Classification of Medical Images using Non-linear Distortion Models

Daniel Keysers, Christian Gollan, Hermann Ney

Abstract:

We propose the application of two-dimensional distortion models for comparisons of medical images in a distance-based classifier. We extend a simple zero-order distortion model by using local context within the compared image parts. Vertical and horizontal image gradients as well as small sub images are used as local context. Taking into account dependencies within the displacement field of the distortion by using a pseudo two-dimensional hidden Markov model with additional distortion possibilities further improves the error rate. Using the methods presented in this work, the previous best error rate of 8.0% on the used medical data could be considerably reduced by about one third to 5.3%.