Abstract
Multimodal image registration is a difficult task, due to the significant intensity variations between the images. A common approach is to use sophisticated similarity measures, such as mutual information, that are robust to those intensity variations. However, these similarity measures are computationally expensive and, moreover, often fail to capture the geometry and the associated dynamics linked with the images. Another approach is the transformation of the images into a common space where modalities can be directly compared. Within this approach, we propose to register multimodal images by using diffusion maps to describe the geometric and spectral properties of the data. Through diffusion maps, the multimodal data is transformed into a new set of canonical coordinates that reflect its geometry uniformly across modalities, so that meaningful correspondences can be established between them. Images in this new representation can then be registered using a simple Euclidean distance as a similarity measure. Registration accuracy was evaluated on both real and simulated brain images with known ground-truth for both rigid and non-rigid registration. Results showed that the proposed approach achieved higher accuracy than the conventional approach using mutual information.
Highlights
Feature modeling, as well as dimensionality reduction for image representation is important in fields, such as image analysis and computer vision
We propose to use diffusion mappings [1] to obtain a unified representation of multimodal images corresponding to the same underlying object
We have described a multimodal registration framework that uses diffusion maps for the structural representation of the images to be registered
Summary
As well as dimensionality reduction for image representation is important in fields, such as image analysis and computer vision. When dealing with multimodal imaging, a main challenge is to obtain a unified representation of the heterogeneous image data, so that meaningful comparisons and effective combinations can be performed. We propose to apply diffusion maps [1] to represent heterogeneous images for multimodal medical image registration. The motivation for using diffusion maps comes from the fact that the resulting embedding captures the intrinsic geometry of the underlying manifold independently of the sampling density and image modality. The purpose of multimodal image registration is to identify the geometric transformation that maps the coordinate system of one modality into another. Multimodal images have significant variations in their intensities, which makes it difficult to capture their structural similarities, increasing the difficulty of achieving accurate registration. While a T1 magnetic resonance (MR) image shows better anatomical detail (Figure 1a), T2 MR highlights pathological changes better (Figure 1b)
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
