A deep learning framework for unsupervised affine and deformable image registration |
| |
| Institution: | 1. Image Sciences Institute, University Medical Center Utrecht and Utrecht University, Utrecht, The Netherlands;2. Division of Image Processing of the Leiden University Medical Center, Leiden, The Netherlands;1. Inception Institute of Artificial Intelligence, Abu Dhabi, United Arab Emirates;2. 2- Monash eResearch, Faculty of Engineering, Monash University, Australia; 3- Airdoc Research, Australia; 4- NVIDIA AI Tech Centre, Australia;1. Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA;2. Institute for Medical Imaging Technology, School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China;3. Department of Brain and Cognitive Engineering, Korea University, Seoul 02841, Republic of Korea;1. Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA;2. Beijing Engineering Research Center of Mixed Reality and Advanced Display, School of Optics and Photonics, Beijing Institute of Technology, Beijing, China;3. Shanghai United Imaging Intelligence Co. Ltd., Shanghai, China;4. Department of Brain and Cognitive Engineering, Korea University, Seoul, Republic of Korea |
| |
| Abstract: | Image registration, the process of aligning two or more images, is the core technique of many (semi-)automatic medical image analysis tasks. Recent studies have shown that deep learning methods, notably convolutional neural networks (ConvNets), can be used for image registration. Thus far training of ConvNets for registration was supervised using predefined example registrations. However, obtaining example registrations is not trivial. To circumvent the need for predefined examples, and thereby to increase convenience of training ConvNets for image registration, we propose the Deep Learning Image Registration (DLIR) framework for unsupervised affine and deformable image registration. In the DLIR framework ConvNets are trained for image registration by exploiting image similarity analogous to conventional intensity-based image registration. After a ConvNet has been trained with the DLIR framework, it can be used to register pairs of unseen images in one shot. We propose flexible ConvNets designs for affine image registration and for deformable image registration. By stacking multiple of these ConvNets into a larger architecture, we are able to perform coarse-to-fine image registration. We show for registration of cardiac cine MRI and registration of chest CT that performance of the DLIR framework is comparable to conventional image registration while being several orders of magnitude faster. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
