Contour-Constrained Deformable Registration with Parameter Characterization for Head and Neck Surgical Guidance

2026-06-18

AI Summary

This study addresses the challenge of accurately localizing positive surgical margins in head and neck cancer resection, where tissue deformation and mucosal contraction after excision complicate intraoperative assessment. To overcome this, the authors propose a biomechanics-based deformable registration framework that integrates intraoperative 3D specimen meshes with wound cavity point clouds. The method innovatively incorporates boundary contour constraints to directly penalize the perpendicular distance error between corresponding boundaries, and combines Kelvinlet basis functions, fiducial markers, and strain energy regularization to achieve high-fidelity alignment. Validation on nine clinical cases demonstrates that the proposed approach reduces the mean target registration error by 49.41% compared to rigid registration, with particularly pronounced improvements in highly deformable regions such as the tongue.

Abstract

With 890,000 annual new cases globally, head and neck squamous cell carcinoma has one of the highest recurrence rates among solid malignancies. Although frozen section analysis is the standard of care for intraoperative margin assessment, accurately relocating detected positive margins on the resection bed remains challenging due to imprecise alignment between resected specimens and their resection bed, compounded by post-resection mucosal tissue shrinkage. We present a biomechanics-driven deformable registration framework that corrects post-resection tissue deformation to provide intraoperative guidance. Our approach registers 3D specimen meshes to intraoperative resection bed point clouds using a deformable registration approach based on regularized Kelvinlet basis functions. The registration matches surface point clouds, fiducial landmarks, and boundary contour constraints that directly penalize perpendicular distance-to-agreement between specimen and resection bed boundaries. Across nine specimens from skin, buccal mucosa, and tongue sites, the overall mean target registration error was $11.11 \pm 4.07$ mm using rigid registration, which decreased to $8.20 \pm 2.68$ mm (26.19\% reduction) using deformable registration without contour constraint. The proposed contour-constrained deformable registration further reduced the error to $5.62 \pm 2.28$ mm, a 49.41\% reduction relative to rigid registration. We observed the largest reduction in the most clinically challenging tongue specimens. We also performed a systematic two-stage parameter search to characterize the relative importance of surface alignment, fiducial correspondences, contour constraint, and strain energy regularization. This search revealed that contour weighting dominates registration accuracy for tissue types with large lateral deformation, while the algorithm operates over a broad range of parameter combinations.

Problem

• head and neck cancer
• intraoperative margin assessment
• tissue deformation
• positive margin relocation
• resection bed alignment

Innovation

• contour-constrained registration
• deformable registration
• Kelvinlet basis functions
• intraoperative guidance
• parameter characterization