Empirical comparison of color normalization methods for epithelial-stromal classification in H and E images

• Main Authors: Amit Sethi, Lingdao Sha, Abhishek Ramnath Vahadane, Ryan J Deaton, Neeraj Kumar, Virgilia Macias, Peter H Gann
• Format: Article
• Language: English
• Published: Wolters Kluwer Medknow Publications 2016-01-01
• Series: Journal of Pathology Informatics
• Subjects: Color normalization; computational pathology; epithelial-stromal classification
• Online Access: http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2016;volume=7;issue=1;spage=17;epage=17;aulast=Sethi
• ISSN: 2153-3539; 2153-3539

Context: Color normalization techniques for histology have not been empirically tested for their utility for computational pathology pipelines. Aims: We compared two contemporary techniques for achieving a common intermediate goal - epithelial-stromal classification. Settings and Design: Expert-annotated regions of epithelium and stroma were treated as ground truth for comparing classifiers on original and color-normalized images. Materials and Methods: Epithelial and stromal regions were annotated on thirty diverse-appearing H and E stained prostate cancer tissue microarray cores. Corresponding sets of thirty images each were generated using the two color normalization techniques. Color metrics were compared for original and color-normalized images. Separate epithelial-stromal classifiers were trained and compared on test images. Main analyses were conducted using a multiresolution segmentation (MRS) approach; comparative analyses using two other classification approaches (convolutional neural network [CNN], Wndchrm) were also performed. Statistical Analysis: For the main MRS method, which relied on classification of super-pixels, the number of variables used was reduced using backward elimination without compromising accuracy, and test - area under the curves (AUCs) were compared for original and normalized images. For CNN and Wndchrm, pixel classification test-AUCs were compared. Results: Khan method reduced color saturation while Vahadane reduced hue variance. Super-pixel-level test-AUC for MRS was 0.010-0.025 (95% confidence interval limits ± 0.004) higher for the two normalized image sets compared to the original in the 10-80 variable range. Improvement in pixel classification accuracy was also observed for CNN and Wndchrm for color-normalized images. Conclusions: Color normalization can give a small incremental benefit when a super-pixel-based classification method is used with features that perform implicit color normalization while the gain is higher for patch-based classification methods for classifying epithelium versus stroma.