DeepAI AI Chat
Log In Sign Up

A Deep-Discrete Learning Framework for Spherical Surface Registration

by   Mohamed A. Suliman, et al.
King's College London

Cortical surface registration is a fundamental tool for neuroimaging analysis that has been shown to improve the alignment of functional regions relative to volumetric approaches. Classically, image registration is performed by optimizing a complex objective similarity function, leading to long run times. This contributes to a convention for aligning all data to a global average reference frame that poorly reflects the underlying cortical heterogeneity. In this paper, we propose a novel unsupervised learning-based framework that converts registration to a multi-label classification problem, where each point in a low-resolution control grid deforms to one of fixed, finite number of endpoints. This is learned using a spherical geometric deep learning architecture, in an end-to-end unsupervised way, with regularization imposed using a deep Conditional Random Field (CRF). Experiments show that our proposed framework performs competitively, in terms of similarity and areal distortion, relative to the most popular classical surface registration algorithms and generates smoother deformations than other learning-based surface registration methods, even in subjects with atypical cortical morphology.


page 8

page 9

page 10

page 11


Cortical surface registration using unsupervised learning

Non-rigid cortical registration is an important and challenging task due...

A Robust Loss for Point Cloud Registration

The performance of surface registration relies heavily on the metric use...

Joint cortical registration of geometry and function using semi-supervised learning

Brain surface-based image registration, an important component of brain ...

Mutual information neural estimation for unsupervised multi-modal registration of brain images

Many applications in image-guided surgery and therapy require fast and r...

Unsupervised Diffeomorphic Surface Registration and Non-Linear Modelling

Registration is an essential tool in image analysis. Deep learning based...

3D B-mode ultrasound speckle reduction using deep learning for 3D registration applications

Ultrasound (US) speckles are granular patterns which can impede image po...

Learning Thin-Plate Spline Motion and Seamless Composition for Parallax-Tolerant Unsupervised Deep Image Stitching

Traditional image stitching approaches tend to leverage increasingly com...