A Statistics-Based Approach to Binary Image Registration with Uncertainty Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
| Hi-index | 0.00 |
Non-rigid image registration is used pervasively in medical image analysis for applications ranging from anatomical and functional studies to surgical assistance. Error in specific instances of a non-rigid registration process, however, is often not determined. In this paper, we propose a method to determine the magnitude and spatial location of error in non-rigid registration. The method is independent of the registration method and similarity measure used. We show that our algorithm is capable of detecting the distribution and magnitude of registration error in a simulated case. Using real data, our algorithm also is able to identify registration error that is consistent with error that can be seen visually.