View Labeled IHC images of RCC (public)

2012-03-09 11:27 by jetic | Version 4 | Rating Empty StarEmpty StarEmpty StarEmpty StarEmpty StarEmpty Star
Rating
Empty StarEmpty StarEmpty StarEmpty StarEmpty StarEmpty Star Overall (based on 0 votes)
Empty StarEmpty StarEmpty StarEmpty StarEmpty StarEmpty Star Interesting
Empty StarEmpty StarEmpty StarEmpty StarEmpty StarEmpty Star Documentation
Summary

Labeled immunohistochemically stained tissue micro array images for nucleus detection and classification

DOI (more info at datacite)
10.5881/LABELED-IHC-IMAGES-OF-RCC
License
CC0
Dependencies
Tags
Carcinoma Cell Classification Clear compuational detection immunohistochemistry pathology Renal
Attribute Types
Download
zip (20.5 MB)

Files are converted on demand and the process can take up to a minute. Please wait until download begins.

Completeness of this item currently: 77%.
You can edit this item to add more meta information and make use of the site's premium features.
Original Data Format
zip
Name
Version mldata
Comment
Names
Data (first 10 data points)
    ZIP archive immunohistochemical_images/, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist1/, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist1/spots_A_08_1_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist1/spots_B_05_5_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist1/spots_B_10_3_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist1/spots_B_11_2_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist1/spots_B_12_6_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist1/spots_C_07_6_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist1/spots_C_10_8_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist1/spots_C_11_6_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist2/, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist2/spots_A_08_1_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist2/spots_B_05_5_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist2/spots_B_10_3_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist2/spots_B_11_2_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist2/spots_B_12_6_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist2/spots_C_07_6_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist2/spots_C_10_8_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/Pathologist2/spots_C_11_6_top_left.xml, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/spots_A_08_1_top_left.png, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/spots_B_05_5_top_left.png, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/spots_B_10_3_top_left.png, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/spots_B_11_2_top_left.png, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/spots_B_12_6_top_left.png, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/spots_C_07_6_top_left.png, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/spots_C_10_8_top_left.png, immunohistochemical_images/Mib-1 on Human Renal Clear Cell Carcinoma/spots_C_11_6_top_left.png, immunohistochemical_images/Readme.txt
Description

The images show immunohistochemical stainings (e.g. MIB-1 staining) on several tissue micro array (TMA) spots.

Blue dots on the images are cell nuclei, negative for the protein, brown ones are positive nuclei.

Additionally, some nuclei belong to malignant cancerous cells and some belong to benign cells (the class of a nucleus). The location and class of all nuclei in the images is written in the .XML files. Each nucleus has a location and label (0 for benign, 1 for malignant).

Note that besides a big overlap between different pathologists, there are some disagreements in the location and class of a nucleus.

The task is to improve state-of-the-art computer vision and image processing to be capable of automatically detect and classify cell nuclei in such type of images.

URLs
(No information yet)
Publications
    Data Source
    University Hospital Zurich, Switzerland.
    Measurement Details

    The tissue microarray block was generated in a trial from the University Hospital Zurich. The TMA slides were immunohistochemically stained with the MIB-1 (Ki-67) antigen. Scanning was performed on a Nanozoomer C9600 virtual slide light microscope scanner from HAMAMATSU. The magnification of 40x resulted in a per pixel resolution of 0.23μm. The tissue microarry was tiled into 133 single spots of size 3000 × 3000 pixel, representing one patient each. 8 spots were randomely selected and quartered for manual labeling, training and testing.

    Usage Scenario
    revision 1
    by jetic on 2012-03-08 12:06
    revision 2
    by jetic on 2012-03-08 12:12
    revision 3
    by jetic on 2012-03-08 12:15
    revision 4
    by jetic on 2012-03-09 11:27

    No one has posted any comments yet. Perhaps you would like to be the first?

    Leave a comment

    To post a comment, please sign in.

    This item was downloaded 2418 times and viewed 3331 times.

    No Tasks yet on dataset Labeled IHC images of RCC

    Submit a new Task for this Data item

    Data

    Sort by

    Disclaimer

    We are acting in good faith to make datasets submitted for the use of the scientific community available to everybody, but if you are a copyright holder and would like us to remove a dataset please inform us and we will do it as soon as possible.

    Data | Task | Method | Challenge

    Acknowledgements

    This project is supported by PASCAL (Pattern Analysis, Statistical Modelling and Computational Learning)
    PASCAL Logo
    http://www.pascal-network.org/.