Bridging the Gap: Integrating Cutting-edge Techniques into Biological Imaging with deepImageJ
Published in bioRxiv, 2023
Recommended citation: Fuster-Barceló, C., García López de Haro, C., Gómez-de-Mariscal, E., Ouyang, W., Olivo-Marin, J.C., Sage, D., & Muñoz-Barrutia, A. (2024). Bridging the Gap: Integrating Cutting-edge Techniques into Biological Imaging with deepImageJ. *bioRxiv*. https://doi.org/10.1101/2024.01.12.575015 https://www.biorxiv.org/content/10.1101/2024.01.12.575015v1.abstract
Bridging the Gap: Integrating Cutting-edge Techniques into Biological Imaging with deepImageJ
This work presents the latest developments in deepImageJ, a powerful and user-friendly Fiji/ImageJ plugin that enables researchers to apply state-of-the-art deep learning models for biological image analysis without writing code.
🔍 Highlights:
- Multi-framework support through the Java Deep Learning Library (JDLL), enabling the execution of TensorFlow, PyTorch, and ONNX models within one environment.
- Seamless handling of 3D image data, large-scale images, and multi-model pipelines.
- Real-world case studies that illustrate:
- Integrated image-to-image translation + nuclei segmentation
- 3D nuclei segmentation workflows
- Large image segmentation performance
💡 Why it matters:
By lowering the entry barrier for applying AI in microscopy, deepImageJ empowers life scientists, clinicians, and analysts to integrate AI into their workflows—no engineering background required. This bridges a critical gap between deep learning model developers and experimental researchers, fostering broader interdisciplinary collaboration.
Links
📄 bioRxiv Preprint
🧠 deepImageJ Plugin Overview
💻 GitHub Repository