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

doi:10.4103/2153-3539.179984

RESEARCH ARTICLE

Year : 2016 | Volume : 7 | Issue : 1 | Page : 17

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

Amit Sethi¹, Lingdao Sha², Abhishek Ramnath Vahadane³, Ryan J Deaton⁴, Neeraj Kumar³, Virgilia Macias⁴, Peter H Gann⁴
¹ Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam; Department of Pathology, University of Illinois, Chicago, IL, India
² Department of Electrical and Computer Engineering, University of Illinois, Chicago, IL, USA
³ Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India
⁴ Department of Pathology, University of Illinois, Chicago, IL, USA

Correspondence Address:
Amit Sethi
Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam; Department of Pathology, University of Illinois, Chicago, IL
India

Source of Support: None, Conflict of Interest: None

Check

DOI: 10.4103/2153-3539.179984

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.

[FULL TEXT] [PDF]*

Table of Contents

Similar in PUBMED

Search Pubmed for

Search in Google Scholar for

Related articles

Citation Manager

Access Statistics

Reader Comments

Email Alert *

Add to My List *

* Requires registration (Free)

Article Access Statistics

Viewed	3007

Printed	29

Emailed	0

PDF Downloaded	611

Comments	[Add]

Cited by others	4