CHeart: A Conditional Spatio-Temporal Generative Model for Cardiac Anatomy

Two key questions in cardiac image analysis are to assess the anatomy and motion of the heart from images; and to understand how they are associated with non-imaging clinical factors such as gender, age and diseases. While the first question can often be addressed by image segmentation and motion tracking algorithms, our capability to model and to answer the second question is still limited. In this work, we propose a novel conditional generative model to describe the 4D spatio-temporal anatomy of the heart and its interaction with non-imaging clinical factors. The clinical factors are integrated as the conditions of the generative modelling, which allows us to investigate how these factors influence the cardiac anatomy. We evaluate the model performance in mainly two tasks, anatomical sequence completion and sequence generation. The model achieves a high performance in anatomical sequence completion, comparable to or outperforming other state-of-the-art generative models. In terms of sequence generation, given clinical conditions, the model can generate realistic synthetic 4D sequential anatomies that share similar distributions with the real data.

[1]  C. Lorenz,et al.  A Framework for Simulating Cardiac MR Images With Varying Anatomy and Contrast , 2022, IEEE Transactions on Medical Imaging.

[2]  Yaniv Taigman,et al.  Make-A-Video: Text-to-Video Generation without Text-Video Data , 2022, ICLR.

[3]  Víctor M. Campello,et al.  Cardiac aging synthesis from cross-sectional data with conditional generative adversarial networks , 2022, Frontiers in Cardiovascular Medicine.

[4]  P. Leeson,et al.  D'ARTAGNAN: Counterfactual Video Generation , 2022, MICCAI.

[5]  Michael J. Black,et al.  TEMOS: Generating diverse human motions from textual descriptions , 2022, ECCV.

[6]  Prafulla Dhariwal,et al.  GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models , 2021, ICML.

[7]  A. McCulloch,et al.  Right-left ventricular shape variations in tetralogy of Fallot: associations with pulmonary regurgitation , 2021, Journal of Cardiovascular Magnetic Resonance.

[8]  Pieter Abbeel,et al.  VideoGPT: Video Generation using VQ-VAE and Transformers , 2021, ArXiv.

[9]  Aäron van den Oord,et al.  Predicting Video with VQVAE , 2021, ArXiv.

[10]  Y. Demiris,et al.  Disentangled Sequence Clustering for Human Intention Inference , 2021, 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[11]  Hao Zhang,et al.  DECOR-GAN: 3D Shape Detailization by Conditional Refinement , 2020, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[12]  Jens Petersen,et al.  nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation , 2020, Nature Methods.

[13]  N. Ayache,et al.  Learning a Generative Motion Model From Image Sequences Based on a Latent Motion Matrix , 2020, IEEE Transactions on Medical Imaging.

[14]  Alistair A. Young,et al.  Artificial Intelligence in Cardiac Imaging With Statistical Atlases of Cardiac Anatomy , 2020, Frontiers in Cardiovascular Medicine.

[15]  Ilya Sutskever,et al.  Jukebox: A Generative Model for Music , 2020, ArXiv.

[16]  Seong Joon Oh,et al.  Reliable Fidelity and Diversity Metrics for Generative Models , 2020, ICML.

[17]  Aditya Khamparia,et al.  An Integrated Hybrid CNN–RNN Model for Visual Description and Generation of Captions , 2020, Circuits Syst. Signal Process..

[18]  Sotirios A. Tsaftaris,et al.  Learning to synthesise the ageing brain without longitudinal data , 2019, Medical Image Anal..

[19]  Natalia Gimelshein,et al.  PyTorch: An Imperative Style, High-Performance Deep Learning Library , 2019, NeurIPS.

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

[21]  Konstantinos Kamnitsas,et al.  Explainable Shape Analysis through Deep Hierarchical Generative Models: Application to Cardiac Remodeling , 2019, ArXiv.

[22]  Timo Aila,et al.  A Style-Based Generator Architecture for Generative Adversarial Networks , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Olivier Bachem,et al.  Assessing Generative Models via Precision and Recall , 2018, NeurIPS.

[24]  Nicholas Ayache,et al.  Model-Based Generation of Large Databases of Cardiac Images: Synthesis of Pathological Cine MR Sequences From Real Healthy Cases , 2018, IEEE Transactions on Medical Imaging.

[25]  Daniel Rueckert,et al.  Unbiased construction of a temporally consistent morphological atlas of neonatal brain development , 2018, bioRxiv.

[26]  Jung-Woo Ha,et al.  StarGAN: Unified Generative Adversarial Networks for Multi-domain Image-to-Image Translation , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[27]  Ben Glocker,et al.  Automated cardiovascular magnetic resonance image analysis with fully convolutional networks , 2017, Journal of Cardiovascular Magnetic Resonance.

[28]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[29]  Gang Hua,et al.  CVAE-GAN: Fine-Grained Image Generation through Asymmetric Training , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[30]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[31]  Christopher Burgess,et al.  beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework , 2016, ICLR 2016.

[32]  John Eng,et al.  Adverse Left Ventricular Remodeling and Age Assessed with Cardiac MR Imaging: The Multi-Ethnic Study of Atherosclerosis. , 2016, Radiology.

[33]  L. Anderson,et al.  The Role of Cardiovascular Magnetic Resonance Imaging in Heart Failure. , 2016, Cardiac failure review.

[34]  Honglak Lee,et al.  Learning Structured Output Representation using Deep Conditional Generative Models , 2015, NIPS.

[35]  Hans Torp,et al.  Myocardial strain imaging: how useful is it in clinical decision making? , 2015, European heart journal.

[36]  Shakir Mohamed,et al.  Variational Inference with Normalizing Flows , 2015, ICML.

[37]  Erwan Donal,et al.  Role of multimodality cardiac imaging in the management of patients with hypertrophic cardiomyopathy: an expert consensus of the European Association of Cardiovascular Imaging Endorsed by the Saudi Heart Association. , 2015, European heart journal cardiovascular Imaging.

[38]  Samy Bengio,et al.  Show and tell: A neural image caption generator , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[39]  Simon Osindero,et al.  Conditional Generative Adversarial Nets , 2014, ArXiv.

[40]  Quoc V. Le,et al.  Sequence to Sequence Learning with Neural Networks , 2014, NIPS.

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

[42]  Daniel Rueckert,et al.  A Probabilistic Patch-Based Label Fusion Model for Multi-Atlas Segmentation With Registration Refinement: Application to Cardiac MR Images , 2013, IEEE Transactions on Medical Imaging.

[43]  D. Firmin,et al.  Motion in cardiovascular MR imaging. , 2009, Radiology.

[44]  Guido Gerig,et al.  User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability , 2006, NeuroImage.

[45]  Daniel Rueckert,et al.  Comparison and evaluation of rigid and nonrigid registration of breast MR images , 1999, Medical Imaging.

[46]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[47]  William C. Little,et al.  The cardiac cycle and the physiologic basis of left ventricular contraction, ejection, relaxation, and filling. , 2008, Heart failure clinics.

[48]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[49]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[50]  Ian T. Jolliffe,et al.  Principal Component Analysis for Special Types of Data , 1986 .