Modelling the Distribution of 3D Brain MRI using a 2D Slice VAE

Probabilistic modelling has been an essential tool in medical image analysis, especially for analyzing brain Magnetic Resonance Images (MRI). Recent deep learning techniques for estimating high-dimensional distributions, in particular Variational Autoencoders (VAEs), opened up new avenues for probabilistic modeling. Modelling of volumetric data has remained a challenge, however, because constraints on available computation and training data make it difficult effectively leverage VAEs, which are well-developed for 2D images. We propose a method to model 3D MR brain volumes distribution by combining a 2D slice VAE with a Gaussian model that captures the relationships between slices. We do so by estimating the sample mean and covariance in the latent space of the 2D model over the slice direction. This combined model lets us sample new coherent stacks of latent variables to decode into slices of a volume. We also introduce a novel evaluation method for generated volumes that quantifies how well their segmentations match those of true brain anatomy. We demonstrate that our proposed model is competitive in generating high quality volumes at high resolutions according to both traditional metrics and our proposed evaluation.

[1]  Luc Van Gool,et al.  Improving Video Generation for Multi-functional Applications. , 2017 .

[2]  Essa Yacoub,et al.  The WU-Minn Human Connectome Project: An overview , 2013, NeuroImage.

[3]  Karl J. Friston,et al.  Unified segmentation , 2005, NeuroImage.

[4]  Ender Konukoglu,et al.  MR Image Reconstruction Using Deep Density Priors , 2017, IEEE Transactions on Medical Imaging.

[5]  Ole Winther,et al.  Autoencoding beyond pixels using a learned similarity metric , 2015, ICML.

[6]  Ender Konukoglu,et al.  Unsupervised Detection of Lesions in Brain MRI using constrained adversarial auto-encoders , 2018, ArXiv.

[7]  Brian B. Avants,et al.  N4ITK: Improved N3 Bias Correction , 2010, IEEE Transactions on Medical Imaging.

[8]  Sepp Hochreiter,et al.  GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium , 2017, NIPS.

[9]  Luc Van Gool,et al.  Towards an Understanding of Our World by GANing Videos in the Wild , 2017, ArXiv.

[10]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[11]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[12]  Bruce Fischl,et al.  FreeSurfer , 2012, NeuroImage.

[13]  Seyed-Ahmad Ahmadi,et al.  V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation , 2016, 2016 Fourth International Conference on 3D Vision (3DV).

[14]  Konstantinos Kamnitsas,et al.  Reverse Classification Accuracy: Predicting Segmentation Performance in the Absence of Ground Truth , 2017, IEEE Transactions on Medical Imaging.

[15]  Antonio Torralba,et al.  Generating Videos with Scene Dynamics , 2016, NIPS.

[16]  Raquel Urtasun,et al.  The Reversible Residual Network: Backpropagation Without Storing Activations , 2017, NIPS.

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

[18]  Polina Golland,et al.  Automated segmentation of hippocampal subfields from ultra‐high resolution in vivo MRI , 2009, Hippocampus.

[19]  Wojciech Zaremba,et al.  Improved Techniques for Training GANs , 2016, NIPS.

[20]  Gihyun Kwon,et al.  Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networks , 2019, MICCAI.

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

[22]  Shakir Mohamed,et al.  Variational Approaches for Auto-Encoding Generative Adversarial Networks , 2017, ArXiv.