Identification of tumor epithelium and stroma in tissue microarrays using texture analysis

Esa Rahtu,Juho Konsti,Riku Turkki,Johan Lundin,Nina Linder,Caj Haglund,Mikael Lundin,Stig Nordling,Timo Ahonen,Matti Pietikäinen

doi:10.1186/1746-1596-7-22

Abstract

BackgroundThe aim of the study was to assess whether texture analysis is feasible for automated identification of epithelium and stroma in digitized tumor tissue microarrays (TMAs). Texture analysis based on local binary patterns (LBP) has previously been used successfully in applications such as face recognition and industrial machine vision. TMAs with tissue samples from 643 patients with colorectal cancer were digitized using a whole slide scanner and areas representing epithelium and stroma were annotated in the images. Well-defined images of epithelium (n = 41) and stroma (n = 39) were used for training a support vector machine (SVM) classifier with LBP texture features and a contrast measure C (LBP/C) as input. We optimized the classifier on a validation set (n = 576) and then assessed its performance on an independent test set of images (n = 720). Finally, the performance of the LBP/C classifier was evaluated against classifiers based on Haralick texture features and Gabor filtered images.ResultsThe proposed approach using LPB/C texture features was able to correctly differentiate epithelium from stroma according to texture: the agreement between the classifier and the human observer was 97 per cent (kappa value = 0.934, P < 0.0001) and the accuracy (area under the ROC curve) of the LBP/C classifier was 0.995 (CI95% 0.991-0.998). The accuracy of the corresponding classifiers based on Haralick features and Gabor-filter images were 0.976 and 0.981 respectively.ConclusionsThe method illustrates the capability of automated segmentation of epithelial and stromal tissue in TMAs based on texture features and an SVM classifier. Applications include tissue specific assessment of gene and protein expression, as well as computerized analysis of the tumor microenvironment.Virtual slidesThe virtual slide(s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/4123422336534537

Highlights

The aim of the study was to assess whether texture analysis is feasible for automated identification of epithelium and stroma in digitized tumor tissue microarrays (TMAs)
The local binary patterns (LBP)/C, Haralick and Gabor texture classifiers were optimized on the validation set of 576 colorectal cancer microscopy images
Optimization was done by computing the accuracy over a set of cost parameter values, C for the linear support vector machine classifier for each of the LBP/C, Haralick- and Gabor descriptors

Summary

Introduction

The aim of the study was to assess whether texture analysis is feasible for automated identification of epithelium and stroma in digitized tumor tissue microarrays (TMAs). Tissue microarrays (TMAs) are the standard for highthroughput analysis of diagnostic, prognostic and predictive tissue biomarkers [1] and for rapid validation of molecular expression patterns in large-scale tissue materials [2]. Computer-assisted automated quantification of immunohistochemical protein staining has previously been shown to be feasible in TMAs [3,4,5,6] and resulted in higher reproducibility compared to human-based judgment [7]. A skilled human observer segments the tissue into compartments and can report immunohistochemical staining in tumor cells and stroma separately. Since the spatial location (in tumor cells vs. stroma) of protein expression can be of biological and clinical relevance [8,9,10], more efficient methods for computerized segmentation are needed

Objectives

Methods

Results

Discussion

Conclusion