BATS: Bioimage Annotation Tool for Segmentation
A Bioimage Annotation Tool for Segmentation for all-kinds segmentation in microscopy imaging
How to use it?
The client and server communicate via the bentoml library. The client interacts with the server every time we run model inference or training. For full functionality of the software the server should be running, either locally or remotely.
To install and start the server side follow the instructions described in BATS Server. To run the client GUI follow the instructions described in BATS Client
BATS handles all kinds of segmentation tasks! Try it out if you need to do:
Instance segmentation
Semantic segmentation
Multi-class instance segmentation
Toy data
Our github repo includes the data/ directory with some toy data which you can use as the Uncurated dataset folder. You can create (empty) folders for the other two directories required in the welcome window and start playing around.
Enabling data centric development
Our platform encourages the use of data centric practices. With the user friendly client interface you can:
Detect and remove outliers from your training data: only confirmed samples are used to train our models
Detect and correct labeling errors: editing labels with the integrated napari visualisation tool
AI-assisted labelling: Apply any changes to your labels faster using SAM prompts
Auto cleanup: Left over pixels remaining after using the eraser tool or an object your forgot to add a class label to? BATS will let you know and clean everything up for you!
Establish consensus: allows for multiple annotators before curated label is passed to train model
Focus on data curation: no interaction with model parameters during training and inference
Get more with less!
BATS Imaging Conventions
BATS currently follows the imaging conventions described below:
Only 2D images are accepted
The accepted imaging formats are:
(".jpg", ".jpeg", ".png", ".tiff", ".tif")RGB and RGBA images are accepted, however they will be converted to grayscale after read into BATS. The dims can be [C, H, W] or [H, W, C]
Existing segementations can be used, however they need to be TIFF files and have the same name as the corresponding image followed by ‘_seg’, e.g. image1_seg.tiff