A FCN-based Unsupervised Learning Model for Deformable Chest CT Image Registration

Image registration is a fundamental technique for many automatic medical image analysis tasks, but it can be time-consuming, especially for deformable three-dimensional image registration. In this paper we propose a fast unsupervised learning method for deformable image registration using a fully convolutional network (FCN). The network directly learns to estimate a dense displacement vector field (DVF) from a pair of input images. A spatial transform layer then uses the DVF to warp the moving image to the fixed image. Different from supervised learning based image registration methods, the network is trained by maximization of a similarity metric between the fixed image and the warped moving image. Thus training does not require supervised information such as manually annotated or synthetic ground truth. We evaluate the proposed model on publicly available datasets of inspiration-expiration chest CT image pairs. The results demonstrate that the accuracy of the model is comparable to that of the conventional image registration while executing orders of magnitude faster.

[1]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[2]  Maxime Sermesant,et al.  SVF-Net: Learning Deformable Image Registration Using Shape Matching , 2017, MICCAI.

[3]  Mitko Veta,et al.  Deformable image registration using convolutional neural networks , 2018, Medical Imaging.

[4]  R. Castillo,et al.  Four-dimensional deformable image registration using trajectory modeling , 2010, Physics in medicine and biology.

[5]  Andrew Zisserman,et al.  Spatial Transformer Networks , 2015, NIPS.

[6]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[7]  Boudewijn P. F. Lelieveldt,et al.  Nonrigid Image Registration Using Multi-scale 3D Convolutional Neural Networks , 2017, MICCAI.

[8]  Max A. Viergever,et al.  A deep learning framework for unsupervised affine and deformable image registration , 2018, Medical Image Anal..

[9]  Max A. Viergever,et al.  End-to-End Unsupervised Deformable Image Registration with a Convolutional Neural Network , 2017, DLMIA/ML-CDS@MICCAI.

[10]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Qian Wang,et al.  Deformable Image Registration Based on Similarity-Steered CNN Regression , 2017, MICCAI.

[12]  Marc Modat,et al.  Label-driven weakly-supervised learning for multimodal deformarle image registration , 2017, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[13]  Yong Fan,et al.  Non-rigid image registration using self-supervised fully convolutional networks without training data , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[14]  Mert R. Sabuncu,et al.  An Unsupervised Learning Model for Deformable Medical Image Registration , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[15]  R. Castillo,et al.  A framework for evaluation of deformable image registration spatial accuracy using large landmark point sets , 2009, Physics in medicine and biology.

[16]  Hervé Delingette,et al.  Robust Non-rigid Registration Through Agent-Based Action Learning , 2017, MICCAI.

[17]  Won-Ki Jeong,et al.  ssEMnet: Serial-Section Electron Microscopy Image Registration Using a Spatial Transformer Network with Learned Features , 2017, DLMIA/ML-CDS@MICCAI.

[18]  Max A. Viergever,et al.  Registration of organs with sliding interfaces and changing topologies , 2014, Medical Imaging.

[19]  Marc Niethammer,et al.  Quicksilver: Fast predictive image registration – A deep learning approach , 2017, NeuroImage.