Title:(CVPR 2018) Generating Synthetic X-ray Images of a Person from the Surface Geometry Paper Link
Authors: Brian Teixeira et al.
Association: Siemens Medical Solutions Inc., Princeton, NJ, USA
Submission: 2018
Contributions
(0) A novel framework to generate parametrized images using a convergent training pipeline.
(1) A novel technology to predict parametrized X-ray im- ages from body surface data, which as we demonstrate can significantly impact the healthcare domain.
(2) Use of Wasserstein GANs (WGAN) with gradient penalty method for a conditional regression task.
Methods
Learning parametrized image representations can be formulated as multi-task learning.
By learning a pair of networks:
-
Marker Prediction network (MPN): trained to predict the parameters from the image contents
-
Conditional Image Generation network (CIGN): trained to predict the image contents given the parametrization.
During training, the two networks are trained iteratively such that they would converge to a solution where the predicted parameters and the full image are consistent with each other.
In addition to medical data enrichment, our framework can also be used for image completion as well as anomaly detection.
