SIViP (2014) 8 (Suppl 1):S63–S70 DOI 10.1007/s11760-014-0681-0 ORIGINAL PAPER Multi-scale directional-filtering-based method for follicular lymphoma grading Alican Bozkurt · Alexander Suhre · A. Enis Cetin Received: 2 May 2014 / Revised: 6 July 2014 / Accepted: 13 July 2014 / Published online: 7 August 2014 © Springer-Verlag London 2014 Abstract Follicular lymphoma (FL) is a group of malig- nancies of lymphocyte origin that arise from lymph nodes, spleen, and bone marrow in the lymphatic system. It is the second most common non-Hodgkins lymphoma. Character- istic of FL is the presence of follicle center B cells consist- ing of centrocytes and centroblasts. Typically, FL images are graded by an expert manually counting the centroblasts in an image. This is time consuming. In this paper, we present a novel multi-scale directional filtering scheme and utilize it to classify FL images into different grades. Instead of counting the centroblasts individually, we classify the texture formed by centroblasts. We apply our multi-scale directional filter- ing scheme in two scales and along eight orientations, and use the mean and the standard deviation of each filter out- put as feature parameters. For classification, we use support vector machines with the radial basis function kernel. We map the features into two dimensions using linear discrimi- nant analysis prior to classification. Experimental results are presented. Keywords Follicular lymphoma · Directional filtering · SVM · Texture classification A. Bozkurt (B ) · A. E. Cetin Department of Electrical and Electronics Engineering, Bilkent University, 06800 Ankara, Turkey e-mail: alican@ee.bilkent.edu.tr A. E. Cetin e-mail: cetin@bilkent.edu.tr A. Suhre Valeo Schalter und Sensoren GmbH, Laiernstrasse 12, 74321 Bietigheim-Bissingen, Germany e-mail: suhre@ee.bilkent.edu.tr 1 Introduction Microscopic image processing has become an important research area [12, 28] in recent years. Follicular lymphoma (FL) is a group of malignancies of lymphocyte origin that arise from lymph nodes, spleen, and bone marrow in the lymphatic system in most cases. It is the second most common non-Hodgkins lymphoma [6]. Characteris- tic of FL is the presence of a follicular or nodular pat- tern of growth presented by follicle center B cells consist- ing of centrocytes and centroblasts. World Health Organiza- tion’s (WHO) histological grading process of FL depends on the number of centroblasts counted within represen- tative follicles, resulting in three grades with increasing severity [10]: Grade 1: 0–5 centroblasts (CBs) per high-power field (HPF), Grade 2: 6–15 centroblasts per HPF, and Grade 3: More than 15 centroblasts per HPF. While grades one and two are considered indolent, with long average survival rates and no needs of chemotherapy, grade three is an aggressive disease. It is rapidly fatal if not immediately treated with aggressive chemotherapy [21]. Therefore, accurate grading of follicular lymphoma images is of course essential to the optimal choice of treatment. In FL grading problem, human experts manually count the centroblasts in an HPF image. This is obviously time con- suming. Some computerized methods mimic this approach [16, 19, 25]. Instead of counting the centroblasts individually, we can treat images as textures and try to classify the texture formed by centroblasts in this article. Recently, Suhre pro- posed a two-level classification tree using sparsity-smoothed Bayesian classifier and reported very high accuracy [27]. 123