Few-shot learning for deformable image registration in 4DCT images
- 1 January 2022
- journal article
- research article
- Published by Oxford University Press (OUP) in The British Journal of Radiology
- Vol. 95 (1129), 20210819
- https://doi.org/10.1259/bjr.20210819
Abstract
To develop a rapid and accurate 4D deformable image registration (DIR) approach for online adaptive radiotherapy. We propose a deep learning (DL)-based few-shot registration network (FR-Net) to generate deformation vector fields from each respiratory phase to an implicit reference image, thereby mitigating the bias introduced by the selection of reference images. The proposed FR-Net is pretrained with limited unlabeled 4D data and further optimized by maximizing the intensity similarity of one specific four-dimensional computed tomography (4DCT) scan. Because of the learning ability of DL models, the few-shot learning strategy facilitates the generalization of the model to other 4D data sets and the acceleration of the optimization process. The proposed FR-Net is evaluated for 4D groupwise and 3D pairwise registration on thoracic 4DCT data sets DIR-Lab and POPI. FR-Net displays an averaged target registration error of 1.48 mm and 1.16 mm between the maximum inhalation and exhalation phases in the 4DCT of DIR-Lab and POPI, respectively, with approximately 2 min required to optimize one 4DCT. Overall, FR-Net outperforms state-of-the-art methods in terms of registration accuracy and exhibits a low computational time. We develop a few-shot groupwise DIR algorithm for 4DCT images. The promising registration performance and computational efficiency demonstrate the prospective applications of this approach in registration tasks for online adaptive radiotherapy. This work exploits DL models to solve the optimization problem in registering 4DCT scans while combining groupwise registration and few-shot learning strategy to solve the problem of consuming computational time and inferior registration accuracy.This publication has 24 references indexed in Scilit:
- Nonrigid registration of dynamic medical imaging data using nD+t B-splines and a groupwise optimization approachMedical Image Analysis, 2011
- The Use of 4DCT to Reduce Lung Dose: A Dosimetric AnalysisMedical Dosimetry, 2010
- Four-dimensional deformable image registration using trajectory modelingPhysics in Medicine & Biology, 2009
- Implementation and evaluation of various demons deformable image registration algorithms on a GPUPhysics in Medicine & Biology, 2009
- Implicit reference-based group-wise image registration and its application to structural and functional MRINeuroImage, 2009
- A framework for evaluation of deformable image registration spatial accuracy using large landmark point setsPhysics in Medicine & Biology, 2009
- Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brainMedical Image Analysis, 2008
- Automatic re-contouring in 4D radiotherapyPhysics in Medicine & Biology, 2006
- Non-rigid image registration: theory and practiceThe British Journal of Radiology, 2004
- 4-dimensional computed tomography imaging and treatment planningSeminars in Radiation Oncology, 2004