For a few years now I have been on a quest to find a tool I really like for annotating HCS images using a web interface. I've used several tools, including a desktop application called LabelImg, and I have finally found a tool that checks all the boxes called LabelStudio!
Label Studio is an annotation tool for images, audio, and text. Here we'll be concentrating on images as our medium of choice.
I go through the process in this video.
You can, of course, use your own data, but for this tutorial I will be using a publically available C. elegans dataset from the Broad BioImage Benchmark Collection.
mkdir data cd data wget https://data.broadinstitute.org/bbbc/BBBC010/BBBC010_v2_images.zip unzip BBBC010_v2_images.zip
HCS images are often very dark when opened in a system viewer. To use them for the rest of the pipeline we will have to do a two step conversion process, first using bftools to convert from tif -> png, and then using Imagmagick to do a levels...
Subscribe to the newsletter! You'll get a weekly tutorial on all the DevOps you need to know as a Data Scientist. Build Python Apps with Docker, Design and Deploy complex analyses with Apache Airflow, build computer vision platforms, and more.