Sensitivity to noise and outliers
Medical Image Registration

The presence of noise and outliers in images can significantly degrade registration quality. In some cases, it may be worthwhile to pre-process images to reduce noise levels using denoising methods, or to correct certain acquisition-related artifacts.

The sensitivity of a registration method to noise and outliers is closely linked to the amount of information available to estimate the registration and the number of parameters to be estimated. The greater the number of degrees of freedom in the transformation, the more sensitive the parameter estimation is to noise and outliers. Conversely, in the case, for example, of...