Predictive sparse morphometric context for classification of histology sections

Classification of histology sections from large cohorts, in terms of distinct regions of microanatomy (e.g., tumor, stroma, normal), enables the quantification of tumor composition, and the construction of predictive models of the clinical outcome. To tackle the batch effects and biological heterogeneities that are persistent in large cohorts, sparse cellular morphometric context has recently been developed for invariant representation of the underlying properties in the data, which summarizes cellular morphometric features at various locations and scales, and leads to a system with superior performance for classification of microanatomy and histopathology. However, the sparse optimization protocol for the calculation of sparse cellular morphometric features is not scalable for large scale classification. To improve the scalability of systems, based on sparse morphometric context, we propose the predictive sparse morphometric context in place of the original implementation, which approximates the sparse cellular morphometric feature through a non-linear regressor that is jointly learned with an over-complete dictionary in an unsupervised manner. Experimental results indicates over 50 times speedup compared to our previous implementation with the help of non-linear regressor; while producing competitive performance.