Denoising diffusion probabilistic models for generation of realistic fully-annotated microscopy image datasets

PLoS Computational Biology, vol. 20, pp. e1011890

Abstract

Recent advances in computer vision have led to significant progress in the generation of realistic image data, with denoising diffusion probabilistic models proving to be a particularly effective method. In this study, we demonstrate that diffusion models can effectively generate fully-annotated microscopy image data sets through an unsupervised and intuitive approach, using rough sketches of desired structures as the starting point. The proposed pipeline helps to reduce the reliance on manual annotations when training deep learning-based segmentation approaches and enables the segmentation of diverse datasets without the need for human annotations. We demonstrate that segmentation models trained with a small set of synthetic image data reach accuracy levels comparable to those of generalist models trained with a large and diverse collection of manually annotated image data, thereby offering a streamlined and specialized application of segmentation models.

Authors 8

1. Dennis Eschweiler corresponding Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Institute of Imaging and Computer Vision, Aachen, Germany

2. Rüveyda Yilmaz Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Institute of Imaging and Computer Vision, Aachen, Germany

3. Matisse Baumann Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Institute of Imaging and Computer Vision, Aachen, Germany

4. Ina Laube Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Institute of Imaging and Computer Vision, Aachen, Germany

5. Rijo Roy Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Institute of Imaging and Computer Vision, Aachen, Germany

6. Abin Jose Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Institute of Imaging and Computer Vision, Aachen, Germany

7. Daniel Brückner Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Institute of Imaging and Computer Vision, Aachen, Germany

8. Johannes Stegmaier corresponding Aachen Institute of Imaging & Computer Vision

   RWTH Aachen University

   Affiliation as printed

   RWTH Aachen University, Institute of Imaging and Computer Vision, Aachen, Germany