ALSUBAIE et al.: DISCRIMINATIVE MAXWELLIAN STAIN DECONVOLUTION 1 A Discriminative Framework for Stain Deconvolution of Histopathology Images in the Maxwellian Space Najah Alsubaie 1,2 N.M.F.Alsubaie@warwick.ac.uk Nicholas Trahearn 1 N.Trahearn@warwick.ac.uk Shan-E-Ahmed Raza 1 S.E.A.Raza@warwick.ac.uk Nasir M. Rajpoot 3,1 Nasir.Rajpoot@ieee.org 1 Department of Computer Science University of Warwick Coventry, UK 2 Department of Computer Science Princess Nourah bint Abdulrahman University Riyadh, KSA 3 Department of Computer Science and Engineering Qatar University, Qatar Abstract Histopathology image analysis has received a lot of attention since the advent of whole slide scanners. Digitisation of tissue slides lends itself to the automation of histopathology image analysis algorithms such as mitotic cell detection, nuclei segmen- tation and hormone receptors scoring. Most of these algorithms depend on the stain expression of scanned tissue slides. However, different standards followed by different labs and the technical variations among different scanners result in stain colour inconsis- tency in histopathology images across different labs. Thus, applications that rely on stain colour intensity might fail when they are applied to images with different colour appear- ance. In this paper, we present an effective method of stain deconvolution of histopathol- ogy images, which is a fast and reliable method of deriving the stain matrix. We propose a discriminative framework in the Maxwellian space to achieve reliable estimation of the stain matrix. We compare the proposed method with one of the state-of-the-art stain deconvolution methods and show that the proposed method estimates stain matrix with high accuracy. 1 Introduction Stain deconvolution is a pre-processing step which aims to deconvolve the applied stains to generate separate images, where each image shows the distribution of single stain. Its im- portance can be seen when one considers the noticeable differences in the colour of different stains in histopathology images produced in different staining conditions by different labs. Stain colour may vary due to several reasons: The amount of stain applied to the tissue, the stain manufacturers, the storage conditions of the tissue and the variation between the tech- nical properties of scanners among different brands. All of these factors cause differences in the colour appearance and hence affect algorithms that rely on the colour of stains, such c  2015. The copyright of this document resides with its authors. It may be distributed unchanged freely in print or electronic forms.