Image processing algorithms

Quantification of histochemical staining by color deconvolution

Kanteron Systems, in a proof-of-concept partnership with IBM (not available for clinical use), brings the power of Medical Imaging Analysis to the IBM Cloud marketplace by making it easy to integrate very specific tools for medical image processing and analysis into existing workflows.

This solution is the first of many to come in the next months, but represents a true paradigm shift, a great value to our customers, who will be able to add advanced algorithms to their workflows from anywhere with the click of a button:

Color image analysis: separation | Quantification of histochemical staining by color deconvolution

Immunohistochemical staining colors separation will allow the user, for example, to separate the immunohistochemical (IHC) staining from the hematoxylin counterstaining. The separation is achieved with a method known as “color deconvolution”.

Sample use case: the IHC staining expression of the FHL2 protein is revealed with Diaminobenzidine (DAB) which gives a brown color.

The algorithm was developed to deconvolve the color information present in red-green-blue (RGB) images and to calculate the contribution of each of the applied stains based on stain-specific RGB absorption. The algorithm was tested using different combinations of diaminobenzidine, hematoxylin and eosin at different staining levels.

Quantification of the different stains is not significantly influenced by the combination of multiple stains in a single sample. The color deconvolution algorithm results in comparable quantification independent of the stain combinations as long as the histochemical procedures do not influence the amount of stain in the sample (due to bleaching because of stain solubility and saturation of staining was prevented).

This image analysis algorithm provides a robust and flexible method for objective immunohistochemical analysis of samples stained with up to three different stains using a digital pathology scanner, or a laboratory microscope with standard RGB camera setup.