Three-Dimensional Medical Image Synthesis with Denoising Diffusion Probabilistic Models

Zolnamar Dorjsembe, Sodtavilan Odonchimed, Furen Xiao

Keywords: Diffusion models, image synthesis, 3D MRI

TL;DR: This work presents a 3D-DDPM for generating three-dimensional medical images.

Abstract: Denoising diffusion probabilistic models (DDPM) have recently shown superior performance in image synthesis and have been extensively studied in various image processing tasks. In this work, we propose a 3D-DDPM for generating three-dimensional (3D) medical images. Different from previous studies, to the best of our knowledge, this work presents the first attempt to investigate the DDPM to enable 3D medical image synthesis. We investigated the generation of high-resolution magnetic resonance images (MRI) of brain tumors. The proposed method is evaluated through experiments on a semi-public dataset, with both quantitative and qualitative tests showing promising results.

Registration: I acknowledge that acceptance of this work at MIDL requires at least one of the authors to register and present the work during the conference.

Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.

Paper Type: novel methodological ideas without extensive validation

Primary Subject Area: Image Synthesis

Secondary Subject Area: Unsupervised Learning and Representation Learning

Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.

Code And Data: https://github.com/DL-Circle/3D-DDPM