Congratulations to Lin Tian, Hastings Greer who are presenting their CVPR paper on gradient inverse consistent image registraton (GradICON) this week. GradICON is a new deep-learning-based image registration approach which only weakly regularizes the tranformations via a new gradient inverse consistency loss. Doing so results in state-of-the-art registration performance (as tested on 3D knee, lung, and brain images) without the need for extensive hyperparameter tuning.
- GradICON: Approximate Diffeomorphisms via Gradient Inverse Consistency
- Anatomical Data Augmentation via Fluid-Based Image Registration
- DeepAtlas: Joint Semi-supervised Learning of Image Registration and Segmentation
- LiftReg: Limited Angle 2D/3D Deformable Registration
- A feature-based affine registration method for capturing background lung tissue deformation for ground glass nodule tracking