tissues better. The authors developed a new method that not only uses a robot tracker to start the matching but also adjusts for the way soft tissues get squished during the procedure. They used a special math tool called an implicit neural representation that flexibly models these tissue changes while respecting harder tissues like bone. This approach made the matching more accurate than older methods, improving alignment by about 17%.
What this means in practice
- •For medical imaging developers: Integrate deformable alignment that accounts for tissue stiffness to improve accuracy of ultrasound-CT fusion during minimally invasive surgeries.
- •For robotic surgery teams: Use the method to refine intraoperative ultrasound positioning by adjusting for tissue deformation from probe contact in robot-assisted interventions.
Authors
Agnieszka Lach, Magdalena Wysocki, Feng Li, Mohammad Farid Azampour, Benjamin D. Killeen, Felix Ginzinger, Mathias Braun, Philipp Steininger, Heinz Deutschmann, Nassir Navab
Abstract
Slice-to-volume registration between ultrasound (US) and preoperative computed tomography (CT) imaging would enhance many minimally invasive interventions, for example by locating soft tissue structures intra-operatively that are discernible in CT. While optical tracking enables initial rigid registration, contact from the probe induces soft tissue deformations that inhibit accurate alignment. In this work, we introduce a deformable CT-ultrasound registration framework that incorporates anatomical priors derived from CT to improve registration under deformation. Rigid registration is first established using a robot-assisted optical tracking system, after which a deformable transformation is estimated using a sinusoidal implicit neural representation (SIREN) optimized per frame. Tissue stiffness is approximated from CT-based HU values and used as spatially varying regularization, suppressing deformation in rigid structures such as bone while allowing more flexibility in soft tissue. Two additional constraints capture the physics of probe contact: a contact-zone displacement prior that drives the displacement field to compress tissue below the probe face, and a fan-geometry regularization term based on beam direction and convex transducer field of view. Model parameters are optimized with a normalized gradient field (NGF). The proposed approach improves alignment over rigid initialisation by 17% and outperforms classical deformable baselines while maintaining near-zero topological folding.