Non-Rigid Image Registration Evaluation Project (NIREP)
Image registration is important for many applications, including longitudinal
evaluations in individuals, comparison between individuals, creation of population
atlases, use of atlas-linked information in individual cases, delivery of
precision therapies, and many others. Non-rigid image registration is a more general approach than the widely used affine and rigid methods, but requires
more complex methodology and computational effort to implement. Evaluating
the performance of non-rigid image registration algorithms is a difficult task since point-wise correspondence from one image to another is not unique. That is there
is rarely if ever a ground truth correspondence map to judge the performance of
a registration algorithm.
We have started the Non-rigid Image Registration Evaluation Project (NIREP)
to develop software tools and provide shared image validation databases for rigorous
testing of non-rigid image registration algorithms. NIREP will extend the
scope of prior validation projects by developing evaluation criteria and metrics using
large image populations, using richly annotated image databases, using computer simulated data, and increasing the number and types of evaluation criteria.
The goal of this project is to establish, maintain, and endorse a standardized
set of relevant benchmarks and metrics for performance evaluation of nonrigid
image registration algorithms. Furthermore, these standards will be incorporated
into an exportable computer program to automatically evaluate the registration
accuracy of nonrigid image registration algorithms.
