| Users Online: 585
Month wise articles
Figures next to the month indicate the number of articles in that month
» Articles published in the past year
To view other articles click corresponding year from the navigation links on the left side.
Letters to Editor
Original Research Article
Technical Note: Software
Export selected to
Show all abstracts
Show selected abstracts
Export selected to
Add to my list
Empirical comparison of color normalization methods for epithelial-stromal classification in H and E images
Amit Sethi, Lingdao Sha, Abhishek Ramnath Vahadane, Ryan J Deaton, Neeraj Kumar, Virgilia Macias, Peter H Gann
J Pathol Inform
2016, 7:17 (11 April 2016)
Color normalization techniques for histology have not been empirically tested for their utility for computational pathology pipelines.
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],
) were also performed.
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
, pixel classification test-AUCs were compared.
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
for color-normalized images.
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.
[HTML Full text]
[Mobile Full text]
[Citations (4) ]
[Sword Plugin for Repository]
© Journal of Pathology Informatics | Published by Wolters Kluwer -
Online since 10