Abstract
Image registration is a key technique in medical image analysis to estimate deformations between image pairs. A good deformation model is important for high-quality estimates. However, most existing approaches use ad-hoc deformation models chosen for mathematical convenience rather than to capture observed data variation. Recent deep learning approaches learn deformation models directly from data. However, they provide limited control over the spatial regularity of transformations. Instead of learning the entire registration approach, we learn a spatially-adaptive regularizer within a registration model. This allows controlling the desired level of regularity and preserving structural properties of a registration model. For example, diffeomorphic transformations can be attained. Our approach is a radical departure from existing deep learning approaches to image registration by embedding a deep learning model in an optimization-based registration algorithm to parameterize and data-adapt the registration model itself.
Originalsprache | Englisch |
---|---|
Titel | Proceedings of the 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition |
Herausgeber (Verlag) | IEEE Computer Society |
Seiten | 8463-8472 |
Seitenumfang | 9 |
Publikationsstatus | Veröffentlicht - 2019 |
Veranstaltung | IEEE/CVF Conference on Computer Vision and Pattern Recognition - Long Beach Convention Center, Long Beach, CA, USA/Vereinigte Staaten Dauer: 16 Jun 2019 → 20 Jun 2019 |
Konferenz
Konferenz | IEEE/CVF Conference on Computer Vision and Pattern Recognition |
---|---|
Kurztitel | CVPR |
Land | USA/Vereinigte Staaten |
Ort | Long Beach, CA |
Zeitraum | 16/06/19 → 20/06/19 |
Systematik der Wissenschaftszweige 2012
- 102 Informatik