Abstract
Many biomedical applications require accurate non-rigid image registration that can cope with complex deformations. However, popular diffeomorphic Demons registration algorithms suffer from difficulties for complex and serious distortions since they only use image greyscale and gradient information. To address these difficulties, a new diffeomorphic Demons registration algorithm is proposed using hierarchical neighbourhood spectral features namely HNSF Log-Demons in this paper. In view of three important properties of hierarchical neighbourhood spectral features based on line graph such as rotation invariance, invariance of linear changes of brightness, and robustness to noise, the hierarchical neighbourhood spectral features of a reference image and a moving image is first extracted and these novel spectral features are incorporated into the energy function of the diffeomorphic registration framework to improve the capability of capturing complex distortions. Secondly, the Nystr o ̈ m approximation based on random singular value decomposition is employed to effectively enhance the computational efficiency of HNSF Log-Demons. Finally, the hybrid multi-resolution strategy based on wavelet decomposition in the registration process is utilised to further improve the registration accuracy and efficiency. Experimental results show that the proposed HNSF Log-Demons not only effectively ensures the generation of smooth and reversible deformation field, but also achieves better performance than state-of-the-art algorithms.
Highlights
Medical image registration refers to the process of finding a plausible spatial transformation for moving images, so that it can reach the same spatial relationship with the corresponding anatomical points or at least diagnostic points on reference images [1, 2]
Registration experiments are conducted by using the free form deformation (FFD) based on B-spline, Demons, active Demons, improved active Demons, Log-Demons, spectral Demons and HNSF Log-Demons
The HNSF Log-Demons can effectively deal with the local non-rigid deformation and improve the registration accuracy, which benefits from the employment of hierarchical neighbourhood spectral features
Summary
Medical image registration refers to the process of finding a plausible spatial transformation for moving images, so that it can reach the same spatial relationship with the corresponding anatomical points or at least diagnostic points on reference images [1, 2]. According to different spatial transformations, medical image registration is generally categorised into two groups, i.e. rigid registration and non-rigid registration. The rigid registration only describes the motion that is limited to global rotations and translations while non-rigid registration usually includes very complex local and global elastic deformations. In the process of image acquisition, same or different patients are often influenced by other factors, such as lung movement and bladder filling, resulting in complex non-rigid deformation. The non-rigid registration often plays an important role in the medical clinical applications such as adaptive radiotherapy, image-guided surgery, disease diagnosis, pathological change tracking and treatment evaluation etc. The non-rigid registration is still one of the most challenge topics in medical image analysis [3]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
