FAIM - A ConvNet Method for Unsupervised 3D Medical Image Registration

We present a new unsupervised learning algorithm, "FAIM", for 3D medical image registration. With a different architecture than the popular "U-net", the network takes a pair of full image volumes and predicts the displacement fields needed to register source to target. Compared with "U-net" based registration networks such as VoxelMorph, FAIM has fewer trainable parameters but can achieve higher registration accuracy as judged by Dice score on region labels in the Mindboggle-101 dataset. Moreover, with the proposed penalty loss on negative Jacobian determinants, FAIM produces deformations with many fewer "foldings", i.e. regions of non-invertibility where the surface folds over itself. In our experiment, we varied the strength of this penalty and investigated changes in registration accuracy and non-invertibility in terms of number of "folding" locations. We found that FAIM is able to maintain both the advantages of higher accuracy and fewer "folding" locations over VoxelMorph, over a range of hyper-parameters (with the same values used for both networks). Further, when trading off registration accuracy for better invertibility, FAIM required less sacrifice of registration accuracy. Codes for this paper will be released upon publication.

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

[2]  Mert R. Sabuncu,et al.  Unsupervised Learning for Fast Probabilistic Diffeomorphic Registration , 2018, MICCAI.

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

[4]  Ieee Xplore,et al.  IEEE Transactions on Pattern Analysis and Machine Intelligence Information for Authors , 2022, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[6]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[7]  Arno Klein,et al.  101 Labeled Brain Images and a Consistent Human Cortical Labeling Protocol , 2012, Front. Neurosci..

[8]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[9]  P. Cochat,et al.  Et al , 2008, Archives de pediatrie : organe officiel de la Societe francaise de pediatrie.

[10]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

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

[12]  Daniel Rueckert,et al.  Diffeomorphic 3D Image Registration via Geodesic Shooting Using an Efficient Adjoint Calculation , 2011, International Journal of Computer Vision.

[13]  Stephen Smith,et al.  FSL: New tools for functional and structural brain image analysis , 2001, NeuroImage.

[14]  Xiao Yang,et al.  Fast Predictive Image Registration , 2016, LABELS/DLMIA@MICCAI.

[15]  Jun Zhang,et al.  Inverse-Consistent Deep Networks for Unsupervised Deformable Image Registration , 2018, ArXiv.

[16]  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).

[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]  Arno Klein,et al.  A reproducible evaluation of ANTs similarity metric performance in brain image registration , 2011, NeuroImage.

[19]  Paul A. Yushkevich,et al.  Multi-Atlas Segmentation with Joint Label Fusion , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  Wen Yan,et al.  Unsupervised End-to-end Learning for Deformable Medical Image Registration , 2017, ArXiv.

[21]  Dinggang Shen,et al.  Scalable High-Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning , 2016, IEEE Transactions on Biomedical Engineering.

[22]  Arthur W. Toga,et al.  Construction of a 3D probabilistic atlas of human cortical structures , 2008, NeuroImage.

[23]  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.

[24]  Yong Fan,et al.  Non-rigid image registration using fully convolutional networks with deep self-supervision , 2017, ArXiv.

[25]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  P. Thomas Fletcher,et al.  Bayesian Principal Geodesic Analysis in Diffeomorphic Image Registration , 2014, MICCAI.

[27]  Dinggang Shen,et al.  Scalable High Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning , 2017, Deep Learning for Medical Image Analysis.