Altmetric

On the adaptability of unsupervised CNN-based deformable image registration to unseen image domains

File Description SizeFormat 
ferrante2018mlmi.pdfAccepted version453.71 kBAdobe PDFView/Open
Title: On the adaptability of unsupervised CNN-based deformable image registration to unseen image domains
Authors: Ferrante, E
Oktay, O
Glocker, B
Milone, DH
Item Type: Conference Paper
Abstract: Deformable image registration is a fundamental problem in medical image analysis. During the last years, several methods based on deep convolutional neural networks (CNN) proved to be highly accurate to perform this task. These models achieved state-of-the-art accuracy while drastically reducing the required computational time, but mainly focusing on images of specific organs and modalities. To date, no work has reported on how these models adapt across different domains. In this work, we ask the question: can we use CNN-based registration models to spatially align images coming from a domain different than the one/s used at training time? We explore the adaptability of CNN-based image registration to different organs/modalities. We employ a fully convolutional architecture trained following an unsupervised approach. We consider a simple transfer learning strategy to study the generalisation of such model to unseen target domains, and devise a one-shot learning scheme taking advantage of the unsupervised nature of the proposed method. Evaluation on two publicly available datasets of X-Ray lung images and cardiac cine magnetic resonance sequences is provided. Our experiments suggest that models learned in different domains can be transferred at the expense of a decrease in performance, and that one-shot learning in the context of unsupervised CNN-based registration is a valid alternative to achieve consistent registration performance when only a pair of images from the target domain is available.
Issue Date: 15-Sep-2018
Date of Acceptance: 18-Jul-2018
URI: http://hdl.handle.net/10044/1/62670
DOI: https://dx.doi.org/10.1007/978-3-030-00919-9_34
ISSN: 0302-9743
Publisher: Springer Verlag
Start Page: 294
End Page: 302
Journal / Book Title: Machine Learning in Medical Imaging
Volume: LNCS, 11046
Copyright Statement: © Springer Nature Switzerland AG 2018. The final publication is available at Springer via https://link.springer.com/chapter/10.1007/978-3-030-00919-9_34
Conference Name: International Workshop on Machine Learning in Medical Imaging (MLMI)
Keywords: 08 Information And Computing Sciences
Artificial Intelligence & Image Processing
Publication Status: Published
Start Date: 2018-09-16
Conference Place: Granada, Spain
Online Publication Date: 2018-09-15
Appears in Collections:Faculty of Engineering
Computing



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commonsx