After After
Before Before

10047 - CK8/18, Breast Cancer

INTRODUCTION

Cytokeratins (CKs) are intermediate filament proteins located in the cytoplasm. CKs belong to the most fundamental markers of epithelial differentiation; including that of the epithelia of breast ductal carcinoma [See REFERENCES: 1].

This APP can be used to determine the tumor density i.e. the area of tumor growth compared to tissue area. With some precaution, the tumor region can be defined as the region where certain CKs are expressed in the cytoplasm.

NOTE: To get an optimal and unbiased result, the APP is dependent on a stable staining intensity.

KEYWORDS

Breast ductal carcinoma, cytokeratin, tumor density, cytoplasmatic staining, cytoplasmatic intensity, quantitative, digital pathology, image analysis.

METHODS

Two color deconvolution bands are used as preprocessing steps to enhance tissue and tumor regions. These color bands are filtered with a median filter to smoothen the image while preserving the edges.
The classification of the tumor and non-tumor region is based on an intensity based thresholding classifier. The classifier segments the tissue into three parts: tumor, non-tumor and background corresponding to blue-, green- and clear-label, respectively.
The last processing step is the post-processing. Here the tumor-, non-tumor and clear-labels are expanded, thereby closing any clear-holes in the tumor- and non-tumor labels - [See EXAMPLES: 2 and 3].

QUANTITATIVE OUTPUT VARIABLES

The output variables obtained from this protocol include:

- Tumor (A): Tumor region area

- Tumor Density = Tumor (A) / Total tissue region (A): Tumor density


AUXILIARY APPS (included)

Auxiliary APPs are used for additional process steps, e.g. finding Region of Interest (ROI).

There are no Auxiliary APPs available.


STAINING PROTOCOL

There is no staining protocol available


ADDITIONAL INFORMATION

The APP utilizes the EngineTM and Viewer software modules, where EngineTM offers an execution platform to expand processing capability and speed of image analysis. Viewer gives a fast review together with several types of image adjustment properties ex. outlining of regions, annotations and direct measures of distance, curve length, radius, etc.
By adding the AuthorTM module the APP can be customized to fit other purposes. AuthorTM offers a comprehensive and dedicated set of tools for creating new fit-for-purpose analysis APPs, and no programming experience is required.


REFERENCES

This APP was developed in cooperation with Professor Mogens Vyberg from NordiQC and Aalborg University Hospital.

LITERATURE

1. NordiQC: Pan Cytokeratin
www.nordiqc.org/downloads/assessments/82_85.pdf
RUO
FIGURE 1
FIGURE 1
Field of view showing invasive tumor in an image of a TMA core of breast tissue stained by IHC for CK. The core ROI has been outlined automatically (green hatched line).
FIGURE 2
FIGURE 2
The same field of view as in Figure 1 after the initial automatic detection of the Tumor region (blue label) and Non-tumor region (green label).
FIGURE 3
FIGURE 3
The same field of view as in Figure 1 after the final automatic classification of Tumor region (blue label) and Non-tumor region (green label).