JHancox

A slightly different use-case is when you tile the input and the thresholded output is binary per tile. This results in the same low-res binary mask but is accomplished in...

The purpose of the binary mask (foreground/background) is the same as usual - to eliminate the background from any computation. The way it might work is: - Ingest the WSI...

Hi @KumoLiu , So, I'm probably making it sound more complicated that it is! If you have an input image of say 1000 x 1000 (x3) and you want to...

> Hi @JHancox , > > I would suggest to put this loss implementation in: https://github.com/Project-MONAI/MONAI/tree/dev/monai/apps/pathology /losses/hovernet_loss.py > > What do you think? > > Thanks. Thanks @Nic-Ma - I...

Thanks @Nic-Ma. You are right - the loss is specific to Hovernet. I have no problem redirecting this to apps but will leave the decision to @drbeh

> Hi @benjamin-gorman , > > As your error message shows: _Module 'HoVerNetLoss' has no attribute 'sobel' (This attribute exists on the Python module, but we failed to convert Python...

> Is it ready for review now? > > Thanks. I just need to check with @drbeh whether there was anything else. Will try to get an answer today (in...

I think @drbeh may have already tackled the last Common Transform ("Calculate the distance from sequence...") The first 2 HNet-specific Transforms are to do with representing contours. There may be...

Sorry - inadvertantly closed the PR

What I was trying to do was to comment that I don't recall seeing that same effect (i.e. the instance segmentation difference), so just wondering whether it really is just...