Validation by Visual Inspection

One of the quickest validation methods to implement is simple visual inspection of the results. Although this may seem like an informal and potentially unreliable approach, Fitzpatrick et al. [1] have shown that visual inspection can detect 2-millimeter misregistrations of brain MRI images to brain CT images quite reliably. Misregistration can be accurately identified even when one of the images is a low-resolution PET image. Wong et al. [10] found that translations of 2 millimeters along the x- and y- axes and 3 mm along the z-axis could be detected reliably. In-plane rotations of 2° were reliably detectable, as were across-plane rotations less than 4°. Whereas learning to recognize misregistration of dissimilar images requires some experience and effort, recognition of errors in similar images is fairly trivial. In general, if the images look misregistered, they probably are misregistered, and visual inspection should be used as a routine ongoing validation approach at every opportunity.

0 0

Post a comment