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

Two examples of cores whose pixels have been classified into epithelium (green) and stroma (red) based on original images as well as normalized images using Vahadane and Khan methods
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 9: Two examples of cores whose pixels have been classified into epithelium (green) and stroma (red) based on original images as well as normalized images using Vahadane and Khan methods

Mentions: Some examples of resultant epithelial-stromal maps obtained using MRS and a logistic regression threshold of 0.5 on the twenty-variable models for the three sets of images are shown in Figure 9. We observed that more of the light-colored epithelium was confused as stroma in the original images [see lower example in Figure 9]. On the other hand, due to color normalization, both Vahadane and Khan had less trouble with such images, thus explaining their improved performance over the original set. Relative to Vahadane, Khan struggled with correctly identifying epithelium with nuclei whose chromatin had marginated. This is likely because Vahadane estimates the stain density maps in an unsupervised fashion. Therefore, it adapts to the images including those with light colored epithelium whereas Khan uses a pretrained stain classification model. On the other hand, Vahadane struggled relatively more with identifying inflamed stroma as stroma because of the concentration of hematoxylin in clustered lymphocytes. In this case, Khan's pretrained model seems to help in identifying the matrix surrounding lymphocytes correctly.


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)

Two examples of cores whose pixels have been classified into epithelium (green) and stroma (red) based on original images as well as normalized images using Vahadane and Khan methods
© Copyright Policy - open-access
Related In: Results  -  Collection

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

Figure 9: Two examples of cores whose pixels have been classified into epithelium (green) and stroma (red) based on original images as well as normalized images using Vahadane and Khan methods
Mentions: Some examples of resultant epithelial-stromal maps obtained using MRS and a logistic regression threshold of 0.5 on the twenty-variable models for the three sets of images are shown in Figure 9. We observed that more of the light-colored epithelium was confused as stroma in the original images [see lower example in Figure 9]. On the other hand, due to color normalization, both Vahadane and Khan had less trouble with such images, thus explaining their improved performance over the original set. Relative to Vahadane, Khan struggled with correctly identifying epithelium with nuclei whose chromatin had marginated. This is likely because Vahadane estimates the stain density maps in an unsupervised fashion. Therefore, it adapts to the images including those with light colored epithelium whereas Khan uses a pretrained stain classification model. On the other hand, Vahadane struggled relatively more with identifying inflamed stroma as stroma because of the concentration of hematoxylin in clustered lymphocytes. In this case, Khan's pretrained model seems to help in identifying the matrix surrounding lymphocytes correctly.

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