Biomedical Engineering Reference
In-Depth Information
processes and aging. Nonrigid registration algorithms will be reliable enough for
clinical applications and provide valuable tools for diagnosis and for monitoring
disease progression.
13.1.6
Combination of Registration and Segmentation
Good segmentation can be achieved by lining up images to an atlas using the
image registration algorithm. Labeled structures in the atlas can then be used
to split up the images into anatomical and pathological components for visual-
ization or quantification. For example, registration and segmentation of plaque
images may allow the detecting of much of more subtle changes.
13.1.7
Registration to Data Acquisition
Registration is beginning to be used to improve data acquisition. For example,
online registration can be used to dynamically adjust slice position in MR scans
to compensate prospectively for motion correction. Spectroscopic or perfusion
acquisitions can be defined to interrogate specific tissues of interest, delineated
in a previously acquired high resolution image, rather than a fixed region relative
to the scanner. Specific tissue regions could be followed as the patient moves
or is repositioned. These applications are likely to grow as algorithms become
faster and scanner computing power increases.
13.2
A Multiresolution Approach to Medical
Image Registration Using Binning
Technique
Medical image registration has been applied to the diagnosis of cardiac studies
and a variety neurological disorders including brain tumors. Image registration,
or alignment, is the process of aligning two images so that corresponding fea-
tures of the images can be easily related. Registration using different modalities
is widely used in many medical applications. In practice, the complementary
information acquired from the registration of multiple imaging modalities can
be used for medical diagnosis and treatment planning. In recent years many
registration algorithms for medical imaging have been designed. Typically an
