Fig. 1.

Traditional and proposed frameworks for image registration.{I_n} indicates a collection of images. In image registration, we seek a deformation ${\mathrm{\Gamma }}_n^{*}$ for each image I_n. The resulting deformations $\{{\mathrm{\Gamma }}_n^{*}\}$ are then used for other applications, such as segmentation or group analysis. The registration cost function typically contains multiple parameters, such as the tradeoff parameter λ and the template T. Changes in these parameters alter the deformations $\{{\mathrm{\Gamma }}_n^{*}\}$ and thus the outcomes of downstream applications. In our framework (b), we assume a training data set, which allows us to evaluate the quality of the registration as measured by the application performance (or cross-validation error metric) g_n for each training subject. This allows us to pick the best parameters that result in good registration as measured by {g_n}. Subsequent new subjects are registered using these learned parameters.