Stacked Predictive Sparse Decomposition for Classification of Histology Sections

Hang Chang, Yin Zhou, Alexander Borowsky, Kenneth Barner, Paul Spellman, Bahram Parvin
2014 International Journal of Computer Vision  
Image-based classification of histology sections, in terms of distinct components (e.g., tumor, stroma, normal), provides a series of indices for histology composition (e.g., the percentage of each distinct components in histology sections), and enables the study of nuclear properties within each component. Furthermore, the study of these indices, constructed from each whole slide image in a large cohort, has the potential to provide predictive models of clinical outcome. For example,
more » ... ns can be established between the constructed indices and the patients' survival Correspondence to: Hang Chang, hchang@lbl.gov; Bahram Parvin, b_parvin@lbl.gov. Hang Chang and Yin Zhou are Co-First Authors. Hang Chang and Bahram Parvin are Co-Corresponding Authors. information at cohort level, which is a fundamental step towards personalized medicine. However, performance of the existing techniques is hindered as a result of large technical variations (e.g., variations of color/textures in tissue images due to non-standard experimental protocols) and biological heterogeneities (e.g., cell type, cell state) that are always present in a large cohort. We propose a system that automatically learns a series of dictionary elements for representing the underlying spatial distribution using stacked predictive sparse decomposition. The learned representation is then fed into the spatial pyramid matching framework with a linear support vector machine classifier. The system has been evaluated for classification of distinct histological components for two cohorts of tumor types. Throughput has been increased by using of graphical processing unit (GPU), and evaluation indicates a superior performance results, compared with previous research. In the context of computer vision research on image categorization, the traditional bag of features (BoF) model has been widely studied and improved through different variations Chang et al.
doi:10.1007/s11263-014-0790-9 pmid:27721567 pmcid:PMC5051579 fatcat:m2uwfsks6nd47kfiy6xcfhm22m