Synthetic data generation for X-ray imaging

Image processing softwares, like all softwares, need to be both verified and validated. Synthetic images are very useful during the medical software development process to verify the accuracy of algorithms. In this paper we introduce the process of generating synthetic 2D medical X-ray images in addition to ground truth imaging parameters. First, a 3D model of an organ (e.g., vessels) is made in a 3D-modeling software. Then, this volume model is voxelized based on the specified resolution in order to create a 3D CT image of that organ by assigning proper Hounsfield unit to each voxel. The obtained 3D CT image volume is used in DRR program as the input. Geometry parameters such as internal and external parameters are adjusted to take some images from different views. We demonstrated this process by three examples to confirm its usage in validation of medical image processing applications.