A visual latent semantic approach for automatic analysis and interpretation of anaplastic medulloblastoma virtual slides

Authors:
Angel Cruz-Roa;Fabio González;Joseph Galaro;Alexander R. Judkins;David Ellison;Jennifer Baccon;Anant Madabhushi;Eduardo Romero
Affiliations:
BioIngenium Research Group, Universidad Nacional de Colombia, Bogotá, Colombia;BioIngenium Research Group, Universidad Nacional de Colombia, Bogotá, Colombia;Department of Biomedical Engineering, Rutgers, Piscataway, NJ;Department of Pathology Lab Medicine, Children Hospital of L.A., Los Angeles, CA;St. Jude Children's Research Hospital from Memphis, TN;Department of Pathology, Penn State College of Medicine, Hershey, PA;Department of Biomedical Engineering, Rutgers, Piscataway, NJ;BioIngenium Research Group, Universidad Nacional de Colombia, Bogotá, Colombia
Venue:
MICCAI'12 Proceedings of the 15th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Year:
2012

Citing 3
Cited 0

Unsupervised learning by probabilistic latent semantic analysis

Machine Learning
Latent dirichlet allocation

The Journal of Machine Learning Research
On the equivalence between Non-negative Matrix Factorization and Probabilistic Latent Semantic Indexing

Computational Statistics & Data Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

A method for automatic analysis and interpretation of histopathology images is presented. The method uses a representation of the image data set based on bag of features histograms built from visual dictionary of Haar-based patches and a novel visual latent semantic strategy for characterizing the visual content of a set of images. One important contribution of the method is the provision of an interpretability layer, which is able to explain a particular classification by visually mapping the most important visual patterns associated with such classification. The method was evaluated on a challenging problem involving automated discrimination of medulloblastoma tumors based on image derived attributes from whole slide images as anaplastic or non-anaplastic. The data set comprised 10 labeled histopathological patient studies, 5 for anaplastic and 5 for non-anaplastic, where 750 square images cropped randomly from cancerous region from whole slide per study. The experimental results show that the new method is competitive in terms of classification accuracy achieving 0.87 in average.