BIOMEDICAL IMAGING GROUP (BIG)
Laboratoire d'imagerie biomédicale (LIB)

DeepImageJ: Bridging Deep Learning to ImageJ

E. Gómez-de-Mariscal, C. García-López-de-Haro, L. Donati, M. Unser, A. Muñoz Barrutia, D. Sage

Fourth Network of European Bioimage Analysts Conference & Symposium (NEUBIAS'20), Bordeaux, French Republic, March 4-6, 2020.

Machine learning (ML), and in particular, Deep Neural Networks (DNN), have become an inflection point in many areas of scientific research. In the case of biomedical image analysis, these new techniques provide significant improvements in most of the tasks such as denoising, super-resolution, segmentation, detection, tracking, response prediction or computer-aided diagnosis.

Nonetheless, the use of DNN models requires previous programming knowledge and expertise, which makes them unapproachable to the general public. Therefore, the spread of this technology to the scientific community is strongly limited. We present DeepImageJ [1], a user-friendly plugin of FIJI/ImageJ, as an alternative solution to target this imminent necessity. DeepImageJ is designed as a standard ImageJ plugin with the technicalities hidden behind a user-friendly interface. It has the potential to make available many of the powerful algorithms for image processing that are continuously being developed and published, enhancing research. While the plugin is thought to import TensorFlow and Keras models, currently there exist python routines to convert other Pyhton-based models such as Pytorch, into a format compatible to DeepImageJ.

The plugin is built at two different levels: (1) a model importer tool that gather from developers all critical information to get a correct image processing, and (2) a user-oriented tool that run a selected model on an image batch. This design facilitates the use of DNN models by end-users. Furthermore, the plugin can be called in a standard ImageJ macro which permits its inclusion in image analysis workflows.

As part of this project, we have also made available a web page (https://deepimagej.github.io/deepimagej/) that serves as a model repository that can benefit both image processing users and developers.

References

  1. E. Gómez-de-Mariscal, C. García-López-de-Haro, L. Donati, M. Unser, A. Arrate Muñoz-Barrutia, "DeepImageJ: A User-Friendly Plugin to Run Deep Learning Models in ImageJ," bioRxiv 799270, https://doi.org/10.1101/799270, October 16, 2019. 

@INPROCEEDINGS(http://bigwww.epfl.ch/publications/gomezdemariscal2001.html,
AUTHOR="G{\'{o}}mez-de-Mariscal, E. and
	Garc{\'{i}}a-L{\'{o}}pez-de-Haro, C. and Donati, L. and Unser, M.
	and Mu{\~{n}}oz-Barrutia, A. and Sage, D.",
TITLE="{DeepImageJ}: {B}ridging Deep Learning to {ImageJ}",
BOOKTITLE="Fourth Network of European Bioimage Analysts Conference \&
	Symposium ({NEUBIAS'20})",
YEAR="2020",
editor="",
volume="",
series="",
pages="",
address="Bordeaux, French Republic",
month="March 4-6,",
organization="",
publisher="",
note="")
© 2020 NEUBIAS. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from NEUBIAS. This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.