Automatic detection of blue-white veil and related structures in dermoscopy images

https://doi.org/10.1016/j.compmedimag.2008.08.003Get rights and content

Abstract

Dermoscopy is a non-invasive skin imaging technique, which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. One of the most important features for the diagnosis of melanoma in dermoscopy images is the blue-white veil (irregular, structureless areas of confluent blue pigmentation with an overlying white “ground-glass” film). In this article, we present a machine learning approach to the detection of blue-white veil and related structures in dermoscopy images. The method involves contextual pixel classification using a decision tree classifier. The percentage of blue-white areas detected in a lesion combined with a simple shape descriptor yielded a sensitivity of 69.35% and a specificity of 89.97% on a set of 545 dermoscopy images. The sensitivity rises to 78.20% for detection of blue veil in those cases where it is a primary feature for melanoma recognition.

Introduction

Malignant melanoma, the most deadly form of skin cancer, is one of the most rapidly increasing cancers in the world, with an estimated incidence of 59,940 and an estimated total of 8110 deaths in the United States in 2007 alone [1]. Dermoscopy is a non-invasive skin imaging technique which permits visualization of features of pigmented melanocytic neoplasms that are not discernable by examination with the naked eye. Practiced by experienced observers, this imaging modality offers higher diagnostic accuracy than observation without magnification [2], [3], [4], [5]. Dermoscopy allows the identification of dozens of morphological features one of which is the blue-white veil (irregular, structureless areas of confluent blue pigmentation with an overlying white “ground-glass” film) [6]. This feature is one of the most significant dermoscopic indicator of invasive malignant melanoma, with a sensitivity of 51% and a specificity of 97% [7]. Fig. 1 shows a melanoma with blue-white veil.

Numerous methods for extracting features from clinical skin lesion images have been proposed in literature [8], [9], [10]. However, feature extraction in dermoscopy images is relatively unexplored. The dermoscopic feature extraction studies to date include two pilot studies on pigment networks [11], [12] and globules [11], and three systematic studies on dots [13] and blotches [14], [15]. To the best of our knowledge, there is no published systematic study on the detection of blue-white veil.

In this article, we present a machine learning approach to the detection of blue-white veil in dermoscopy images. Fig. 2 shows an overview of the approach. The rest of the paper is organized as follows. Section 2 describes the image set and the preprocessing phase. Section 3 discusses the feature extraction. Section 4 presents the pixel classification. Section 5 describes the classification of lesions based on the blue-white veil feature. Finally, Section 6 gives the conclusions.

Section snippets

Image set description

The image set used in this study consists of 545 digital dermoscopy images obtained from two atlases. The first is the CD-ROM Interactive Atlas of Dermoscopy [6], which is a collection of images acquired in three institutions: University Federico II of Naples, Italy, University of Graz, Austria, and University of Florence, Italy. The second atlas is a pre-publication version of the American Academy of Dermatology DVD on Dermoscopy, edited by Harold Rabinovitz et al. These were true-color images

Feature extraction

After the selection of training and test pixels, features that will be used in the classification of these pixels need to be extracted. There are two main approaches to pixel classification: non-contextual and contextual [20]. In non-contextual pixel classification, during feature extraction, a pixel is treated in isolation from its spatial neighborhood. This often leads to noisy results. On the other hand, in contextual pixel classification, the spatial neighborhood of the pixel is also taken

Pixel classification

Popular classifiers used in pixel classification tasks include k-nearest neighbor [27], Bayesian [28], artificial neural networks [29], and support vector machines [28]. In this study, a decision tree classifier was used to classify the image pixels into 2 classes: veil and non-veil. The motivation for this choice was 2-fold. First, decision tree classifiers generate easy-to-understand rules, which is important for the clinical acceptance of a computer-aided diagnosis system. Second, they are

Lesion classification based on the blue-white veil feature

In the second part of the study, we developed a second classifier to discriminate between melanoma and benign lesions based on the presence/absence of the blue-white veil feature. In order to characterize the detected blue-white areas, we used a numerical feature defined as follows:S1=AreaofDetectedBlueWhiteVeilAreaofLesionThe problem with using S1 alone is that a blue nevus (such as the one in Fig. 7h) might be misclassified as melanoma due to its high percentage of

Conclusions

In this article, a machine learning approach to the detection of blue-white veil in dermoscopy images was described. The method is comprised of several steps including preprocessing, feature extraction, decision tree induction, rule application, and postprocessing. The detected blue-white areas were characterized using a numerical feature, which in conjunction with an ellipticity measure yielded a sensitivity of 69.35% and a specificity of 89.97% on a set of 545 dermoscopy images. The presented

Acknowledgments

This work was supported by grants from NIH (SBIR #2R44 CA-101639-02A2), NSF (#0216500-EIA), Texas Workforce Commission (#3204600182), and James A. Schlipmann Melanoma Cancer Foundation. The permissions to use the images from the CD-ROM Interactive Atlas of Dermoscopy and American Academy of Dermatology DVD on Dermoscopy are gratefully acknowledged.

M. Emre Celebi received his BSc degree in computer engineering from Middle East Technical University (Ankara, Turkey) in 2002. He received his MSc and PhD degrees in computer science and engineering from the University of Texas at Arlington (Arlington, TX, USA) in 2003 and 2006, respectively. He is currently an assistant professor in the Department of Computer Science at the Louisiana State University in Shreveport (Shreveport, LA, USA). His research interests include medical image analysis,

References (34)

  • S.W. Menzies et al.

    Why perform dermoscopy? The evidence for its role in the routine management of pigmented skin lesions

    Archives of Dermatology

    (2006)
  • G. Argenziano et al.

    Epiluminescence microscopy for the diagnosis of doubtful melanocytic skin lesions: comparison of the ABCD rule of dermatoscopy and a new 7-point checklist based on pattern analysis

    Archives of Dermatology

    (1998)
  • G. Argenziano et al.

    Interactive atlas of dermoscopy

    (2002)
  • S.W. Menzies et al.

    An atlas of surface microscopy of pigmented skin lesions: dermoscopy

    (2003)
  • Z. She et al.

    Analysis of skin line pattern for lesion classification

    Skin Research and Technology

    (2003)
  • B. Caputo et al.

    Toward a quantitative analysis of skin lesion images

    Studies in Health Technology and Informatics

    (2002)
  • Yoshino S, Tanaka T, Tanaka M, Oka H. Application of morphology for detection of dots in tumor. Proceedings of the SICE...
  • Cited by (147)

    • Co-Attention Fusion Network for Multimodal Skin Cancer Diagnosis

      2023, Pattern Recognition
      Citation Excerpt :

      Automated skin cancer diagnosis has been studied extensively. Traditional automated skin cancer diagnosis methods focus on designing hand-crafted features and employing machine learning classifiers for classification [6–8]. In addition to directly classifying skin cancer, some traditional methods attempt to infer skin cancer indirectly by referring to relevant diagnostic rules, such as the ABCD rule, pattern analysis, and seven-point checklist [22].

    View all citing articles on Scopus

    M. Emre Celebi received his BSc degree in computer engineering from Middle East Technical University (Ankara, Turkey) in 2002. He received his MSc and PhD degrees in computer science and engineering from the University of Texas at Arlington (Arlington, TX, USA) in 2003 and 2006, respectively. He is currently an assistant professor in the Department of Computer Science at the Louisiana State University in Shreveport (Shreveport, LA, USA). His research interests include medical image analysis, color image processing, content-based image retrieval, and open-source software development.

    Hitoshi Iyatomi is a research associate in Hosei University, Tokyo, Japan. He received his BE, ME degrees in electrical engineering and PhD degree in science for open and environmental systems from Keio University in 1998, 2000 and 2004, respectively. During 2000–2004, he was employed by Hewlett Packard Japan. His research interests include intelligent image processing and development of practical computer-aided diagnosis systems.

    William V. Stoecker, MD received the BS degree in mathematics in 1968 from the California Institute of Technology, the MS in systems science in 1971 from the University of California, Los Angeles, and the MD in 1977 from the University of Missouri, Columbia. He is adjunct assistant professor of computer science at the Missouri University of Science and Technology and clinical assistant professor of Internal Medicine-Dermatology at the University of Missouri-Columbia. His interests include computer-aided diagnosis and applications of computer vision in dermatology and development of handheld dermatology databases.

    Randy H. Moss received his PhD in electrical engineering from the University of Illinois, and his BS and MS degrees from the University of Arkansas in the same field. He is now professor of electrical and computer engineering at the Missouri University of Science and Technology. He is an associate editor of both Pattern Recognition and Computerized Medical Imaging and Graphics. His research interests emphasize medical applications, but also include industrial applications of machine vision and image processing. He is a senior member of IEEE and a member of the Pattern Recognition Society and Sigma Xi. He is a past recipient of the Society of Automotive Engineers Ralph R. Teetor EducationalAward and the Society of Manufacturing Engineers Young Manufacturing Engineer Award. He is a past National Science Foundation Graduate Fellow and National Merit Scholar.

    Harold S. Rabinovitz is a clinical professor of Dermatology at the University of Miami School of Medicine. He is the director of the Melafind study and has been involved in research into gene profiling and the correlation of dermoscopy with confocal microscopy.

    Giuseppe Argenziano graduated in 1992 from the School of Medicine, University Federico II in Naples/Italy and obtained his specialization diploma in Dermatology and Venereology in 1996. He is currently an assistant professor at the Department of Dermatology, Second University of Naples, in Naples/Italy. His main research field is the clinical diagnosis of melanoma and, particularly, the development of more accurate methods for the early recognition of melanoma. He is the author of numerous scientific articles concerning dermoscopy for the diagnosis of pigmented skin lesions and early recognition of melanoma. He is also the author of three books on the subject. He is the secretary of the International Dermoscopy Society.

    H. Peter Soyer is the inaugural professor of Dermatology at the University of Queensland in Brisbane/Australia. He has come to Queensland from the Medical University of Graz, Austria, where he was a professor of dermatology and the Director of the Research Unit for Teledermatology. His main research interest is teledermatology with special emphasis on the virtual dimension of clinico-pathologic correlation. In 2002, he started together with Gerald Gabler and Rainer Hofmann-Wellenhof the telederm.org project. In 2006, he organized the First World Congress of Teledermatology in Graz/Austria. He is the president of the International Dermoscopy Society and the International Society of Teledermatology.

    View full text