Multi-scale Neural ODEs for 3D Medical Image Registration

Image registration plays an important role in medical image analysis. Conventional optimization based methods provide an accurate estimation due to the iterative process at the cost of expensive computation. Deep learning methods such as learn-to-map are much faster but either iterative or coarse-to-fine approach is required to improve accuracy for handling large motions. In this work, we proposed to learn a registration optimizer via a multi-scale neural ODE model. The inference consists of iterative gradient updates similar to a conventional gradient descent optimizer but in a much faster way, because the neural ODE learns from the training data to adapt the gradient efficiently at each iteration. Furthermore, we proposed to learn a modal-independent similarity metric to address image appearance variations across different image contrasts. We performed evaluations through extensive experiments in the context of multi-contrast 3D MR images from both public and private data sources and demonstrate the superior performance of our proposed methods.

[1]  William Wells,et al.  Multimodal image registration for preoperative planning and image-guided neurosurgical procedures. , 2011, Neurosurgery clinics of North America.

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

[3]  Yu-Ding Lu,et al.  DRIT++: Diverse Image-to-Image Translation via Disentangled Representations , 2020, International Journal of Computer Vision.

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

[5]  Alain Trouvé,et al.  Computing Large Deformation Metric Mappings via Geodesic Flows of Diffeomorphisms , 2005, International Journal of Computer Vision.

[6]  Daniel Cohen-Or,et al.  Unsupervised Multi-Modal Image Registration via Geometry Preserving Image-to-Image Translation , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  David Duvenaud,et al.  Neural Ordinary Differential Equations , 2018, NeurIPS.

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

[9]  Eric Z. Chen,et al.  MRI Image Reconstruction via Learning Optimization Using Neural ODEs , 2020, MICCAI.

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

[11]  Xu Han,et al.  Networks for Joint Affine and Non-Parametric Image Registration , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Brian B. Avants,et al.  The Multimodal Brain Tumor Image Segmentation Benchmark (BRATS) , 2015, IEEE Transactions on Medical Imaging.

[13]  Yaozong Gao,et al.  Dual‐core steered non‐rigid registration for multi‐modal images via bi‐directional image synthesis , 2017, Medical Image Anal..

[14]  Léon Bottou,et al.  Wasserstein GAN , 2017, ArXiv.

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

[16]  Guy Marchal,et al.  Multimodality image registration by maximization of mutual information , 1997, IEEE Transactions on Medical Imaging.

[17]  L. R. Dice Measures of the Amount of Ecologic Association Between Species , 1945 .

[18]  J. Duncan,et al.  Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE , 2020, ICML.

[19]  Jing Hu,et al.  Robust Multimodal Image Registration Using Deep Recurrent Reinforcement Learning , 2018, ACCV.

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

[21]  Michael Brady,et al.  MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration , 2012, Medical Image Anal..

[22]  Jiangping Wang,et al.  Multimodal Image Registration with Deep Context Reinforcement Learning , 2017, MICCAI.

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

[24]  Siwei Lyu,et al.  End-to-end multimodal image registration via reinforcement learning , 2020, Medical Image Anal..

[25]  Marco Aiello,et al.  Radiogenomic Analysis of Oncological Data: A Technical Survey , 2017, International journal of molecular sciences.

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

[27]  Yue Dong,et al.  Recursive Cascaded Networks for Unsupervised Medical Image Registration , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[28]  Jan Kautz,et al.  Multimodal Unsupervised Image-to-Image Translation , 2018, ECCV.

[29]  Brian B. Avants,et al.  Symmetric diffeomorphic image registration with cross-correlation: Evaluating automated labeling of elderly and neurodegenerative brain , 2008, Medical Image Anal..

[30]  Hans J. Johnson,et al.  Advanced Normalization Tools (ANTs) , 2020 .

[31]  Mert R. Sabuncu,et al.  VoxelMorph: A Learning Framework for Deformable Medical Image Registration , 2018, IEEE Transactions on Medical Imaging.

[32]  D. Louis Collins,et al.  Hierarchical Multimodal Image Registration Based on Adaptive Local Mutual Information , 2010, MICCAI.

[33]  Daniel Rueckert,et al.  Unsupervised Deformable Registration for Multi-Modal Images via Disentangled Representations , 2019, IPMI.