Quasiconformal model with CNN features for large deformation image registration
From MaRDI portal
Publication:2158263
Abstract: Image registration has been widely studied over the past several decades, with numerous applications in science, engineering and medicine. Most of the conventional mathematical models for large deformation image registration rely on prescribed landmarks, which usually require tedious manual labeling and are prone to error. In recent years, there has been a surge of interest in the use of machine learning for image registration. In this paper, we develop a novel method for large deformation image registration by a fusion of quasiconformal theory and convolutional neural network (CNN). More specifically, we propose a quasiconformal energy model with a novel fidelity term that incorporates the features extracted using a pre-trained CNN, thereby allowing us to obtain meaningful registration results without any guidance of prescribed landmarks. Moreover, unlike many prior image registration methods, the bijectivity of our method is guaranteed by quasiconformal theory. Experimental results are presented to demonstrate the effectiveness of the proposed method. More broadly, our work sheds light on how rigorous mathematical theories and practical machine learning approaches can be integrated for developing computational methods with improved performance.
Recommendations
- Inverse Consistent Deformable Image Registration
- A novel diffeomorphic model for image registration and its algorithm
- Deformable multi-modal image registration by maximizing Rényi's statistical dependence measure
- Quasi-conformal neural network (QC-net) with applications to shape matching
- A fast image registration algorithm for diffeomorphic images with large deformation
Cites work
- scientific article; zbMATH DE number 1399773 (Why is no real title available?)
- scientific article; zbMATH DE number 3421121 (Why is no real title available?)
- 3D orientation-preserving variational models for accurate image registration
- A linear formulation for disk conformal parameterization of simply-connected open surfaces
- A regularized convolutional neural network for semantic image segmentation
- Computing large deformation metric mappings via geodesic flows of diffeomorphisms
- Deep learning
- Determining optical flow
- FAIR. Flexible algorithms for image registration.
- FLASH: Fast landmark aligned spherical harmonic parameterization for genus-0 closed brain surfaces
- Fast disk conformal parameterization of simply-connected open surfaces
- Free-boundary conformal parameterization of point clouds
- Landmark matching via large deformation diffeomorphisms
- Landmark- and intensity-based registration with large deformations via quasi-conformal maps
- Landmark-matching transformation with large deformation via \(n\)-dimensional quasi-conformal maps
- Parallelizable global conformal parameterization of simply-connected surfaces via partial welding
- Principal warps: thin-plate splines and the decomposition of deformations
- Shape analysis via inconsistent surface registration
- TEMPO: feature-endowed Teichmüller extremal mappings of point clouds
Cited in
(4)- A Unifying Framework for $n$-Dimensional Quasi-Conformal Mappings
- Body-shared learning framework for diffeomorphic landmark-matching registration problem
- A deep learning framework for diffeomorphic mapping problems via quasi-conformal geometry applied to imaging
- Quasi-conformal neural network (QC-net) with applications to shape matching
This page was built for publication: Quasiconformal model with CNN features for large deformation image registration
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2158263)
