Deformable image registration using convolutional neural networks

Koen A.J. Eppenhof, Maxime W. Lafarge, Pim Moeskops, Mitko Veta, Josien P.W. Pluim

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

65 Citaten (Scopus)
1597 Downloads (Pure)


Deformable image registration can be time-consuming and often needs extensive parameterization to perform well on a specific application. We present a step towards a registration framework based on a three-dimensional convolutional neural network. The network directly learns transformations between pairs of three-dimensional images. The outputs of the network are three maps for the x, y, and z components of a thin plate spline transformation grid. The network is trained on synthetic random transformations, which are applied to a small set of representative images for the desired application. Training therefore does not require manually annotated ground truth deformation information. The methodology is demonstrated on public data sets of inspiration-expiration lung CT image pairs, which come with annotated corresponding landmarks for evaluation of the registration accuracy. Advantages of this methodology are its fast registration times and its minimal parameterization.

Originele taal-2Engels
TitelMedical Imaging 2018 Image Processing
Plaats van productieBellingham
Aantal pagina's6
ISBN van elektronische versie9781510616370
StatusGepubliceerd - 15 mrt. 2018
EvenementSPIE Medical Imaging 2018 - Houston, Verenigde Staten van Amerika
Duur: 10 feb. 201815 feb. 2018

Publicatie series

NaamProceedings of SPIE


CongresSPIE Medical Imaging 2018
Land/RegioVerenigde Staten van Amerika


Duik in de onderzoeksthema's van 'Deformable image registration using convolutional neural networks'. Samen vormen ze een unieke vingerafdruk.

Citeer dit