Return to search

Deformable 3D Brain MRI Registration with Deep Learning / Deformerbar 3D MRI-registrering med djupinlärning

Traditional deformable registration methods have achieved impressive performances but are computationally time-consuming since they have to optimize an objective function for each new pair of images. Very recently some learning-based approaches have been proposed to enable fast registration by learning to estimate the spatial transformation parameters directly from the input images. Here we present a method for 3D fast pairwise registration of brain MR images. We model the deformation function with B-splines and learn the optimal control points using a U-Net like CNN architecture. An inverse-consistency loss has been used to enforce diffeomorphicity of the deformation. The proposed algorithm does not require supervised information such as segmented labels but some can be used to help the registration process. We also implemented several strategies to account for the multi-resolution nature of the problem. The method has been evaluated on MICCAI 2012 brain MRI datasets, and evaluated on both similarity and invertibility of the computed transformation.

Identiferoai:union.ndltd.org:UPSALLA1/oai:DiVA.org:kth-262852
Date January 2019
CreatorsJoos, Louis
PublisherKTH, Skolan för kemi, bioteknologi och hälsa (CBH)
Source SetsDiVA Archive at Upsalla University
LanguageEnglish
Detected LanguageEnglish
TypeStudent thesis, info:eu-repo/semantics/bachelorThesis, text
Formatapplication/pdf
Rightsinfo:eu-repo/semantics/openAccess
RelationTRITA-CBH-GRU ; 2019:106

Page generated in 0.002 seconds