HNSF Log‐Demons: Diffeomorphic demons registration using hierarchical neighbourhood spectral features

Many biomedical applications require accurate non-rigid image registration that can cope with complex deformations. However, popular diffeomorphic Demons algorithms suffer from difficulties for and serious distortions since they only use greyscale gradient information. To address these difficulties, a new algorithm is proposed using hierarchical neighbourhood spectral features namely HNSF Log-Demons in this paper. In view of three important properties based on line graph such as rotation invariance, invariance linear changes brightness, robustness to noise, the reference moving first extracted novel are incorporated into energy function framework improve capability capturing distortions. Secondly, Nystr o ̈ m approximation random singular value decomposition employed effectively enhance computational efficiency Log-Demons. Finally, hybrid multi-resolution strategy wavelet process utilised further accuracy efficiency. Experimental results show not ensures generation smooth reversible deformation field, but also achieves better performance than state-of-the-art algorithms.