Diffusion-based Generative Image Outpainting for Recovery of FOV-Truncated CT Images

TL;DR

This paper introduces a diffusion-based generative model for outpainting truncated chest CT images, significantly improving recovery accuracy with less training data, aiding in precise body composition analysis.

Contribution

The study presents a novel diffusion model for FOV recovery in CT images that outperforms previous methods and requires substantially less training data.

Findings

Model reliably recovers truncated anatomy.

Outperforms previous state-of-the-art methods.

Uses 87% less training data.

Abstract

Field-of-view (FOV) recovery of truncated chest CT scans is crucial for accurate body composition analysis, which involves quantifying skeletal muscle and subcutaneous adipose tissue (SAT) on CT slices. This, in turn, enables disease prognostication. Here, we present a method for recovering truncated CT slices using generative image outpainting. We train a diffusion model and apply it to truncated CT slices generated by simulating a small FOV. Our model reliably recovers the truncated anatomy and outperforms the previous state-of-the-art despite being trained on 87% less data.