I am using the Orange platform and am trying a use case for scoring cancer cellularity in images.
Some facts about the training set:
Consists of 2K~ TIF images, for which (2) labels exist: the RID (region) and Score (toxicity) are numerically labeled in a ground truth CSV.
There are 77 possible regions (RID) and 31 values in the range of toxicity scores (integers and decimal between 0 and 1) from which these 2K training images are labeled. (0 = no toxic cells present, vs. 1 = 100% toxic cellularity)
The images are based on about 32 different patients (for which a patient ID exists, but not needed at this time, since I need to be able to score on unknown patient images)
RID = the region from where the biopsy was taken from. That said, a toxic (.50 score) sample from let’s say RID #1 could look very different from an equivalent .50 toxicity sampled from RID # 77. (this can be due to the level of fat/muscle existing within or not, in a particular region).
I need to train a model, that can predict scores of any non-labeled images submitted to it, to give the highest probability of the Score. In the end, I need to be able to run inference on the model once complete, using random batches of images.
My advisor believes this can simply be achieved via a regression model; I would like to demonstrate via Orange if possible.
I have uploaded a directory to (100) images along with a CSV with labels; please find here: https://drive.google.com/file/d/1g1CfgeJzKfVH03vWUM-JOidkUWfmknSt/view