Automatic Identification of Diagnostic Significant Regions in Confocal Laser Scanning Microscopy of Melanocytic Skin Tumors

M. Wiltgen; A. Gerger; C. Wagner; J. Smolle

doi:10.3414/ME0463

Methods of Information in Medicine, Table of Contents

Methods Inf Med 2008; 47(01): 14-25
DOI: 10.3414/ME0463

For Discussion

Schattauer GmbH

Automatic Identification of Diagnostic Significant Regions in Confocal Laser Scanning Microscopy of Melanocytic Skin Tumors

M. Wiltgen

¹Institute of Medical Informatics, Statistics and Documentation, Medical University of Graz, Graz, Austria

,

A. Gerger

²Department of Internal Medicine, Division of Oncology, Medical University of Graz, Graz, Austria

,

C. Wagner

¹Institute of Medical Informatics, Statistics and Documentation, Medical University of Graz, Graz, Austria

,

J. Smolle

¹Institute of Medical Informatics, Statistics and Documentation, Medical University of Graz, Graz, Austria

› Author Affiliations

Abstract

Summary

Objectives: Confocal laser scanning microscopy (CLSM) is used for quick medical checkups. The aim of this study is to check the discrimination power of texture features for the automatic identification of diagnostic significant regions in CLSM views of skin lesions.

Methods: In tissue counter analysis (TCA) the images are dissected in equal square elements, where different classes of features are calculated out. Features defined in the spatial domain are based on histogram (grey level distribution) and co-occurrence matrix (grey level combinations). The features defined in the frequency domain are based on spectral properties of the wavelet Daubechie 4 transform (texture exploration at different scales) and the Fourier transform (global texture properties are localized in the spectrum). Hundred cases of benign common nevi and malignant melanoma were used as the study set. Classification was done with CART (Classification and Regression Trees) analysis which splits the set of square elements into homogenous terminal nodes and generates a set of splitting rules.

Results: Features based on the wavelet transform provide the best results with 96.0% of correctly classified elements from benign common nevi and 97.0% from malignant melanoma. The classification results are relocated to the images by use of the splitting rules as diagnostic aid. The discriminated square elements are highlighted in the images, showing tissue with features in good accordance with typical diagnostic CLSM features.

Conclusion: Square elements with more than 80% of discrimination power enable the identification of diagnostic highly significant parts in confocal microscopic views of malignant melanoma.

Keywords

Medical image processing - confocal laser scanning microscopy - tissue counter analysis - computer-assisted diagnosis

Full Text

References

References
1 Busam KJ, Hester K, Charles C, Sachs DL, Antonescu CR, Gonzalez S, Halpern AC. Detection of clinically amelanotic malignant melanoma and assessment of its margins by in vivo confocal scanning laser microscopy. Arch Dermatol 2001; 137: 923-929.
2 Busam KJ, Charles C, Lohmann CM, Marghoob A, Goldgeier M, Halpern AC. Detection of intraepidermal malignant melanoma in vivo by confocal scanning laser microscopy. Melanoma Res 2001; 12: 349-355.
3 Langley RG, Rajadhyaksha M, Dwyer PJ, Sober AJ, Flotte TJ, Anderson RR. Confocal scanning laser microscopy of benign and malignant skin lesions in vivo. J Am Acad Dermatol 2001; 45: 365-376.
4 Harland CC, Kale SG, Jackson P, Mortimer PS, Bamber JC. Differentiation of common benign pigmented skin lesions from melanoma by highresolution ultrasound. Br J Dermatol 2000; 143: 281-289.
5 Lehmann TM, Meinzer HP, Tolxdorf T. Advantages in Biomedical Image Analysis – Past, Present and Future Challenges. Methods Inf Med 2004; 43 (04) 308-314.
6 Chrastek R, Skokan M, Lubecka L, Wolf M, Donath K, Jan J, Michelson G, Niemann H. Multimodal Retinal Image Registration for Optic Disk Segmentation. Methods Inf Med 2004; 43 (04) 336-342.
7 Krügerl S, Vogt F, Hohenberger W, Paulus D, Niemann H, Schick CH. Evaluation of Computerassisted Image Enhancement in Minimal Invasive Endoscopic Surgery. Methods Inf Med 2004; 43 (04) 362-366.
8 Adler W, Hothorn T, Lausen B. Simulation Based Analysis of Automated Classification of Medical Images. Methods Inf Med 2004; 43 (02) 150-155.
9 Gerger A, Pompl R, Smolle J, Stolz W. Automated epiluminescence microscopy – tissue counter analysis using CART and 1-NN in the diagnosis of Melanoma. Skin Res Technol 2003; 9 (02) 105-110.
10 Smolle J. Diagnostic Assessment of Cutaneous Melanoma and Common Nevi Using Tissue Counter Analysis. Analyt and Quant Cytol Histol 2000; 22 (04) 299-306.
11 Smolle J. Computer recognition of skin structures using discriminant and cluster analysis. Skin Research and Technology 2000; 6: 58-63.
12 Smolle J, Gerger A, Weger W, Kutzner H, Tronnier M. Tissue Counter Analysis of Histologic Sections of Melanoma: Influence of Mask Size and Shape, Feature Selection, Statistical Methods and Tissue Preparation. Anal Cell Pathol 2002; 24 2, 3 59-67.
13 Gerger A, Wiltgen M, Smolle J. Tissue counter analysis – A novel tool for the fully automated analysis of complex tissue scenes. Cytometry Part A 2004; 59A (01) 39-40.
14 Wiltgen M, Gerger A, Wagner C, Bergthaler P, Smolle J. Evaluation of the influence of image compression to the automatic discrimination of histological images of skin lesions. Methods Inf Med 2004; 43: 141-149.
15 Langley RGB, Rajadhyaksha M, Dwyer PJ, Sober AJ, Flotte TJ, Anderson RR. Confocal scanning laser microscopy of benign and malignant melanocytic skin lesions in vivo. J AM Acad Dermatol 2001; 45 (03) 365-376.
16 Goldgeier M, Alessi C, Muhlbauer JE. Immediate noninvasive diagnosis of herpes virus by confocal scanning laser microscopy. J Am Acad Dermatol 2002; 46: 783-785.
17 Aghassi D, Anderson RR, Gonzalez S. Confocal laser microscopic imaging of actinic keratoses in vivo: a preliminary report. J Am Acad Dermatol. 2000 pp 42-48.
18 Aghassi D, Anderson RR, Gonzalez S. Time-sequence histologic imaging of laser-treated cherry angiomas with in vivo confocal microscopy. J Am Acad Dermatol 2000; 43: 37-41.
19 Stolz W, Vogth T, Landthaler M, Hempfer S, Bingler P, Abmayr W. Differentiation between maligant melanomas and benign melanocytic nevi by computerized DNA cytometry of imprint specimens. J Cutan Pathol 1994; 21: 7-15.
20 Brown AR. Combined immunocytochemical staining and image analysis for the study of lymphocyte specificity and function in situ. J Immunol Methods 1990; 130: 410-414.
21 Hamilton PW, Bartels PH, Montironi R. et al. Automated histometry in quantitative prostate pathology. Analytical and Quantitative Cytology and Histology 1998; 20: 443-460.
22 Sahn EE, Thiers BH, Nicholson JH, Maize JC. A new method for comprehensive automatic morphologic image analysis of Langerhans cells. Am J Dermatopathol 1988; 10: 410-414.
23 Harms H, Aus HM, Haucke M, Gunzer U. Segmentation of stained blood cell images measured at high scanning density with high magnification and high numerical aperture optics. Cytometry 1992; 7: 522-531.
24 Wiltgen M, Gerger A, Smolle J. Tissue counter analysis of benign common nevi and malignant melanoma. Int J Med Inform 2003; 69 (01) 17-28.
25 Haralick RM, Shanmugam K, Dinstein I. Textural Features for Image Classification. EEE Transactions on Systems Man Cybernetics 1973; 3: 610-621.
26 Prasad L, Iyengar SS. Wavelet Analysis with Applications to Image Processing. Boca Raton, Boston, London, New York, Washington, D.C: CRC Press LLC; 1997
27 Mello-Thoms C, Dunn SM, Nodine CF, Kundel HL. An analysis of perceptual errors in reading mammograms using quasi-local spatial frequency spectra. Journal of Digital Imaging 2001; 14 (03) 117-123.
28 Terae S, Miyasaka K, Kudoh K, Nambu T, Shimizu T, Kaneko K, Yoshikawa H, Kishimoto R, Omatsu T, Fujita N. Wavelet compression on detection of brain lesions with magnetic resonance imaging. Journal of Digital Imaging 2000; 13 (04) 178-190.
29 Kerut EK, Given MB, Mc Ilwain E, Allen G, Espinoza C, Giles TD. Echocardiographic texture analysis using the wavelet transform: Differentiation of early heart muscle disease. Ultrasound in Medicine and Biology 2000; 26 (09) 1445-1453.
30 Press WH, Teukolsky SA, Vetterling WT, Flannery BP. Numerical Recipes in C: The Art of Scientific Computing, 2nd ed. Cambridge University Press; 1992
31 Tang YY, Yang LH, Liu J, Ma H. Wavelet Theory and its Application to Pattern Recognition. New Jersey, London, Singapore, Hong Kong, Taipei, Bangalore: World Scientific Publishing Company Inc; 2000
32 Wiltgen M, Gerger A, Wagner C, Bergthaler P, Smolle J. Discrimination of benign common nevi and malignant melanoma lesions by use of features based on spectral properties of the wavelet transform. Analytical and Quantitative Cytology and Histology 2003; 25 (05) 243-253.
33 Wiltgen M. Digitale Bildverarbeitung in der Medizin. Grundlagen der Verarbeitung bildhafter Informationen für die Interpretation und Kommunikation in der Medizin. Aachen: Shaker Verlag; 1999
34 Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and Regression Trees. New York, London: Chapman & Hall; 1993
35 Pellacani G, Cesinaro AM, Longo C, Grana C, Seidenari S. Microscopic in vivo description of cellular architecture of dermoscopic pigment network in nevi and melanomas. Arch Dermatol 2005; 141 (02) 147-154.
36 Gerger A, Koller S, Weger W, Richtig E, Kerl H, Samonigg H, Krippl P, Smolle J. Sensitivity and specificity of confocal laser-scanning microscopy for in vivo diagnosis of malignant skin tumors. Cancer. 2006; 107 (01) 193-200.
37 Langley RG, Burton E, Walsh N, Propperova I, Murray SJ. In vivo confocal scanning laser microscopy of benign lentigines: comparison to conventional histology and in vivo characteristics of lentigo maligna. J Am Acad Dermatol 2006; 55 (01) 88-97.