Image registration is the process of bringing images acquired at different times or with different modalities in to a common coordinate system. Registration is necessary in order to be able to compare or integrate the data obtained from different measurements.
Medical image registration (e.g. for data of the same patient taken at different points in time) often additionally involves elastic (or nonrigid) registration to cope with deformation of the subject (due to breathing, anatomical changes, etc.). Nonrigid registration of medical images can also be used to register a patient's data to an anatomical atlas, such as the Talairach atlas for neuroimaging.
Image registration is used for a number of radiotherapy-related processes, including
- multi-modality segmentation,
- image-guided radiation treatment (IGRT),
- image-guided dose tracking (IGDT), and
- adaptive radiation treatment (ART).
See the
Image Registration article for more information.
EditUsing Adaptive Parzen Window Optimization for Mutual Information-based Registration
The method of Adaptive Parzen Window Optimization can be applied readily to the problem of Maximization of Mutual Information (MMI) registration. This type of registration involves an optimization which is a functional of a probability density function (PDF), which is the type of problem that Adaptive Parzen Window Optimization can be applied to.
In the case of MMI, the parzen windowing is applied to the formation of the joint histogram: i.e. the optimization adjusts the gaussian window used in the formation of the joint histogram. When the gaussian window is wider, the resulting distribution has a higher entropy. As the window narrows, the entropy decreases.
TODO: Add formula for MMI when using parzen window
This page is a Draft, its content is not complete and might contain errors.