3D Convolutional Neural Networks Image Registration Based on Efficient Supervised Learning from Artificial Deformations
This work addresses the challenge of accurate and efficient medical image registration for chest CT analysis, though it is incremental as it builds on existing supervised learning approaches with artificial data generation.
The authors tackled the problem of nonrigid image registration for chest CT scans by proposing a supervised method trained with artificially generated displacement vector fields, achieving target registration errors of 2.32 ± 5.33 mm and 1.86 ± 2.12 mm on two datasets with an inference time of about 2.2 seconds.
We propose a supervised nonrigid image registration method, trained using artificial displacement vector fields (DVF), for which we propose and compare three network architectures. The artificial DVFs allow training in a fully supervised and voxel-wise dense manner, but without the cost usually associated with the creation of densely labeled data. We propose a scheme to artificially generate DVFs, and for chest CT registration augment these with simulated respiratory motion. The proposed architectures are embedded in a multi-stage approach, to increase the capture range of the proposed networks in order to more accurately predict larger displacements. The proposed method, RegNet, is evaluated on multiple databases of chest CT scans and achieved a target registration error of 2.32 $\pm$ 5.33 mm and 1.86 $\pm$ 2.12 mm on SPREAD and DIR-Lab-4DCT studies, respectively. The average inference time of RegNet with two stages is about 2.2 s.