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

Sethi A, Sha L, Vahadane AR, Deaton RJ, Kumar N, Macias V, Gann PH - J Pathol Inform (2016)

Bottom Line: 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.Khan method reduced color saturation while Vahadane reduced hue variance.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.

View Article: PubMed Central - PubMed

Affiliation: Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India; Department of Pathology, University of Illinois, Chicago, IL, USA.

ABSTRACT

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.

No MeSH data available.


Related in: MedlinePlus

Preparation of the training and testing sets using original and color-normalized images
© Copyright Policy - open-access
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4837797&req=5

Figure 2: Preparation of the training and testing sets using original and color-normalized images

Mentions: Under the supervision of a pathologist, epithelial and stromal areas were separately marked on the thirty images using Aperio ImageScope® software to delineate regions serving as ground truth for both training and testing the epithelial-stromal classifiers. Due to the complex architecture of epithelial glands, it would have been impractically tedious to annotate entire images. Thus, we annotated only a few sub-regions in each image such that a large and diverse set of training examples was created. As illustrated in Figure 2, the set of thirty cores was further divided into twenty cores that were used for training epithelial-stromal classifier, and ten that were used for testing the classifiers. Six out of the ten testing images were taken from a block that was not represented in the training set at all. This simulated the real-world scenario in which software can be used on images from a lab that did not contribute data to the training of the software.


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

Sethi A, Sha L, Vahadane AR, Deaton RJ, Kumar N, Macias V, Gann PH - J Pathol Inform (2016)

Preparation of the training and testing sets using original and color-normalized images
© Copyright Policy - open-access
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4837797&req=5

Figure 2: Preparation of the training and testing sets using original and color-normalized images
Mentions: Under the supervision of a pathologist, epithelial and stromal areas were separately marked on the thirty images using Aperio ImageScope® software to delineate regions serving as ground truth for both training and testing the epithelial-stromal classifiers. Due to the complex architecture of epithelial glands, it would have been impractically tedious to annotate entire images. Thus, we annotated only a few sub-regions in each image such that a large and diverse set of training examples was created. As illustrated in Figure 2, the set of thirty cores was further divided into twenty cores that were used for training epithelial-stromal classifier, and ten that were used for testing the classifiers. Six out of the ten testing images were taken from a block that was not represented in the training set at all. This simulated the real-world scenario in which software can be used on images from a lab that did not contribute data to the training of the software.

Bottom Line: 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.Khan method reduced color saturation while Vahadane reduced hue variance.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.

View Article: PubMed Central - PubMed

Affiliation: Department of Electronics and Electrical Engineering, Indian Institute of Technology Guwahati, Guwahati, Assam, India; Department of Pathology, University of Illinois, Chicago, IL, USA.

ABSTRACT

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.

No MeSH data available.


Related in: MedlinePlus