Pathology Synthesis of 3D Consistent Cardiac MR Im-ages Using 2D VAEs and GANs

We propose a method for synthesizing cardiac MR images with plausible heart shapes and realistic appearances for the purpose of generating labeled data for deep-learning (DL) training. It breaks down the image synthesis into label deformation and label-to-image translation tasks. The former is achieved via latent space interpolation in a VAE model, while the latter is accomplished via a conditional GAN model. We devise an approach for label manipulation in the latent space of the trained VAE model, namely pathology synthesis, aiming to synthesize a series of pseudo-pathological synthetic subjects with characteristics of a desired heart disease. Furthermore, we propose to model the relationship between 2D slices in the latent space of the VAE via estimating the correlation coefficient matrix between the latent vectors and utilizing it to correlate elements of randomly drawn samples before decoding to image space. This simple yet effective approach results in generating 3D consistent subjects from 2D slice-by-slice generations. Such an approach could provide a solution to diversify and enrich the available database of cardiac MR images and to pave the way for the development of generalizable DL-based image analysis algorithms. The code will be available at https://github.com/sinaamirrajab/CardiacPathologySynthesis.

XCAT-GAN for Synthesizing 3D Consistent Labeled Cardiac MR Images on Anatomically Variable XCAT Phantoms

Generative adversarial networks (GANs) have provided promising data enrichment solutions by synthesizing high-fidelity images. However, generating large sets of labeled images with new anatomical variations remains unexplored. We propose a novel method for synthesizing cardiac magnetic resonance (CMR) images on a population of virtual subjects with a large anatomical variation, introduced using the 4D eXtended Cardiac and Torso (XCAT) computerized human phantom. We investigate two conditional image synthesis approaches grounded on a semantically-consistent mask-guided image generation technique: 4-class and 8-class XCAT-GANs. The 4-class technique relies on only the annotations of the heart; while the 8-class technique employs a predicted multi-tissue label map of the heart-surrounding organs and provides better guidance for our conditional image synthesis. For both techniques, we train our conditional XCAT-GAN with real images paired with corresponding labels and subsequently at the inference time, we substitute the labels with the XCAT derived ones. Therefore, the trained network accurately transfers the tissue-specific textures to the new label maps. By creating 33 virtual subjects of synthetic CMR images at the end-diastolic and end-systolic phases, we evaluate the usefulness of such data in the downstream cardiac cavity segmentation task under different augmentation strategies. Results demonstrate that even with only 20% of real images (40 volumes) seen during training, segmentation performance is retained with the addition of synthetic CMR images. Moreover, the improvement in utilizing synthetic images for augmenting the real data is evident through the reduction of Hausdorff distance up to 28% and an increase in the Dice score up to 5%, indicating a higher similarity to the ground truth in all dimensions.

4D Semantic Cardiac Magnetic Resonance Image Synthesis on XCAT Anatomical Model

We propose a hybrid controllable image generation method to synthesize anatomically meaningful 3D+t labeled Cardiac Magnetic Resonance (CMR) images. Our hybrid method takes the mechanistic 4D eXtended CArdiac Torso (XCAT) heart model as the anatomical ground truth and synthesizes CMR images via a data-driven Generative Adversarial Network (GAN). We employ the state-of-the-art SPatially Adaptive De-normalization (SPADE) technique for conditional image synthesis to preserve the semantic spatial information of ground truth anatomy. Using the parameterized motion model of the XCAT heart, we generate labels for 25 time frames of the heart for one cardiac cycle at 18 locations for the short axis view. Subsequently, realistic images are generated from these labels, with modality-specific features that are learned from real CMR image data. We demonstrate that style transfer from another cardiac image can be accomplished by using a style encoder network. Due to the flexibility of XCAT in creating new heart models, this approach can result in a realistic virtual population to address different challenges the medical image analysis research community is facing such as expensive data collection. Our proposed method has a great potential to synthesize 4D controllable CMR images with annotations and adaptable styles to be used in various supervised multi-site, multi-vendor applications in medical image analysis.