V. Jeya Sutha et al. Int. Journal of Engineering Research and Applications www.ijera.com ISSN : 2248-9622, Vol. 4, Issue 2( Version 2), February 2014, pp.16-20 www.ijera.com 16 | Page Segmentation of Immunohistochemical Staining Of B-Catenin Expression of Oral Cancer V. Jeya Sutha, K.Srividhya (Department of Electronics and Communication Engineering, Anna University,Chennai) ABSTRACT Oral Cancer is any cancerous tissue growth located in the mouth, also called as Squamous Cell Carcinoma . It has been one of the serious cancer that affect the south Asian countries. Oral cancer has variable diagnosis method and the one is biopsy. Histopathological results suffers from considerable inter and intrareader variability even when used by expert pathologists. In order to get both qualitative and quantitative results, we has been developed a system for diagnosis of oral cancer using EM algorithm. The microscopic images of immunohistochemical staining of β-catenin expression are segmented using iterative method of EM algorithm to extract the cellular and extracellular components of an image. The segmentation process of the system uses unitone conversion to obtain a single channel image using PCA that has highest contrast then normalize the unitone image to the [0,1] range. Based on the segmentation process we conclude that β-Catenin expression using EM algorithm is an efficient technique to help the pathologist to evaluate the histological changes on microscopic images of oral cancer. Keywords – Immunohistopatholoy, Oral Squamous Cell Carcinoma, PCA, Unitone, EM Algorithm. I. INTRODUCTION ORAL cancer is the cancer that starts in the mouth or oral cavity and is especially seen disadvantaged in elderly males. It is one among the 10 most common cancers worldwide, with 2,80,000 new cases of oral cancer found every year. It has been one of the serious cancer that affect the South Asian Countries. In India, it is the sixth most common malignancy reported with high mortality ratio. They are highly curable if found and treated at an early stage. The early detection is expected to increase when the patient’s awareness regarding the danger of oral cancer increases. More than 90% of all oral cavity cancers are Oral Squamous Cell Carcinoma(OSCC), and tobacco, alcohol, and betel consumption are the main risk factor for these and many potentially malignant lesions(PML) groups. The adult males who use tobacco and alcohol are the main high risk groups. Early diagnosis of OSCC makes the dentists speed proceeding to further treatment. For this, the patients to seek an dentist at an early stage. The standard method of revealing PML and OSCC is the conventional oral examination, which (a) (b) (c) (d) (e) (f) Fig. 1. (a) Carcinoma of tounge,(b) Erythroplakia,(c) Leukoplakia,(d) Actinic Cheilitis,(e) Lichen Planus,(f) Oral Squamous Fibrosis includes biopsy and histopathological examination by confirming clinical suspicion.Currently, a biopsy with histopathology is considered the gold standard for diagnosis of OSCC. However, it is a rather slow process, requiring several days to fix, embed and stain the biopsy specimen before results can be available. It is subject to interpretation of pathologist, and although it can detect cellular and molecular changes if special techniques are employed. OSCC may be preceded by clinically evident PMLs, particularly Erythroplakia (Fig.1.b) and leukoplakia (Fig.1.c). Erythroplakia is rare, and presents as a velvety plaque. At least 85% of cases show frank malignancy or severe dysplasia(precancerous) and carcinomas are seen 17 times more frequently in RESEARCH ARTICLE OPEN ACCESS