Journal Article
. 2013 Jun; 4(Suppl):S11.
doi: 10.4103/2153-3539.109869.

Histological stain evaluation for machine learning applications

Jimmy C Azar 1 Christer Busch  Ingrid B Carlbom  
  • PMID: 23766933
  •     3 References
  •     3 citations


Aims: A methodology for quantitative comparison of histological stains based on their classification and clustering performance, which may facilitate the choice of histological stains for automatic pattern and image analysis.

Background: Machine learning and image analysis are becoming increasingly important in pathology applications for automatic analysis of histological tissue samples. Pathologists rely on multiple, contrasting stains to analyze tissue samples, but histological stains are developed for visual analysis and are not always ideal for automatic analysis.

Materials And Methods: Thirteen different histological stains were used to stain adjacent prostate tissue sections from radical prostatectomies. We evaluate the stains for both supervised and unsupervised classification of stain/tissue combinations. For supervised classification we measure the error rate of nonlinear support vector machines, and for unsupervised classification we use the Rand index and the F-measure to assess the clustering results of a Gaussian mixture model based on expectation-maximization. Finally, we investigate class separability measures based on scatter criteria.

Results: A methodology for quantitative evaluation of histological stains in terms of their classification and clustering efficacy that aims at improving segmentation and color decomposition. We demonstrate that for a specific tissue type, certain stains perform consistently better than others according to objective error criteria.

Conclusions: The choice of histological stain for automatic analysis must be based on its classification and clustering performance, which are indicators of the performance of automatic segmentation of tissue into morphological components, which in turn may be the basis for diagnosis.

Keywords: F-measure; Fisher criterion; Gaussian mixture model; Mahalanobis distance; Rand index; Support vector machines; expectation-maximization; high throughput imaging systems.

Quantification of histochemical staining by color deconvolution.
A C Ruifrok, D A Johnston.
Anal Quant Cytol Histol, 2001 Sep 04; 23(4). PMID: 11531144
Highly Cited.
Blind decomposition of transmission light microscopic hyperspectral cube using sparse representation.
Grigory Begelman, Michael Zibulevsky, Ehud Rivlin, Tsafrir Kolatt.
IEEE Trans Med Imaging, 2009 Mar 05; 28(8). PMID: 19258197
Digital stain separation for histological images.
P J Tadrous.
J Microsc, 2010 Oct 16; 240(2). PMID: 20946383
Label-free quantitative evaluation of breast tissue using Spatial Light Interference Microscopy (SLIM).
Hassaan Majeed, Tan Huu Nguyen, +2 authors, Gabriel Popescu.
Sci Rep, 2018 May 04; 8(1). PMID: 29720678    Free PMC article.
Glandular Segmentation of Prostate Cancer: An Illustration of How the Choice of Histopathological Stain Is One Key to Success for Computational Pathology.
Christophe Avenel, Anna Tolf, Anca Dragomir, Ingrid B Carlbom.
Front Bioeng Biotechnol, 2019 Jul 25; 7. PMID: 31334225    Free PMC article.
A Regulatory Science Initiative to Harmonize and Standardize Digital Pathology and Machine Learning Processes to Speed up Clinical Innovation to Patients.
Hetal Desai Marble, Richard Huang, +14 authors, Jochen K Lennerz.
J Pathol Inform, 2020 Oct 13; 11. PMID: 33042601    Free PMC article.