A robust similarity measure for volumetric image registration with outliers
Image registration under challenging realistic conditions is a very important area of research. In this paper, we focus on algorithms that seek to densely align two volumetric images according to a global similarity measure. Despite intensive research in this area, there is still a need for similari...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Published: |
Elsevier
2016
|
| Subjects: | |
| Online Access: | https://eprints.nottingham.ac.uk/34219/ |
| _version_ | 1848794800993599488 |
|---|---|
| author | Snape, Patrick Pszczolkowski, Stefan Zafeiriou, Stefanos Tzimiropoulos, Georgios Ledig, Christian Rueckert, Daniel |
| author_facet | Snape, Patrick Pszczolkowski, Stefan Zafeiriou, Stefanos Tzimiropoulos, Georgios Ledig, Christian Rueckert, Daniel |
| author_sort | Snape, Patrick |
| building | Nottingham Research Data Repository |
| collection | Online Access |
| description | Image registration under challenging realistic conditions is a very important area of research. In this paper, we focus on algorithms that seek to densely align two volumetric images according to a global similarity measure. Despite intensive research in this area, there is still a need for similarity measures that are robust to outliers common to many different types of images. For example, medical image data is often corrupted by intensity inhomogeneities and may contain outliers in the form of pathologies. In this paper we propose a global similarity measure that is robust to both intensity inhomogeneities and outliers without requiring prior knowledge of the type of outliers. We combine the normalised gradients of images with the cosine function and show that it is theoretically robust against a very general class of outliers. Experimentally, we verify the robustness of our measures within two distinct algorithms. Firstly, we embed our similarity measures within a proof-of-concept extension of the Lucas–Kanade algorithm for volumetric data. Finally, we embed our measures within a popular non-rigid alignment framework based on free-form deformations and show it to be robust against both simulated tumours and intensity inhomogeneities. |
| first_indexed | 2025-11-14T19:21:57Z |
| format | Article |
| id | nottingham-34219 |
| institution | University of Nottingham Malaysia Campus |
| institution_category | Local University |
| last_indexed | 2025-11-14T19:21:57Z |
| publishDate | 2016 |
| publisher | Elsevier |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | nottingham-342192020-05-04T20:01:49Z https://eprints.nottingham.ac.uk/34219/ A robust similarity measure for volumetric image registration with outliers Snape, Patrick Pszczolkowski, Stefan Zafeiriou, Stefanos Tzimiropoulos, Georgios Ledig, Christian Rueckert, Daniel Image registration under challenging realistic conditions is a very important area of research. In this paper, we focus on algorithms that seek to densely align two volumetric images according to a global similarity measure. Despite intensive research in this area, there is still a need for similarity measures that are robust to outliers common to many different types of images. For example, medical image data is often corrupted by intensity inhomogeneities and may contain outliers in the form of pathologies. In this paper we propose a global similarity measure that is robust to both intensity inhomogeneities and outliers without requiring prior knowledge of the type of outliers. We combine the normalised gradients of images with the cosine function and show that it is theoretically robust against a very general class of outliers. Experimentally, we verify the robustness of our measures within two distinct algorithms. Firstly, we embed our similarity measures within a proof-of-concept extension of the Lucas–Kanade algorithm for volumetric data. Finally, we embed our measures within a popular non-rigid alignment framework based on free-form deformations and show it to be robust against both simulated tumours and intensity inhomogeneities. Elsevier 2016-08 Article PeerReviewed Snape, Patrick, Pszczolkowski, Stefan, Zafeiriou, Stefanos, Tzimiropoulos, Georgios, Ledig, Christian and Rueckert, Daniel (2016) A robust similarity measure for volumetric image registration with outliers. Image and Vision Computing, 52 . pp. 97-113. ISSN 1872-8138 Image registration; Lucas–Kanade; Normalised gradient; Free-form deformation http://www.sciencedirect.com/science/article/pii/S0262885616300841 doi:10.1016/j.imavis.2016.05.006 doi:10.1016/j.imavis.2016.05.006 |
| spellingShingle | Image registration; Lucas–Kanade; Normalised gradient; Free-form deformation Snape, Patrick Pszczolkowski, Stefan Zafeiriou, Stefanos Tzimiropoulos, Georgios Ledig, Christian Rueckert, Daniel A robust similarity measure for volumetric image registration with outliers |
| title | A robust similarity measure for volumetric image registration with outliers |
| title_full | A robust similarity measure for volumetric image registration with outliers |
| title_fullStr | A robust similarity measure for volumetric image registration with outliers |
| title_full_unstemmed | A robust similarity measure for volumetric image registration with outliers |
| title_short | A robust similarity measure for volumetric image registration with outliers |
| title_sort | robust similarity measure for volumetric image registration with outliers |
| topic | Image registration; Lucas–Kanade; Normalised gradient; Free-form deformation |
| url | https://eprints.nottingham.ac.uk/34219/ https://eprints.nottingham.ac.uk/34219/ https://eprints.nottingham.ac.uk/34219/ |