We propose a new voxel similarity measure which utilises local image structure and intensity information. Gaussian scale space derivatives provide the structural information. Each derivative is assigned an information channel of N-D normalised mutual information. We illustrate the behaviour of the measure for a simulated signal and 2D medical brain images and demonstrate its potential for non-rigid, inter-subject registration of 3D thorax MR images as a proof of concept. © Springer-Verlag Berlin Heidelberg 2004.
CITATION STYLE
Holden, M., Griffin, L. D., Saeed, N., & Hill, D. L. G. (2004). Multi-channel mutual information using scale space. In Lecture Notes in Computer Science (Vol. 3216, pp. 797–804). Springer Verlag. https://doi.org/10.1007/978-3-540-30135-6_97
Mendeley helps you to discover research relevant for your work.