Automated Analysis of PIN-4 Stained Prostate Needle Biopsies Bikash Sabata, Boris Babenko, Robert Monroe, and Chukka Srinivas BioImagene Inc., 919 Hermosa Court, Sunnyvale, CA 94085 Bikash.Sabata@bioimagene.com http://www.bioimagene.com Abstract. Prostate Needle biopsies are stained with the PIN-4 marker cocktail to help the pathologist distinguish between HGPIN and adeno- carcinoma. The correct interpretation of multiple IHC markers can be challenging. Therefore we propose the use of computer aided diagnosis algorithms for the identification and classification of glands in a whole slide image of prostate needle biopsy. The paper presents the different issues related to the automated analysis of prostate needle biopsies and the approach taken by BioImagene in its first generation algorithms. Keywords: Computer Aided Diagnostics (CAD), Prostate Analysis, Medical Imaging, Histopathology Image Analysis. 1 Introduction Several immunohistochemistry (IHC) markers are routinely used by pathologists in the interpretation of prostate biopsies, including P504S (racemace), p63, and high molecular weight (HMW) cytokeratins (CK5 and CK14) [1]. P504S is a protein preferentially expressed in the cytoplasm of prostatic adenocarcinoma as well as high-grade prostatic intraepithelial neoplasia (HGPIN). p63 and the HMW cytokeratins are expressed in the nucleus and cytoplasm respectively of prostatic basal cells surrounding benign prostatic glands, but not in the secre- tory cells of these glands [2]. The combination of these markers in the PIN-4 antibody cocktail (Biocare) is useful to the pathologist in the distinction be- tween adenocarcinoma, HGPIN, and benign glands, particularly in cases with limited tissue [3]. However, correct interpretation of multiple IHC markers stain- ing different subcellular compartments of different cell types can be challenging. Computer aided image analysis (CAD) algorithms are therefore required to assist the pathologist in the interpretation of prostatic tissue stained with the PIN-4 cocktail. The workflow within the clinical labs is optimized to maximize the number of cases a pathologist can sign out without compromising the quality of di- agnosis. Digital pathology promises to create the transformation to pathology practice that increases the overall quality and quantity of pathology diagnosis. The pathology slides are scanned using the whole slide scanner such as the iScan device from BioImagene. The images generated are managed within a workflow A. Madabhushi et al. (Eds.): Prostate Cancer Imaging 2010, LNCS 6367, pp. 89–100, 2010. c  Springer-Verlag Berlin Heidelberg 2010