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,

And the entire computational pipeline is illustrated as follows,

Dependencies:

• SPAMS
• minFunc