A Non-Linear Mapping Approach to Stain Normalisation in Digital Histopathology Images using Image-Specific Colour Deconvolution

Histopathology diagnosis is based on visual examination of the morphology of histological sections under a microscope. With the increasing popularity of digital slide scanners, decision support systems based on the analysis of digital pathology images are in high demand. However, computerised decision support systems are fraught with problems that stem from colour variations in tissue appearance due to variation in tissue preparation, variation in stain reactivity from different manufacturers/batches, user or protocol variation and the use of scanners from different manufacturers. In this paper, we present a novel approach to stain normalisation in histopathology images. The method is based on non-linear mapping of a source image to a target image using a representation derived from colour deconvolution. Colour deconvolution is a method to obtain stain concentration values when the stain matrix, describing how the colour is affected by the stain concentration, is given. Rather than relying on standard stain matrices, which may be inappropriate for a given image, we propose the use of a colour based classifier that incorporates a novel stain colour descriptor to calculate image-specific stain matrix. In order to demonstrate the efficacy of the proposed stain matrix estimation and stain normalisation methods, they are applied to the problem of tumor segmentation in breast histopathology images. The experimental results suggest that the paradigm of colour normalisation, as a preprocessing step, can significantly help histological image analysis algorithms to demonstrate stable performance which is insensitive to imaging conditions in general and scanner variations in particular.