Nature Methods
Carlos García López de Haro, Stéphane Dallongeville, Thomas Musset, Estibaliz Gómez-de-Mariscal, Daniel Sage, Wei Ouyang, Arrate Muñoz-Barrutia, Jean-Yves Tinevez & Jean-Christophe Olivo-Marin
Abstract
The advancements in artificial intelligence (AI) technology over the past decade have been a breakthrough in imaging for life sciences, paving the way for novel methods in image restoration, reconstruction and segmentation. However, the wide adoption of deep learning (DL) techniques by end users in bioimage analysis is hindered by the complexity of their deployment. These techniques stem from a variety of rapidly evolving frameworks (for example, TensorFlow, PyTorch) that come with distinct and often conflicting setups, which
can discourage even proficient developers. This has led to integration difficulties or even
absence in mainstream bioimage informatics platforms such as ImageJ, Icy and Fiji, many of
which are primarily developed in Java. We present JDLL ( Java Deep Learning Library), a Java library that provides a comprehensive toolkit and application programming interface (API) for crafting advanced scientific applications and image analysis pipelines with DL capabilities. JDLL streamlines the installation, maintenance and execution of DL models
across any major DL frameworks.
More information at DOI: https://doi.org/10.1038/s41592-023-02129-x
Comentários