Comput Biol Med 2019 May 6;108:49-56. Epub 2019 Apr 6.
Department of Mathematics and Computer Science of University of La Rioja, Spain. Electronic address:
Background And Objective: Deep learning techniques have been successfully applied to tackle several image classification problems in bioimaging. However, the models created from deep learning frameworks cannot be easily accessed from bioimaging tools such as ImageJ or Icy; this means that life scientists are not able to take advantage of the results obtained with those models from their usual tools. In this paper, we aim to facilitate the interoperability of bioimaging tools with deep learning frameworks.
Methods: In this project, called DeepClas4Bio, we have developed an extensible API that provides a common access point for classification models of several deep learning frameworks. In addition, this API might be employed to compare deep learning models, and to extend the functionality of bioimaging programs by creating plugins.
Results: Using the DeepClas4Bio API, we have developed a metagenerator to easily create ImageJ plugins. In addition, we have implemented a Java application that allows users to compare several deep learning models in a simple way using the DeepClas4Bio API. Moreover, we present three examples where we show how to work with different models and frameworks included in the DeepClas4Bio API using several bioimaging tools - namely, ImageJ, Icy and ImagePy.
Conclusions: This project brings to the table benefits from several perspectives. Developers of deep learning models can disseminate those models using well-known tools widely employed by life-scientists. Developers of bioimaging programs can easily create plugins that use models from deep learning frameworks. Finally, users of bioimaging tools have access to powerful tools in a known environment for them.