Quantifying IHC pathology stains

Immunohistochemistry staining is widely used for the analysis of pathology slices. Often, multiple of such stains are applied to identify different cell types. Quantification of the number of cells or percentage of tissue that is stained with the different stainings by pathology analysts is very time consuming. In this project we developed an AI tool that can automatically quantify the relative surface that different stainings in a scan cover. It can be applied in many different contexts and is not staining specific. By automating the quantification process, analysts can much quicker interpret pathology scans and provide greater accuracy, thereby improving the efficiency and accuracy of the work done in the Pathology department.

The RTC Deep Learning and Pathology departmeent have developed a web-based application for the automatic segmentation of immunohistochemistry staining and the subsequent quantification of the different stains. Additional tools for the selection of 'regions of interest' to perform the quantification on are available for the analysts. The algorithm can be used on the Grand Challenge platform. All processing is performed on the platform; there is no specialized hardware required to try out the algorithm. Running the algorithm requires an account for Grand Challenge. If you don't have an account yet, you can register on the website; alternatively, you can log in using a Google account. After registering for a new account, or logging in to an existing Grand Challenge account, you can request access to the algorithm.

Try out the algorithm

People

Esther Markus-Smeets

Esther Markus-Smeets

PhD Candidate

Computational Pathology Group

Daan Geijs

Daan Geijs

PhD Candidate

Computational Pathology Group

Erik Aarntzen

Erik Aarntzen

Nuclear medicine physician

Radboudumc

Silvan Quax

Silvan Quax

Research Scientist RTC Deep Learning

Ajay Patel

Ajay Patel

Coordinator RTC Deep Learning

Bram van Ginneken

Bram van Ginneken

Professor

Diagnostic Image Analysis Group