ROBUST BORDER DETECTION IN DERMOSCOPY IMAGES USING THRESHOLD FUSION M. Emre Celebi 1 * , Sae Hwang 2 , Hitoshi Iyatomi 3 , and Gerald Schaefer 4 1 Department of Computer Science, Louisiana State University, Shreveport, USA 2 Department of Computer Science, University of Illinois, Springfield, USA 3 Department of Applied Informatics, Hosei University, Tokyo, Japan 4 Department of Computer Science, Loughborough University, Loughborough, UK ABSTRACT Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin le- sions. Due to the difficulty and subjectivity of human in- terpretation, automated analysis of dermoscopy images has become an important research area. Border detection is of- ten the first step in this analysis. In many cases, the lesion can be roughly separated from the background skin using a thresholding method applied to the blue channel. However, no single thresholding method appears to be robust enough to successfully handle a wide variety of dermoscopic images. In this paper, we present an automated method for detecting le- sion borders in dermoscopy images using a fusion of several thresholding methods. Experiments on a difficult set of 90 images demonstrate that the proposed method achieves both fast and accurate results when compared to six state-of-the-art methods. 1. INTRODUCTION Invasive and in-situ malignant melanoma together comprise one of the most rapidly increasing cancers in the world. In- vasive melanoma alone has an estimated incidence of 68,720 and an estimated total of 8,650 deaths in the United States in 2009 [1]. Early diagnosis is particularly important since melanoma can be cured with a simple excision if detected early. Dermoscopy has become one of the most important tools in the diagnosis of melanoma and other pigmented skin le- sions. This non-invasive skin imaging technique involves op- tical magnification, which makes subsurface structures more easily visible when compared to conventional clinical images [2]. This in turn reduces screening errors and provides greater differentiation between difficult lesions such as pigmented Spitz nevi and small, clinically equivocal lesions [3]. How- ever, it has also been demonstrated that dermoscopy may ac- tually lower the diagnostic accuracy in the hands of inexperi- enced dermatologists [4]. Therefore, in order to minimize the * This publication was made possible by a grant from The Louisiana Board of Regents (LEQSF2008-11-RD-A-12). Email: ecelebi@lsus.edu diagnostic errors that result from the difficulty and subjectiv- ity of visual interpretation, the development of computerized image analysis techniques is of paramount importance [ 5]. Automated border detection is often the first step in the automated or semi-automated analysis of dermoscopy images [6]. It is crucial for image analysis for two main reasons. First, the border structure provides important information for accurate diagnosis, as many clinical features, such as asym- metry, border irregularity, and abrupt border cutoff, are cal- culated directly from the border. Second, extraction of other important clinical features such as atypical pigment networks, globules, and blue-white areas, critically depends on the ac- curacy of border detection. Automated border detection is a challenging task due to several reasons: (i) low contrast be- tween the lesion and the surrounding skin, (ii) irregular and fuzzy lesion borders, (iii) artifacts and intrinsic cutaneous fea- tures such as black frames, skin lines, blood vessels, hairs, and air bubbles, (iv) variegated coloring inside the lesion, and (v) fragmentation due to various reasons such as scar-like de- pigmentation. Numerous methods have been developed for border de- tection in dermoscopy images [6]. Recent approaches include fuzzy c-means clustering [7, 8], gradient vector flow snakes [9], thresholding followed by region growing [ 10], meanshift clustering [11], color quantization followed by spatial seg- mentation [12], and statistical region merging [13]. In this paper, we present a fast and accurate method for detecting lesion borders in dermoscopy images. The method involves the fusion several thresholding methods followed by various simple postprocessing steps. The rest of the paper is organized as follows. Section 2 describes threshold fusion method and the postprocessing steps. Section 3 presents the experimental results. Finally, Section 4 gives the conclusions. 2. THRESHOLD FUSION In many dermoscopic images, the lesion can be roughly sep- arated from the background skin using a thresholding method applied to the blue channel [6]. While there are a number of thresholding methods that perform well in general, the ef-