XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors

TL;DR

XraySyn is a novel method that synthesizes new radiographic views from single X-ray images by leveraging CT data and differentiable projection, aiding medical interpretation without requiring groundtruth labels.

Contribution

It introduces the first approach for radiograph view synthesis using CT priors and a differentiable projection algorithm for realistic view generation.

Findings

Enables realistic view synthesis from single radiographs.

Supports bone extraction and suppression without groundtruth labels.

First to address radiograph view synthesis with a learning-based approach.

Abstract

A radiograph visualizes the internal anatomy of a patient through the use of X-ray, which projects 3D information onto a 2D plane. Hence, radiograph analysis naturally requires physicians to relate the prior about 3D human anatomy to 2D radiographs. Synthesizing novel radiographic views in a small range can assist physicians in interpreting anatomy more reliably; however, radiograph view synthesis is heavily ill-posed, lacking in paired data, and lacking in differentiable operations to leverage learning-based approaches. To address these problems, we use Computed Tomography (CT) for radiograph simulation and design a differentiable projection algorithm, which enables us to achieve geometrically consistent transformations between the radiography and CT domains. Our method, XraySyn, can synthesize novel views on real radiographs through a combination of realistic simulation and finetuning on real radiographs. To the best of our knowledge, this is the first work on radiograph view synthesis. We show that by gaining an understanding of radiography in 3D space, our method can be applied to radiograph bone extraction and suppression without groundtruth bone labels.