DeepImageJ is a user-friendly solution that enables the generic use of pre-trained deep learning models for biomedical image analysis in ImageJ. The deepImageJ environment gives access to the largest bioimage repository of pre-trained deep learning models (BioImage Model Zoo). Hence, nonexperts can easily perform common image processing tasks in life-science research with deep learning-based tools including pixel and object classification, instance segmentation, denoising or virtual staining. DeepImageJ is compatible with existing state of the art solutions and it is equipped with utility tools for developers to include new models. Very recently, several training frameworks have adopted the deepImageJ format to deploy their work in one of the most used softwares in the field (ImageJ). Beyond its direct use, we expect deepImageJ to contribute to the broader dissemination and reuse of deep learning models in life sciences applications and bioimage informatics.
This is a preview of subscription content
Subscribe to Journal
Get full journal access for 1 year
only $9.92 per issue
All prices are NET prices.
VAT will be added later in the checkout.
Tax calculation will be finalised during checkout.
Rent or Buy article
Get time limited or full article access on ReadCube.
All prices are NET prices.
All data that were used to generate the figures in this paper are available at https://deepimagej.github.io/deepimagej/.
We used TensorFlow and PyTorch libraries for Python to create the in-house models shown in the figures. The deepImageJ plugin can be used in ImageJ and Fiji. The source code for the plugin together with its releases is provided at https://github.com/deepimagej/deepimagej-plugin. The pydeepimagej Python package is provided at https://github.com/deepimagej/pydeepimagej. The ImageJ macro files can be accessed at https://github.com/deepimagej/imagej-macros. All source code is under a BSD 2-Clause License. The web page https://deepimagej.github.io/deepimagej/provides free access to the ImageJ plugin, along with the bundled models and user guide for image processing.
Meijering, E. A bird’s-eye view of deep learning in bioimage analysis. Computational Struct. Biotechnol. J. 18, 2312 (2020).
Moen, E. et al. Deep learning for cellular image analysis. Nat. Methods 16, 1233–1246 (2019).
Schroeder, A. B. et al. The ImageJ ecosystem: Open-source software for image visualization, processing, and analysis. Protein Sci. 30, 234–249 (2020).
Deep learning gets scope time. Nat. Methods 16, 1195 (2019).
Lucas, A. M. et al. Open-source deep-learning software for bioimage segmentation. Mol. Biol. Cell 32, 823–829 (2021).
Weigert, M. et al. Content-aware image restoration: pushing the limits of fluorescence microscopy. Nat. Methods 15, 1090–1097 (2018).
Inés, A., Domínguez, C., Heras, J., Mata, E. & Pascual, V. DeepClas4Bio: Connecting bioimaging tools with deep learning frameworks for image classification. Computers Biol. Med. 108, 49–56 (2019).
Berg, S. et al. Ilastik: interactive machine learning for (bio)image analysis. Nat. Methods 16, 1226–1232 (2019).
Ouyang, W., Mueller, F., Hjelmare, M., Lundberg, E. & Zimmer, C. ImJoy: an open-source computational platform for the deep learning era. Nat. Methods 16, 1199–1200 (2019).
von Chamier, L. et al. Democratising deep learning for microscopy with ZeroCostDL4Mic. Nat. Commun. 12, 2276 (2021).
Fäßler, F. et al. Cryo-electron tomography workflows for quantitative analysis of actin networks involved in cell migration. Microsc. Microanalysis 26, 2518–2519 (2020).
Midtvedt, B. et al. Quantitative digital microscopy with deep learning. Appl. Phys. Rev. 8, 011310 (2021).
Schneider, C. A., Rasband, W. S. & Eliceiri, K. W. NIH Image to ImageJ: 25 years of image analysis. Nat. Methods 9, 671–675 (2012).
Schmidt, U., Weigert, M., Broaddus, C. & Myers, G. Cell detection with star-convex polygons. In Medical Image Computing and Computer Assisted Intervention – MICCAI 2018 – 21st International Conference, Granada, Spain, September 16–20, 2018, Proceedings, Part II 265–273 (Springer, 2018).
Rivenson, Y. et al. Virtual histological staining of unlabelled tissue-autofluorescence images via deep learning. Nat. Biomed. Eng. 3, 466–477 (2019).
Falk, T. et al. U-Net: deep learning for cell counting, detection, and morphometry. Nat. Methods 16, 67–70 (2019).
Nehme, E., Weiss, L. E., Michaeli, T. & Shechtman, Y. Deep-STORM: super-resolution single-molecule microscopy by deep learning. Optica 5, 458–464 (2018).
Caicedo, J. C. et al. Nucleus segmentation across imaging experiments: the 2018 data science bowl. Nat. Methods 16, 1247–1253 (2019).
Gómez-de-Mariscal, E. et al. Deep-learning-based segmentation of small extracellular vesicles in transmission electron microscopy images. Sci. Rep. 9, 13211 (2019).
Tsai, H.-F., Gajda, J., F.W. Sloan, T., Rares, A. & Shen, A. Q. Usiigaci: Instance-aware cell tracking in stain-free phase contrast microscopy enabled by machine learning. SoftwareX 9, 230–237 (2019).
Gómez-de-Mariscal, E., Franco, D., Muñoz-Barrutia, A. & Arganda-Carreras, I. in Bioimage Analysis Components and Workflows (eds Sladoje, N. & Miura, K.) (Springer, 2021).
Schindelin, J. et al. Fiji: an open-source platform for biological-image analysis. Nat. Methods 9, 676–682 (2012).
Rueden, C. T. et al. ImageJ2: ImageJ for the next generation of scientific image data. BMC Bioinformatics 18, 529 (2017).
We thank P. M. Gordaliza, I. Arganda-Carreras (tested the beta-versions), D. F. González-Obando (tested the beta-versions), C. Rueden, S. Tosi, T. Pengo (tested the beta-versions), R. Henriques (ZeroCostDL4Mic), R. F. Laine (ZeroCostDL4Mic), G. Jacquemet (ZeroCostDL4Mic), D. Krentzel (ZeroCostDL4Mic) and C. Möhl (YAPIC) for the fruitful discussions and enriching feedback about the deepImageJ project. We would also like to thank NEUBIAS for supporting the project, the NEUBIAS symposium and NEUBIAS Academy@Home and P. Rasti and S. Bollmann for including deepImageJ in their tutorials. We would like specially to mention all the contributors and community partners at the BioImage Model Zoo for the time they have spent to get a cross-compatible model format. We acknowledge the support of Ministerio de Ciencia, Innovación y Universidades, Agencia Estatal de Investigación, under grant nos TEC2016-78052-R and PID2019-109820RB-I00, MINECO/FEDER, UE, co-financed by European Regional Development Fund (ERDF), ‘A way of making Europe’ (E.G.M., C.G.L.H., A.M.B.), and a 2017 Leonardo Grant for Researchers and Cultural Creators, BBVA Foundation (A.M.B.). This work was also supported by the EPFL Center for Imaging (C.G.L.H., L.D., D.S., M.U.). We would like to thank the Science for Life Laboratory, Erling-Persson Foundation and Knut and Alice Wallenberg foundation (grant no. 2018.0172) (W.O., E.L.). We thank the program ‘Short Term Scientific Missions’ of NEUBIAS (network of European bioimage analysts) (E.G.M., C.G.L.H.). We also want to acknowledge the support of NVIDIA Corporation with the donation of the Titan X (Pascal) GPU card used for this research (A.M.B.).
The authors declare no competing interests.
Peer review information Rita Strack was the primary editor on this article and managed its editorial process and peer review in collaboration with the rest of the editorial team.
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
About this article
Cite this article
Gómez-de-Mariscal, E., García-López-de-Haro, C., Ouyang, W. et al. DeepImageJ: A user-friendly environment to run deep learning models in ImageJ. Nat Methods 18, 1192–1195 (2021). https://doi.org/10.1038/s41592-021-01262-9