Bioimage analysis in Python
Bioimage analysis in Python
to be announced
General context
Microscopy generates complex, multi-dimensional image data that requires efficient analysis to extract meaningful biological insights. This hands-on training teaches you practical skills for handling and processing microscopy images using Python.
You will learn to visualize, manipulate, and analyze image data using tools such as Napari, allowing you to explore 2D and 3D datasets interactively. With built-in tools like Cellpose and Noise2Void, you will learn to leverage deep learning methods for bioimage analysis tasks like image segmentation and quantitative analysis.
Navigate the Napari interface to visualize and interact with multi-dimensional microscopy images
Import and export image data using Napari and Python libraries (e.g., bioio, NumPy) while preserving metadata
Apply basic image processing techniques (e.g., filtering, intensity adjustments) within Napari
Compute and plot quantitative descriptors (e.g., intensity histograms, object counts) for segmented images to support data analysis.
Segment microscopy images using both classical approaches and automated tools to identify biological objects.
Generate simple animations to communicate image analysis results.
This course uses a strong hands-on approach with guided exercises in Napari. We install and use Napari plugins to extend functionality for segmentation and analysis tasks.
Basic knowledge of Python programming and ability to work with Python environments (understanding of syntax, data structures, data handling, and basic plotting. This can be acquired by completing our Python introduction e-learning. Send a mail to trainingandconferences@vib.be and we'll give you access to the material.
- Napari
- The libraries covered will be CellPose, scikit-image, bioio (list non-exhaustive)
This course is part of the learning path Bioimaging.
AI methods used
The course covers deep learning methods for bioimage analysis, including Cellpose for object segmentation and Noise2Void, a self-supervised neural network for image denoising. It also introduces classical image processing methods for comparison with machine learning–based approaches.
