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. This approach holds great promise in streamlining the data generation process and enabling a more efficient and scalable training of segmentation models, as we show in the example of different practical experiments involving various organisms and cell types.
@article{arxiv.2301.10227,
title = {Denoising Diffusion Probabilistic Models for Generation of Realistic Fully-Annotated Microscopy Image Data Sets},
author = {Dennis Eschweiler and Rüveyda Yilmaz and Matisse Baumann and Ina Laube and Rijo Roy and Abin Jose and Daniel Brückner and Johannes Stegmaier},
journal= {arXiv preprint arXiv:2301.10227},
year = {2023}
}