In this work, we investigate image registration in a variational framework and focus on regularization generality solver efficiency. We first propose model combining the state-of-the-art sum of absolute differences (SAD) new arbitrary order total variation term. The main advantage is that preserves discontinuities resultant deformation while being robust to outlier noise. It however non-trivial...

Deformable image registration is one of the fundamental tasks in medical imaging. Classical algorithms usually require a high computational cost for iterative optimizations. Although deep-learning-based methods have been developed fast registration, it still challenging to obtain realistic continuous deformations from moving fixed with less topological folding problem. To address this, here we ...

Many image registration algorithms rely on the use of homologous control points on the two input image sets to be registered. In reality, the interactive identification of the control points on both images is tedious, difficult, and often a source of error. We propose a two-step algorithm to automatically identify homologous regions that are used as a priori information during the image registr...

Despite the availability of national and international guidelines, an accurate efficient, patient-specific, deformable image registration (DIR) validation methodology is not yet established, several groups have found incompatibility various digital phantoms with commercial systems. To evaluate quality computed tomography (CT) on-board cone-beam CT (CBCT) DIRs, a novel was developed tested on 10...

OBJECTIVE To increase the accuracy of beam targeting and improve the dose distributions in radiotherapy using a robust image registration algorithm based on control volumes. METHODS Control volume mapping and thin-plate spline deformable transformation were combined. The use of the control volumes increased the accuracy for the deformable registration. A bi-directional mapping method was also...

Purpose/Objective(s): Conventional deformable registration treats all image volume equally and the calculations are “brute-force” in nature. In reality, some regions can be mapped between the moving and fixed images with higher confidence than others. In this work we investigate a strategy of using a priori knowledge of the system to reduce the dimensionality of the deformable image registratio...

Medical image analysis technology, with image segmentation, image matching /registration, motion tracking and the measurement of anatomical and physiological parameters as the main research areas, has seen a tremendous amount of growth over the past decade. The work described in this chapter is concerned with the problem of automatically aligning 3D medical images. Image registration is one of ...

Deformable image registration is a fundamental task in medical image processing. Among its most important applications, one may cite: i) multi-modality fusion, where information acquired by di erent imaging devices or protocols is fused to facilitate diagnosis and treatment planning; ii) longitudinal studies, where the development of phenomenon is studied over time; and iii) population modeling...