Denoising diffusion probabilistic models for 3D medical image generation.

Journal: Scientific reports
Published Date: May 5, 2023

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

  • Firas Khader
    Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany.
  • Gustav Müller-Franzes
    From the Department of Diagnostic and Interventional Radiology (F.K., G.M.F., L.H., P.S., S.K., E.B., M.S.H., F.P., M.Z., C.K., P.B., S.N., D.T.), Department of Medicine III (J.K., K.H.), and Clinic for Surgical Intensive Medicine and Intermediate Care (G.M.), University Hospital Aachen, Pauwelsstrasse 30, 52064 Aachen, Germany; Physics of Molecular Imaging Systems, Experimental Molecular Imaging (T.H., V.S.), and Institute of Imaging and Computer Vision (J.S.), RWTH Aachen University, Aachen, Germany; Department of Inner Medicine, Luisenhospital Aachen, Aachen, Germany (L.N.); and Ocumeda AG, Erlen, Switzerland (C.H.).
  • Soroosh Tayebi Arasteh
    Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Pauwelsstr. 30, 52074, Aachen, Germany.
  • Tianyu Han
    Physics of Molecular Imaging Systems, Experimental Molecular Imaging, RWTH Aachen University, Aachen, Germany. tianyu.han@pmi.rwth-aachen.de.
  • Christoph Haarburger
    From the Departments of Diagnostic and Interventional Radiology (D.T., S.S., H.S., C.K.) and Institute of Imaging and Computer Vision (C.H., D.M.), RWTH Aachen University, Aachen, Pauwelsstr 30, 52074 Aachen, Germany.
  • Maximilian Schulze-Hagen
    Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany.
  • Philipp Schad
    Department of Diagnostic and Interventional Radiology, RWTH Aachen University Hospital, Pauwelsstraße 30, 52072, Aachen, Germany.
  • Sandy Engelhardt
  • Bettina Baeßler
    Department of Radiology, University Hospital of Cologne, Cologne, Germany.
  • Sebastian Foersch
    Institute of Pathology, University Medical Center Mainz, Mainz, Germany. Electronic address: sebastian.foersch@unimedizin-mainz.de.
  • Johannes Stegmaier
    Institute for Applied Computer Science, Karlsruhe Institute of Technology, Eggenstein-Leopoldshafen, Germany.
  • Christiane Kuhl
    Department of Diagnostic and Interventional Radiology, University Hospital Düsseldorf, Düsseldorf, Germany (J.S., D.B.A., S.N.); Institute of Computer Vision and Imaging, RWTH University Aachen, Pauwelsstrasse 30, 52072 Aachen, Germany (J.S., D.M.); Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany (D.T., M.P., F.M., C.K., S.N.); and Faculty of Mathematics and Natural Sciences, Institute of Informatics, Heinrich Heine University Düsseldorf, Düsseldorf, Germany (S.C.).
  • Sven Nebelung
    Department of Diagnostic and Interventional Radiology, University Hospital Düsseldorf, Düsseldorf, Germany (J.S., D.B.A., S.N.); Institute of Computer Vision and Imaging, RWTH University Aachen, Pauwelsstrasse 30, 52072 Aachen, Germany (J.S., D.M.); Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany (D.T., M.P., F.M., C.K., S.N.); and Faculty of Mathematics and Natural Sciences, Institute of Informatics, Heinrich Heine University Düsseldorf, Düsseldorf, Germany (S.C.).
  • Jakob Nikolas Kather
    Department of Medicine III, University Hospital RWTH Aachen, Aachen, Germany.
  • Daniel Truhn
    Department of Diagnostic and Interventional Radiology, University Hospital Düsseldorf, Düsseldorf, Germany (J.S., D.B.A., S.N.); Institute of Computer Vision and Imaging, RWTH University Aachen, Pauwelsstrasse 30, 52072 Aachen, Germany (J.S., D.M.); Department of Diagnostic and Interventional Radiology, University Hospital Aachen, Aachen, Germany (D.T., M.P., F.M., C.K., S.N.); and Faculty of Mathematics and Natural Sciences, Institute of Informatics, Heinrich Heine University Düsseldorf, Düsseldorf, Germany (S.C.).

Keywords

External Resources

Popular Topics
Recent Journals