Denoising diffusion probabilistic models for 3D medical image generation

Khader F, Müller-Franzes G, Tayebi Arasteh S, Han T, Haarburger C, Schulze-Hagen M, Schad P, Engelhardt S, Baeßler B, Foersch S, Stegmaier J, Kuhl C, Nebelung S, Jakob Nikolas K, Truhn D (2023)

Publication Language: English

Publication Type: Journal article, Original article

Publication year: 2023

Journal

Scientific Reports Nature Publishing Group: Open Access Journals - Option B

Book Volume: 13

Pages Range: 7303 (non-FAU publication)

DOI: 10.1038/s41598-023-34341-2

Open Access Link: https://www.nature.com/articles/s41598-023-34341-2

Abstract

Recent advances in computer vision have shown promising results in image generation. Diffusion probabilistic models have generated realistic images from textual input, as demonstrated by DALL-E 2, Imagen, and Stable Diffusion. However, their use in medicine, where imaging data typically comprises three-dimensional volumes, has not been systematically evaluated. Synthetic images may play a crucial role in privacy-preserving artificial intelligence and can also be used to augment small datasets. We show that diffusion probabilistic models can synthesize high-quality medical data for magnetic resonance imaging (MRI) and computed tomography (CT). For quantitative evaluation, two radiologists rated the quality of the synthesized images regarding "realistic image appearance", "anatomical correctness", and "consistency between slices". Furthermore, we demonstrate that synthetic images can be used in self-supervised pre-training and improve the performance of breast segmentation models when data is scarce (Dice scores, 0.91 [without synthetic data], 0.95 [with synthetic data]).

Authors with CRIS profile

Soroosh Tayebi Arasteh Lehrstuhl für Informatik 5 (Mustererkennung)

Involved external institutions

Universitätsmedizin der Johannes Gutenberg-Universität Mainz DE Germany (DE) Julius-Maximilians-Universität Würzburg DE Germany (DE) Universitätsklinikum Aachen (UKA) DE Germany (DE) Rheinisch-Westfälische Technische Hochschule (RWTH) Aachen DE Germany (DE) Universitätsklinikum Heidelberg DE Germany (DE) Technische Universität Dresden DE Germany (DE)

How to cite

APA:

Khader, F., Müller-Franzes, G., Tayebi Arasteh, S., Han, T., Haarburger, C., Schulze-Hagen, M.,... Truhn, D. (2023). Denoising diffusion probabilistic models for 3D medical image generation. Scientific Reports, 13, 7303 (non-FAU publication). https://doi.org/10.1038/s41598-023-34341-2

MLA:

Khader, Firas, et al. "Denoising diffusion probabilistic models for 3D medical image generation." Scientific Reports 13 (2023): 7303 (non-FAU publication).

BibTeX: Download