A Non-rigid Registration Framework That Accommodates Resection and Retraction

Abstract

Traditional non-rigid registration algorithms are incapable of accurately registering intra-operative with pre-operative images whenever tissue has been resected or retracted. In this work we present methods for detecting and handling retraction and resection. The registration framework is based on the bijective Demons algorithm using an anisotropic diffusion smoother. Retraction is detected at areas of the deformation field with high internal strain and the estimated retraction boundary is integrated as a diffusion boundary in the smoother to allow discontinuities to develop across the resection boundary. Resection is detected by a level set method evolving in the space where image intensities disagree. The estimated resection is integrated into the smoother as a diffusion sink to restrict image forces originating inside the resection from being diffused to surrounding areas. In addition, the deformation field is continuous across the diffusion sink boundary which allow us to move the boundary of the diffusion sink without changing values in the deformation field (no interpolation or extrapolation is needed). We present preliminary results on both synthetic and clinical data which clearly shows the added value of explicitly modeling these processes in a registration framework.

Improving anatomical mapping of complexly deformed anatomy for external beam radiotherapy and brachytherapy dose accumulation in cervical cancer

“…4 Methods to account for missing tissue have been proposed in the literature. 24,25 However, these methods are designed to include excision, resection, and retraction, with a direct application for surgery. In our case, the tumor shrinks due to the death of cells within the tissue, therefore, the use of these methods is limited.…”

Registration of Images With Varying Topology Using Embedded Maps

“…Note that brain resections or the presence of neurosurgical instruments can also be regarded as topological changes in general. Several works are developed to register brain images with resections by matching subvolumes [27,28], landmarks [29] or segmentation surfaces [30]. In addition, the ExpectationMaximization (EM) framework has been used for a joint estimation of resection region and registration [31,32].…”

“…These works rely on local features, and in most cases, their registration results have limited dimensionality rather than a dense deformation field, due to the computational complexity of EM. The work by Risholm et al [29] uses anisotropic diffusion instead of Gaussian smoothing in a registration framework that generates a deformation field that is free of the impact from resections. In their work, the anisotropic diffusion is regulated by diffusion sinks, where it is permitted into the area (resection area) but not out.…”

Concurrent tumor segmentation and registration with uncertainty-based sparse non-uniform graphs

“…The resection area was detected by statistical learning on a training set based on the intensity values and deformed by interpolation (constant registration cost in the resection area). In the same clinical context, Risholm et al (2009) coupled the demons algorithm with level sets. They alternate segmentation of the resected area by evolving a level set based on the image gradient and intensities disagreements, with a demons based registration that accommodates the resection by only allowing displacement towards the area.…”