1. Abstract  Cirrhosis is an endemic diseases across the world that leads to observed liver contour irregularities in the Ultrasound images, which can be used to detect and confirm the pathologic condition.  In this work these irregularities are semi-automatically segmented and quantified in order to help the physician in the diagnosis. Results obtained from real data have shown the ability of the method to detect the disease.  The ultimate goal is to use these irregularity features jointly with other features extracted from the liver parenchyma to design a highly discriminative classifier for liver cirrhosis, steatosis and other diffuse liver diseases. Morphologic cirrhosis diagnosis from Ultrasound RecPad2010 - 16th edition of the Portuguese Conference on Pattern Recognition, UTAD University, Vila Real city, October 29th Ricardo Ribeiro 1,3 Rui Marinho 2 and J.M. Sanches 1 1 Institute for Systems and Robotics / Instituto Superior Técnico 2 Faculdade de Medicina da Universidade de Lisboa 3 Escola Superior de Tecnologia da Saúde de Lisboa Lisboa, Portugal Problem Formulation I.Estimation of the RF envelope and denoised anatomic images This is performed using the Bayesian methods proposed by [8], where the use of total variation techniques allows the preservation of major transitions, as seen in the case of liver capsule and overlying structures. II.Using the de-noised US image, the liver surface contour is obtain using a snake technique which computes one iteration of the energy-minimization of active contour models. III.Based on the detect contour, the following features were extracted: a)Root Mean Square of the different angles produced by the points that characterize the contour (rms α ). b)Root Mean Square of the variation of the points of the contour in the y axis (rms y ). c)Mean and Variance of the calculated angles (m α and v α ). d)Variance of the y axis coordinates at each point (v y ). IV.Feature selection - forward selection method with the criterion 1 - Nearest Neighbor leave-one-out classification performance. V.The features extracted by the preceding methods are used for classification, where a support vector machine (SVM) classifier [3] is used. Experimental Results  Sixty-nine US liver images were obtained from 69 patients:  40 patients had cirrhosis (Ω C )  29 had normal liver (Ω N )  Image Processing Results:  Classification Results: (a) Normal Liver (b) Cirrhotic liver without ascites (c) Cirrhotic liver with ascites Gold Standard ΩNΩN ΩCΩC Classifier ΩNΩN 17(24.6%)7(10.1%) ΩCΩC 12(17.4%)33(47.9%) Conclusions  In this work a semi-automatic detection of liver surface is proposed to help in the diagnosis of the cirrhosis.  Results obtained showed an overall accuracy of 72,46%, a high sensitivity, 82,5%, and a low specificity, 58,6%.  In the future the authors intend to include other features to increase the accuracy of the method, as well as use more state-of-the-art automatic snakes, in order to create a fully automatic method.