This repository lists BIAFLOWS-compatible workflows that can be run in BIOMERO. These workflows are containerized image analysis tools that can be executed on Slurm clusters via the BIOMERO system.
BIAFLOWS (BioImage Analysis workflows) is a standard for packaging and benchmarking image analysis workflows. These workflows can be integrated with BIOMERO to run automated image analysis on OMERO images using HPC resources.
These workflows have been tested and confirmed to work with BIOMERO:
| Workflow | Tool/Program | Description | License | Repository |
|---|---|---|---|---|
| NucleiSegmentation-Stardist5D | StarDist (Python) | Nuclei segmentation using StarDist with versatile nuclei pre-trained model for 5D images. Uses 2D stardist to segment nuclei in all z and time slices. For large images, automated tiling is applied. | Apache-2.0 | maartenpaul/W_NucleiSegmentation-Stardist5d |
| Segmentation-micro-sam | micro-SAM (Python) | BIAFLOWS container for micro-sam (in development). | Apache-2.0 | maartenpaul/W_Segmentation-micro-sam |
| SpotCounting-CellProfiler | CellProfiler | Spot counting using CellProfiler pipeline. | Unknown | maartenpaul/W_SpotCounting-CellProfiler |
| NucleiSegmentation-Cellpose | Cellpose (Python) | 2D nuclei segmentation using Cellpose version 0.7.2. A generalist algorithm for cell and nucleus segmentation. | Unknown | TorecLuik/W_NucleiSegmentation-Cellpose |
| CellExpansion | Python | Cell expansion workflow. | GPL-3.0 | TorecLuik/W_CellExpansion |
| CountMaskOverlap | Python | Counting granules in cells by providing input in 1 directory with suffixes on pairs of masks. | GPL-3.0 | TorecLuik/W_CountMaskOverlap |
| Measurements-Nuclei-CellProfiler | CellProfiler | Nuclei measurements using CellProfiler. | Apache-2.0 | Cellular-Imaging-Amsterdam-UMC/W_Measurements-Nuclei-CellProfiler |
| Measurements-CellProfiler | CellProfiler | Cell measurements using CellProfiler. | Apache-2.0 | Cellular-Imaging-Amsterdam-UMC/W_Measurements-CellProfiler |
Warning
The workflows listed below have not been officially tested with BIOMERO. Some may require additional configuration or may not be compatible. Workflows that require training/prediction with models stored in Cytomine may not work without additional setup.
| Workflow | Tool/Program | Description | License | Repository |
|---|---|---|---|---|
| NucleiSegmentation-UNet | U-Net (Python) | 3-class U-Net segmentation for nuclei. | Unknown | Neubias-WG5/W_NucleiSegmentation-UNet |
| NucleiSegmentation-CellProfiler | CellProfiler | Nuclei segmentation using CellProfiler 2.2.0. | Unknown | Neubias-WG5/W_NucleiSegmentation-CellProfiler |
| NucleiSegmentation-ilastik | ilastik (Python) | Nuclei segmentation using ilastik and Python. | Unknown | Neubias-WG5/W_NucleiSegmentation-ilastik |
| NucleiSegmentation-MaskRCNN | Mask R-CNN (Python) | Nuclei segmentation using Mask-RCNN deep learning model. | Unknown | Neubias-WG5/W_NucleiSegmentation-MaskRCNN |
| NucleiSegmentation-DeepCell | DeepCell (Python) | Nuclei segmentation workflow using DeepCell 1.0. | Unknown | Neubias-WG5/W_NucleiSegmentation-DeepCell |
| NucleiSegmentation-Python | Python | Python script to segment nuclei. | Unknown | Neubias-WG5/W_NucleiSegmentation-Python |
| Workflow | Tool/Program | Description | License | Repository |
|---|---|---|---|---|
| NucleiSegmentation3D-ImageJ | ImageJ | Segment clustered nuclei using a 3D filter, thresholding and a 3D binary watershed. | Unknown | Neubias-WG5/W_NucleiSegmentation3D-ImageJ |
| NucleiSegmentation3D-ilastik | ilastik (Python) | 3D nuclei segmentation in ilastik. | Unknown | Neubias-WG5/W_NucleiSegmentation3D-ilastik |
| Workflow | Tool/Program | Description | License | Repository |
|---|---|---|---|---|
| SpotDetection-Icy | Icy | Spot detection using Icy software. | Unknown | Neubias-WG5/W_SpotDetection-Icy |
| SpotDetection-IJ | ImageJ/FIJI | Spot detection in FIJI using a LoG filter and the detection of minima. | Unknown | Neubias-WG5/W_SpotDetection-IJ |
| SpotDetection-Dmap-IJ | ImageJ Macro | Distance map based spot detection ImageJ macro. | Unknown | Neubias-WG5/W_SpotDetection-Dmap-IJ |
| SpotDetection-MATLAB | MATLAB | Spot detection using MATLAB. | Unknown | Neubias-WG5/W_SpotDetection-MATLAB |
| Workflow | Tool/Program | Description | License | Repository |
|---|---|---|---|---|
| SpotDetection3D-Icy | Icy | 3D spot detection protocol from Icy. | Unknown | Neubias-WG5/W_SpotDetection3D-Icy |
| SpotDetection3D-IJ | ImageJ | 3D spot-detection with ImageJ. | Unknown | Neubias-WG5/W_SpotDetection3D-IJ |
| SpotDetection3D-Hessian-IJ | ImageJ | 3D spot detection using the determinant of the Hessian. | Unknown | Neubias-WG5/W_SpotDetection3D-Hessian-IJ |
| Workflow | Tool/Program | Description | License | Repository |
|---|---|---|---|---|
| ObjectTracking-MU-Lux-CZ | Python | Object tracking algorithm. | Unknown | Neubias-WG5/W_ObjectTracking-MU-Lux-CZ |
| ObjectTracking-Octave | Octave/MATLAB | Nuclei tracking in 2D time-lapse with Octave tracker (adapted from Matlab LOBSTER version). | Unknown | Neubias-WG5/W_ObjectTracking-Octave |
| ObjectTracking-ImageJ | ImageJ Macro | Object tracking workflow using ImageJ. | Unknown | Neubias-WG5/W_ObjectTracking-ImageJ |
| ObjectTracking-PAST-FR | ImageJ Macro | Object tracking using PAST FR method. | Unknown | Neubias-WG5/W_ObjectTracking-PAST-FR |
| Workflow | Tool/Program | Description | License | Repository |
|---|---|---|---|---|
| NucleiTracking-ImageJ | ImageJ | Track nuclei in a time series using 3D-object segmentation with watershed. | Unknown | Neubias-WG5/W_NucleiTracking-ImageJ |
| NucleiTrackingTrackmate-IJ | TrackMate (ImageJ) | Using Trackmate to track non dividing nuclei in a 2D time-lapse. | Unknown | Neubias-WG5/W_NucleiTrackingTrackmate-IJ |
| Workflow | Tool/Program | Description | License | Repository |
|---|---|---|---|---|
| PartTracking-ImageJ | ImageJ Macro | Particle tracking based on linking closest intensity minima detected from LoG filtered time-lapse. | Unknown | Neubias-WG5/W_PartTracking-ImageJ |
| LogPartTrack_IJ | ImageJ Macro | Particle tracking in 2D time-lapse based on linking closest regional intensity minima with user-defined noise tolerance and maximum linking distance. | Unknown | Neubias-WG5/W_LogPartTrack_IJ |
| Workflow | Tool/Program | Description | License | Repository |
|---|---|---|---|---|
| FilamentTracing3D-ImageJ | ImageJ (Python) | 3D filament tracing with ImageJ. | Unknown | Neubias-WG5/W_FilamentTracing3D-ImageJ |
| FilamentTracing3D_Rivuletpy | Rivuletpy (Python) | Filament tracing using Rivuletpy (or Rivulet2) developed by RivuletStudio. | Unknown | Neubias-WG5/W_FilamentTracing3D_Rivuletpy |
| NeuronTracing_vaa3d_app2 | Vaa3D (Python) | Neuron and tree 3D segmentation using all-path-pruning 2.0 (APP2) of Vaa3D. | Unknown | Neubias-WG5/W_NeuronTracing_vaa3d_app2 |
| NeuronTracing_vaa3d_mst | Vaa3D (Python) | Trace 3D neuron with Vaa3D MST (Minimal Spanning Tree) simple algorithm. | Unknown | Neubias-WG5/W_NeuronTracing_vaa3d_mst |
| NeuronTracing_vaa3d_fastmarching_spanningtree | Vaa3D (Python) | Trace 3D neuron with Vaa3D BJUT Fast Marching Spanning Tree algorithm. | Unknown | Neubias-WG5/W_NeuronTracing_vaa3d_fastmarching_spanningtree |
| Neuron3dTree_vaa3d_most | Vaa3D (Python) | Tree 3D segmentation using MOST Vessel Tracer of Vaa3D. | Unknown | Neubias-WG5/W_Neuron3dTree_vaa3d_most |
| Workflow | Tool/Program | Description | License | Repository |
|---|---|---|---|---|
| PixCla-UNet-GlaS | U-Net (Python) | Pixel classification for GlaS challenge with UNet. | Unknown | Neubias-WG5/W_PixCla-UNet-GlaS |
| PixCla-PSPNet-GlaS | PSPNet (Python) | Neural network PSPNet on GlaS dataset. | Unknown | Neubias-WG5/W_PixCla-PSPNet-GlaS |
| PixCla-UNet-Tuned-GlaS | U-Net (Python) | UNet tuned on a validation set for pixel classification. | Unknown | Neubias-WG5/W_PixCla-UNet-Tuned-GlaS |
| Workflow | Tool/Program | Description | License | Repository |
|---|---|---|---|---|
| LandmarkDetect-ML-LC-Train | Python (ML) | Machine learning landmark detection training. Requires model storage. | Unknown | Neubias-WG5/W_LandmarkDetect-ML-LC-Train |
| LandmarkDetect-ML-LC-Pred | Python (ML) | Machine learning landmark detection prediction. Requires model storage. | Unknown | Neubias-WG5/W_LandmarkDetect-ML-LC-Pred |
| LandmarkDetect-ML-MSET-Train | Python (ML) | Machine learning landmark detection (MSET) training. Requires model storage. | Unknown | Neubias-WG5/W_LandmarkDetect-ML-MSET-Train |
| LandmarkDetect-ML-MSET-Pred | Python (ML) | Machine learning landmark detection (MSET) prediction. Requires model storage. | Unknown | Neubias-WG5/W_LandmarkDetect-ML-MSET-Pred |
| LandmarkDetect-ML-DMBL-Train | Python (ML) | Machine learning landmark detection (DMBL) training. Requires model storage. | Unknown | Neubias-WG5/W_LandmarkDetect-ML-DMBL-Train |
| LandmarkDetect-ML-DMBL-Pred | Python (ML) | Machine learning landmark detection (DMBL) prediction. Requires model storage. | Unknown | Neubias-WG5/W_LandmarkDetect-ML-DMBL-Pred |
To use these workflows with BIOMERO:
- Ensure the workflow is packaged as a BIAFLOWS-compatible container
- Add the workflow configuration to your Slurm configuration file (
slurm-config.ini) - The workflow can then be launched from OMERO.web through the BIOMERO interface
- BIOMERO Main Repository: NL-BioImaging/biomero - Python library for connecting OMERO and Slurm clusters
- BIOMERO Scripts: NL-BioImaging/biomero-scripts - Scripts for use with BIOMERO
- BIAFLOWS Template: Neubias-WG5/W_Template - Template repository for creating new BIAFLOWS workflows
- BIAFLOWS Utilities: Neubias-WG5/biaflows-workflow-utilities - Utilities for simpler BIAFLOWS workflow creation
To add a new workflow to this list, please submit a pull request with:
- Workflow name and description
- Link to the repository
- License information
- Category placement
BIAFLOWS workflows have varying licenses. Tested workflows include Apache-2.0 and GPL-3.0 licenses, while many Neubias-WG5 workflows do not have explicit license files (marked as "Unknown"). Please check individual repositories for specific license information before use.