Generating Synthetic X-ray Images of a Person from the Surface Geometry

TL;DR

This paper introduces a framework that generates and manipulates synthetic X-ray images of humans from surface geometry, aiding medical data augmentation and image analysis.

Contribution

It presents a novel, learnable method to produce and adjust synthetic X-ray images from surface geometry, addressing data scarcity in medical imaging.

Findings

Successfully generates synthetic X-ray images from surface geometry.

Allows manipulation of images via adjustable body markers.

Potential applications in medical data augmentation and anomaly detection.

Abstract

We present a novel framework that learns to predict human anatomy from body surface. Specifically, our approach generates a synthetic X-ray image of a person only from the person's surface geometry. Furthermore, the synthetic X-ray image is parametrized and can be manipulated by adjusting a set of body markers which are also generated during the X-ray image prediction. With the proposed framework, multiple synthetic X-ray images can easily be generated by varying surface geometry. By perturbing the parameters, several additional synthetic X-ray images can be generated from the same surface geometry. As a result, our approach offers a potential to overcome the training data barrier in the medical domain. This capability is achieved by learning a pair of networks - one learns to generate the full image from the partial image and a set of parameters, and the other learns to estimate the parameters given the full image. 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.