Analytical Cellular Pathology

Analytical Cellular Pathology / 2014 / Article
Special Issue

Meeting Abstracts of The 2nd International Congress of the International Academy of Digital Pathology

View this Special Issue

Meeting Abstract | Open Access

Volume 2014 |Article ID 964708 | 1 page |

Staining Correction in Digital Pathology with Dye Amount Look-Up Table

Received02 Sep 2014
Accepted02 Sep 2014
Published30 Dec 2014


Automated image analysis of histology images is affected by the staining variations in histology slides. In general, training images are used to optimize the parameters of an image analysis system. Color, being one of the dominant features of stained tissue samples, is being commonly utilized as feature to segment or classify the different stained tissue components. However, the colors impressed on the tissue components vary with the staining condition of the sample. Hence, when the staining conditions of the slides for the training and test images differ, the accuracy of the analysis results would likely degrade. In this work we present a method to correct the staining condition of the histology images by constructing a look-up table (LUT) of the stained pixels’ dye amounts. The present method allows the user to not only correct the staining condition of a given histology image with respect to the staining condition of the reference slide, but to also recreate his/her preferred staining condition for the given image. The results of our experiments with hematoxylin and eosin (H&E) stained tissue images showed the effectiveness of the present method.

Copyright © 2014 Pinky A. Bautista and Yukako Yagi. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

404 Views | 226 Downloads | 0 Citations
 PDF  Download Citation  Citation
 Download other formatsMore
 Order printed copiesOrder
 Sign up for content alertsSign up

You are browsing a BETA version of Click here to switch back to the original design.