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

Michelle Espranita Liman, Daniel Rueckert, Florian J. Fintelmann, Philip Müller
6/7/2024
eess.IVcs.CVcs.LG

No official code found. Best implementation: michelleespranita/ct_palette (9 stars, MIT, last commit 2024-11-25).

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.

View on arXivView PDF

Code Implementations(1)

michelleespranita/ct_paletteCommunity100%
MIT

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

93PythonJul 2, 20241 years agoMIT

Cite this paper

@article{liman2024diffusionbased,
  title  = {Diffusion-based Generative Image Outpainting for Recovery of FOV-Truncated CT Images},
  author = {Michelle Espranita Liman and Daniel Rueckert and Florian J. Fintelmann and Philip Müller},
  year   = {2024},
  eprint = {2406.04769},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2406.04769v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2406.04769.svg)](https://codeofpaper.com/paper/2406.04769)

Discussion