Hi, I recently finished the deep learning specialization course and wanted to try implementing some of the concepts using the public PANDAS dataset (PANDAs which is classification of prostate cancer grade from whole slide H&E images. However, I’m not entirely sure where to start with this, so I’m looking for advice.
Does anyone have recommendations on a general workflow I should follow to get the data into a usable format and then try out basic classification?
First thing that comes into my mind are some free courses on Kaggle about data preparation, if the Labs you have done in DLS dont have a comprehensive data preprocessing steps!
Yeah, thanks. Its, going from fairly preprared data to gigapixel data that I wasn’t familar with. I’ll find some better information on how that is generally processed.
+1 for @gent.spah ‘s recommendation. You might also take a look at papers on similar efforts and see if there are discussions of the approach they used.
For example