3.0.0 Ki-67 Quantification Breast Cancer Application Documentation

 

Application Name

Ki-67 Quantification Breast Cancer

Version

3.0.0

Documentation Version

30.09.2021 - 1

Input Image(s)

2D (standard and/or WSI); RGB

Input Parameter(s)

Regions of interest (optional)

Keywords

pathology, ihc, ki67, ki-67, nuclei, microscopy, mamma, breast, tissue, detection, tumor, oncology, carcinoma

Short Description

Detection of tumor cell nuclei in immunohistochemically (IHC) stained sections of human breast cancer. Counting of positively (brown) and negatively (blue) stained nuclei and calculation of positive/negative ratio.

References / Literature

Reference department: Diagnostic and Research Institute of Pathology, Medical University of Graz, Dr.med.univ. Martin Asslaber

Important Information

Research Use Only!

This application is not certified as a medical device and must not be used for diagnostic or therapeutic purposes.

Table of contents

IKOSA Prisma Ki-67 Quantification Breast Cancer

You can use this image analysis application or any of our other applications in your account on the IKOSA platform. If it is not on the list of available applications, please contact your organization's administrator or our team at support@kmlvision.com.

Application description

This application automatically detects and counts tumor cell nuclei in immunohistochemically (IHC) stained sections of human breast cancer. Positively (brown) and negatively (blue) stained nuclei are counted separately. The ratio of the detected positively and negatively stained nuclei is calculated. The application was developed and tested with microscopy images of human tissue sections.

 In the following, the requirements for an accurate analysis are given and the output of the applications is described.

Input data requirements

Input image(s)

Input for this application is the following image data:

Image type

Color channels

Color depth (per channel)

Size (px)

Resolution (μm/px)

Image type

Color channels

Color depth (per channel)

Size (px)

Resolution (μm/px)

2D (standard and/or WSI)

Check image format https://kmlvision.atlassian.net/wiki/spaces/KB/pages/3406725124

3 (RGB)

8 Bit

WSI formats: arbitrary

Standard images: max. 25,000 x 25,000

Typically: 0.3 - 0.5

 

Image content

Microscopy image of IHC Ki-67 stained sample, typically taken with 20x magnification. 

Additional requirements

  • For imaging, UV and IR filters should be used.

  • Nuclei must have sizes (diameters) in the range of 25-90 Pixels for the application to detect the nuclei.

Important:

For all images, the following requirements apply:

  • The illumination must be constant throughout the image(s).

  • The sample must be in focus, i.e. no blurry regions in image(s).

Input parameter(s)

No additional input parameters are required for this application.

As an optional parameter, a single or multiple regions of interest (ROIs) can be defined in which the analysis should be performed (‘inclusion ROIs’).

Description of output files and their content

Files

File format

Description

File format

Description

1

csv

results.csv:

A csv file containing global analysis results for the input image.

2

jpg

results_visualization.jpg:

A visualization of the analysis:

  • Brown and blue nuclei are visualized using orange and blue rectangles, respectively.

Please note: This file is only generated for standard images (not for Whole Slide Images).

3

json

annotation_results.json:

JSON file containing positions of detected nuclei. The position is measured from the left upper corner (1,1) of the image.

4

json

roiMeta.json:

A json file containing all information regarding the ROIs defined for the analysis job to ensure reproducibility. The file is empty if no ROIs were defined for analysis.

5

jpg

rois_visualization.jpg:

An overview visualization to show locations of all analyzed ROIs for the 2D image.

Please note: This file is only created, if inclusion ROIs were defined for analysis.

6

json

jobResultBundleMeta.json:

A json file containing all information regarding the analysis job (application name and version, project, etc.) to ensure reproducibility

 

Content

results.csv

Single csv-file

If one or more ROIs were specified, the results in a specific row refer to the ROI specified in the corresponding columns, otherwise (empty ROI columns) the results refer to the whole image.

Column NO.

Column name

Examples

Value range

Description

Column NO.

Column name

Examples

Value range

Description

1

roi_id

ROI-03

ROI-01 - 

<roi-id> starting from “ROI1”. Empty, if no inclusion ROI is specified and the whole image was analyzed.

2

roi_name

“central”

text

Custom text to identify the ROI. Empty, if no inclusion ROI is specified and the whole image was analyzed.

3

roi_size [Px^2]

1212212

1 -

Size of the ROI that was analyzed in pixels^2. The size of the whole image is given if no inclusion ROI is specified and the whole image was analyzed.

4

nuclei count

1232

0 -

Number of detected nuclei.

5

blue nuclei count

386

0 -

Number of detected blue nuclei.

6

brown nuclei count

846

0 -

Number of detected brown nuclei.

7

ratio brown/blue nuclei

2.19

0 - inf

Number of brown nuclei divided by the number of blue nuclei. if blue=0 the result is "inf" (infinity).

 

Error information

If an image analysis job fails, an error code and error message are returned. Failed analysis jobs are listed in the Failed tab of the Analysis Jobs section on the Image Analysis page on IKOSA®. More information about errors can be found in the Application Error Documentation.

Contact

If you have any questions about this app, as well as suggestions or ideas for new ones, email us at support@kmlvision.com.

Feel free to book a 30-minute meeting to speak with us about IKOSA and the apps!

https://calendly.com/kmlvision/book-the-ikosa-platform-demo

 

Copyright 2016-2021 KML Vision GmbH. IKOSA® is a registered EU trademark.