Stacked Predictive Sparse Decomposition

Background:

Stacked Predictive Sparse Decomposition is a machine learning algorithm that was initially developed for the classification of distinct regions of microanatomy and histopathology.  Examples can be found as follows,

Description:

This project contains the source code (matlab) for Stacked Predictive Sparse Decomposition that is described in the publication as follows,

  • Hang Chang*, Yin Zhou*, A Borowsky, K Barner, Paul Spellman and Bahram Parvin. “Stacked Predictive Sparse Decomposition for Classification of Histology Sections.”International Journal of Computer Vision (Special Issues on Deep Learning), (2015): 113(1) 3-18.(*Co-First Authors)

It provides API functions, examplar data and a demo function, with which the learnt basis functions from GBM (left) and KIRC (rigth) datasts are illustrated as follows,

GBM DictionaryKIRC Dictionary

And the entire computational pipeline is illustrated as follows,

StackedPSD pileline

Dependencies:

Downloads

Project category: 
Source Code / Software