ELIXIR Service. Galaxy Image Analysis is an ELIXIR Service for computer-based image analysis in Galaxy. The goal is to provide all necessary tools to perform image analysis directly within the Galaxy platform.
Contributions are welcome. Please see our contribution instructions if you would like to contribute. Galaxy Image Analysis was initiated and is maintained by the Biomedical Computer Vision (BMCV) Group at Heidelberg University.
Community. Galaxy Image Analysis is used within the Image Analysis Community in Galaxy. Tutorials are available on the Galaxy Training Network. A hands-on video tutorial is available on YouTube (Image Segmentation using Galaxy Workflows). If Galaxy Image Analysis helped with the analysis of your data, please do not forget to cite: https://doi.org/10.1016/j.jbiotec.2017.07.019
Image processing […]
- Apply anisotropic diffusion with MedPy
- Apply a morphological operation with SciPy
- Crop image with giatools
- Filter 2D image with scikit-image
- Perform histogram equalization with scikit-image
- Process images using arithmetic expressions with NumPy
- Remove image background with scikit-image
- Scale image with scikit-image
- Show image info with Bioformats
Image conversion […]
- Concatenate images or channels
- Convert binary image to label map
- Convert binary image to points (center of masses)
- Convert binary image to points (point coordinates)
- Convert coordinates to label map
- Convert image format with Bioformats
- Convert label map to binary image with NumPy
- Convert label map to points (center of masses)
- Convert single-channel to multi-channel image with NumPy
- Convert to OME-Zarr with Bioformats
- Perform color deconvolution or transformation
- Permutate image axes
- Slice image into patches
- Split image along axes with NumPy
- Switch axis coordinates
Segmentation, partitioning, and detection […]
- Compute Voronoi tessellation with scikit-image
- Count objects in label map
- Extract 2D features with scikit-image
- Filter label map by rules
- Merge neighbors in label map
- Perform 2D spot detection
- Perform segmentation in densely packed 3-D volumetric images with PlantSeg
- Perform segmentation using region-based fitting of overlapping ellipses with RFOVE
- Perform segmentation using deformable shape models with SuperDSM
- Split label map using morphological operators
- Threshold image with scikit-image
Registration […]
- Compute image orientation with OrientationPy
- Perform affine image registration (intensity-based)
- Perform affine image registration (landmark-based)
- Performs projective transformation with/without labels
- Performs projective transformation
Tracking […]
Visualization and validation […]
- Colorize labels with NetworkX
- Compute image segmentation and object detection performance measures with SegMetrics
- Evaluate segmentation with EvaluateSegmentation
- Overlay images
- Visualize detections
- Compute image features with Mahotas
- Extract top view with OpenSlide
- Generate ISCC hash with ISCC-SUM
- Perform curve fitting
- Unzip
This work has been funded by the BMFTR (Federal Ministry of Research, Technology and Space), Heidelberg Center for Human Bioinformatics (HD-HuB) within the German Network for Bioinformatics Infrastructure (de.NBI) & ELIXIR-DE, and LiBiS (Baden-Württemberg Institute for Bioinformatics Infrastructure).
