Fluorescently-labelled zebrafish pronephroi + ground truth classes (normal/cystic) + trained CNN model

This upload contains :

- images.zip:  microscope images of fluorescently-labelled pronephroi in larvae of the Tg(wt1b:EGFP) transgenic zebrafish line showing 2 morphologies (normal vs cystic) upon injection with Co-Mo or ift172-MO, respectively. Images were obtained using  an ACQUIFER Imaging Machine widefield high content screening microscope.

Reference: 

Pandey, G., Westhoff, J., Schaefer, F. and Gehrig, J. (2019). A Smart Imaging Workflow for Organ-Specific Screening in a Cystic Kidney Zebrafish Disease Model. International Journal of Molecular Sciences 20, 1290, doi:10.3390/ijms20061290.

- Annotations-***.csv : Tables containing ground-truth category classes (normal vs cystic) for the images in the zip file.

The tables contain columns with the image filename, folder and category.

Note : the Folder column should be updated with the root folder directory once downloaded on your machine.

These files were generated with the Fiji plugin single-class (button) from the Qualitative-Annotations update site.

The 2 files contain the same information, they only differ in the formatting of the category, the singleColumn file has a single category column while the multiColumn has 2 columns (normal/cystic) with 0/1 encoding.

The choice of category encoding solely depends on how the table is used, i.e. in which training workflow, home-made script or software.

- trainedModel.zip : This archive contains 2 files: (1) a h5 file corresponding to a trained deep-learning model to classify the images of the dataset in the 2 categories (normal vs cystic), and (2) a text file containing the class names. Both files are necessary to predict the category of new images similar to the one in the dataset, for instance using the published KNIME workflows.