Quasiconformal model with CNN features for large deformation image registration

DOI10.3934/IPI.2022010zbMATH Open1492.65051arXiv2011.00731OpenAlexW3176990113MaRDI QIDQ2158263FDOQ2158263

Ho Law, Lok Ming Lui, Gary Pui-Tung Choi, Ka Chun Lam

Publication date: 26 July 2022

Published in: Inverse Problems and Imaging (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/2011.00731

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

zbMATH Keywords

image registrationconvolutional neural networksquasiconformal theory

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Computer graphics; computational geometry (digital and algorithmic aspects) (68U05) Computing methodologies for image processing (68U10) Numerical aspects of computer graphics, image analysis, and computational geometry (65D18)

Cites Work

• FAIR
• Computing large deformation metric mappings via geodesic flows of diffeomorphisms
• Principal warps: thin-plate splines and the decomposition of deformations
• Title not available (Why is that?)
• Title not available (Why is that?)
• Determining optical flow
• Title not available (Why is that?)
• Landmark matching via large deformation diffeomorphisms
• A regularized convolutional neural network for semantic image segmentation
• FLASH: Fast Landmark Aligned Spherical Harmonic Parameterization for Genus-0 Closed Brain Surfaces
• TEMPO: Feature-Endowed Teichmüller Extremal Mappings of Point Clouds
• Fast disk conformal parameterization of simply-connected open surfaces
• Landmark-matching transformation with large deformation via \(n\)-dimensional quasi-conformal maps
• Landmark- and Intensity-Based Registration with Large Deformations via Quasi-conformal Maps
• Free-boundary conformal parameterization of point clouds
• A linear formulation for disk conformal parameterization of simply-connected open surfaces
• Shape analysis via inconsistent surface registration
• Parallelizable Global Conformal Parameterization of Simply-Connected Surfaces via Partial Welding
• 3D Orientation-Preserving Variational Models for Accurate Image Registration

Cited In (2)

• A Unifying Framework for $n$-Dimensional Quasi-Conformal Mappings
• A deep learning framework for diffeomorphic mapping problems via quasi-conformal geometry applied to imaging

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)