DA-AR-Net: an attentive activation based Deformable auto-encoder for group-wise registration

Medical image registration over the past many years has been dominated by techniques which rely on expert an- notations, while not taking advantage of the unlabelled data. Deep unsupervised architectures utilized this widely available unlabelled data to model the anatomically induced patterns in a dataset. Deformable Auto-encoder (DAE), an unsupervised group-wise registration technique, has been used to generate a deformed reconstruction of an input image, which also subsequently generates a global template to capture the deformations in a medical dataset. DAEs however have significant weakness in propagating global information over range long dependencies, which may affect the registration performance on quantitative and qualitative measures. Our proposed method captures valuable knowledge over the whole spatial dimension using an attention mechanism. We present Deformable Auto-encoder Attention Relu Network (DA-AR-Net), which is an exquisite integration of the Attention Relu(Arelu), an attention based activation function into the DAE framework. A detachment of the template image from the deformation field is achieved by encoding the spatial information into two separate latent code representation. Each latent code is followed by a separate decoder network, while only a single encoder is used for feature encoding. Our DA-AR-Net is formalized after an extensive and systematic search across various hyper-parameters - initial setting of learnable parameters of Arelu, the appropriate positioning of Arelu, latent code dimensions, and batch size. Our best architecture shows a significant improvement of 42% on MSE score over previous DAEs and 32% reduction is attained while generating visually sharp global templates.

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

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

[3]  Dinggang Shen,et al.  BIRNet: Brain image registration using dual‐supervised fully convolutional networks , 2018, Medical Image Anal..

[4]  Yuanjie Zheng,et al.  Deep Group-Wise Registration for Multi-Spectral Images From Fundus Images , 2019, IEEE Access.

[5]  John Ashburner,et al.  A fast diffeomorphic image registration algorithm , 2007, NeuroImage.

[6]  Quoc V. Le,et al.  Attention Augmented Convolutional Networks , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

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

[8]  Hervé Delingette,et al.  Learning a Probabilistic Model for Diffeomorphic Registration , 2018, IEEE Transactions on Medical Imaging.

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

[10]  Stefan Heldmann,et al.  Deformable Groupwise Image Registration using Low-Rank and Sparse Decomposition , 2020, Journal of Mathematical Imaging and Vision.

[11]  Mattias P. Heinrich,et al.  Deep Groupwise Registration of MRI Using Deforming Autoencoders , 2020, Bildverarbeitung für die Medizin.

[12]  Iasonas Kokkinos,et al.  Deforming Autoencoders: Unsupervised Disentangling of Shape and Appearance , 2018, ECCV.

[13]  Mert R. Sabuncu,et al.  Learning Conditional Deformable Templates with Convolutional Networks , 2019, NeurIPS.

[14]  Paul M. Thompson,et al.  The role of image registration in brain mapping , 2001, Image Vis. Comput..

[15]  Yuanjie Zheng,et al.  DGR-Net: Deep Groupwise Registration of Multispectral Images , 2019, IPMI.

[16]  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.

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

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

[19]  Ashish Vaswani,et al.  Stand-Alone Self-Attention in Vision Models , 2019, NeurIPS.

[20]  Shuicheng Yan,et al.  A2-Nets: Double Attention Networks , 2018, NeurIPS.