Add Post-processing Transforms in MONAI for Nuclei Prediction

[KumoLiu]

Description
It is an overall PR created to track the progress of adding post-processing transforms in MONAI.

Describe the solution you'd like
Several post-processing transforms need to be added to MONAI which I simply divided into two categories.

• Common transforms which can be integrated into MONAI core
• HoVerNet-specific transforms which can be integrated into apps/pathology/transforms

Tasks

Common transforms:

• Get a bounding box BoundingRect
• Remove small objects RemoveSmallObjects
• Sobel Gradients Operator #5015
• Process NP branch output(an output branch in HoVerNet) which turns the probability map from the network into the instance segmentation result #5310
• Transform to Threshold Image for Tissue #4181

HoVerNet-specific transforms:

• Converts Scipy-style contours to a more succinct version which only includes the pixels to which lines need to be drawn (i.e. not the intervening pixels along each line) #5178
• Given the previous and current border positions, returns the int pixel that marks the extremity of the segmented pixels #5179
• Post-process script for HoVerNet #5180

Additional context
There is already a draft implementation in the tutorial repo refer to Project-MONAI/tutorials#890.
Related PR: #4181
Related Issues: #4180

cc @wyli @Nic-Ma @drbeh @JHancox @shaneahmed

[JHancox]

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 a different representation that we would prefer to adopt. This one just provides compatibility with the existing OpenCV-based outputs (which are better, IMHO, than SciPy's)

[shaneahmed]

Hi @KumoLiu, I think we will need to discuss on how to take this forward. i.e., which of the post processing algorithms to be made part of MONAI. As most of the post-processing algorithms are available in libraries like scikit-learn/image e.g., peak detection, distance transform etc. If there is GPU optimization then probably it should be part of MONAI. One of these as @JHancox mentioned is to generate contours from segmentation masks which can be optimized.