Quasiconformal model with CNN features for large deformation image registration

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.

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• VoxelMorph: A Learning Framework for Deformable Medical Image Registration
• A Deep Learning Framework for Unsupervised Affine and Deformable Image Registration
• PN-Net: Conjoined Triple Deep Network for Learning Local Image Descriptors
• TEMPO: Feature-Endowed Teichmüller Extremal Mappings of Point Clouds
• Fast Disk Conformal Parameterization of Simply-connected Open Surfaces
• Parallelizable global conformal parameterization of simply-connected surfaces via partial welding
• Tooth morphometry using quasi-conformal theory
• A Linear Formulation for Disk Conformal Parameterization of Simply-Connected Open Surfaces
• Efficient Feature-based Image Registration by Mapping Sparsified Surfaces
• Free-boundary conformal parameterization of point clouds
• Shape analysis via inconsistent surface registration

Cited by in corpus (1)

• A unifying framework for $n$-dimensional quasi-conformal mappings