Automatic Differential Diagnosis of Melanocytic Skin Tumors Using Ultrasound Data.

We describe a novel automatic diagnostic system based on quantitative analysis of ultrasound data for differential diagnosis of melanocytic skin tumors. The proposed method has been tested on 160 ultrasound data sets (80 of malignant melanoma and 80 of benign melanocytic nevi). Acoustical, textural and shape features have been evaluated for each segmented lesion. Using parameters selected according to Mahalanobis distance and linear support vector machine classifier, we are able to differentiate malignant melanoma from benign melanocytic skin tumors with 82.4% accuracy (sensitivity = 85.8%, specificity = 79.6%). The results indicate that high-frequency ultrasound has the potential to be used for differential diagnosis of melanocytic skin tumors and to provide supplementary information on lesion penetration depth. The proposed system can be used as an additional tool for clinical decision support to improve the early-stage detection of malignant melanoma.

[1]  Wagner Coelho de Albuquerque Pereira,et al.  Characterization of in vitro healthy and pathological human liver tissue periodicity using backscattered ultrasound signals. , 2006, Ultrasound in medicine & biology.

[2]  William D O'Brien,et al.  Characterization of tissue microstructure using ultrasonic backscatter: theory and technique for optimization using a Gaussian form factor. , 2002, The Journal of the Acoustical Society of America.

[3]  E. Feleppa,et al.  Statistics of ultrasonic spectral parameters for prostate and liver examinations , 1997, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[4]  C Edwards,et al.  The use of A‐scan ultrasound in the assessment of small skin tumours , 1989, The British journal of dermatology.

[5]  L. Vaillant,et al.  High‐resolution ultrasonography assists the differential diagnosis of blue naevi and cutaneous metastases of melanoma , 2010, The British journal of dermatology.

[6]  Jonathan Mamou,et al.  Quantitative Ultrasound in Soft Tissues , 2013, Springer Netherlands.

[7]  Ernest J. Feleppa,et al.  Ultrasonic spectrum analysis for tissue evaluation , 2003, Pattern Recognit. Lett..

[8]  Ronald H. Silverman,et al.  Ultrasonic spectrum analysis for assays of different scatterer morphologies: theory and very-high frequency clinical results , 1996, 1996 IEEE Ultrasonics Symposium. Proceedings.

[9]  L Pourcelot,et al.  High-frequency estimation of the ultrasonic attenuation coefficient slope obtained in human skin: simulation and in vivo results. , 1999, Ultrasound in medicine & biology.

[10]  A. Hauschild,et al.  Sentinel node biopsy in melanoma , 2001, Virchows Archiv.

[11]  Frédéric Patat,et al.  High Resolution Ultrasound Imaging of Melanocytic and Other Pigmented Lesions of the Skin , 2011 .

[12]  J A Noble,et al.  Ultrasound image segmentation and tissue characterization , 2010, Proceedings of the Institution of Mechanical Engineers. Part H, Journal of engineering in medicine.

[13]  Timothy A Bigelow,et al.  Estimation of total attenuation and scatterer size from backscattered ultrasound waveforms. , 2005, The Journal of the Acoustical Society of America.

[14]  Yu-Len Huang,et al.  Support vector machines in sonography: application to decision making in the diagnosis of breast cancer. , 2005, Clinical imaging.

[15]  Guojun Lu,et al.  A comparative study of curvature scale space and Fourier descriptors for shape-based image retrieval , 2003, J. Vis. Commun. Image Represent..

[16]  H. Chenga,et al.  Automated breast cancer detection and classification using ultrasound images A survey , 2009 .

[17]  J. Bamber,et al.  Quantitative discrimination of pigmented lesions using three-dimensional high-resolution ultrasound reflex transmission imaging. , 2007, The Journal of investigative dermatology.

[18]  M A Srinivasan,et al.  High-frequency ultrasonic attenuation and backscatter coefficients of in vivo normal human dermis and subcutaneous fat. , 2001, Ultrasound in medicine & biology.

[19]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[20]  J C Bamber,et al.  Differentiation of common benign pigmented skin lesions from melanoma by high‐resolution ultrasound , 2000, The British journal of dermatology.

[21]  Bruce R Smoller,et al.  Histologic criteria for diagnosing primary cutaneous malignant melanoma , 2006, Modern Pathology.

[22]  Theofanis Sapatinas,et al.  Discriminant Analysis and Statistical Pattern Recognition , 2005 .

[23]  F. M. Hendriks,et al.  Mechanical Behaviour of Human Skin in Vivo , 2001 .

[24]  Tian Liu,et al.  A feasibility study of novel ultrasonic tissue characterization for prostate-cancer diagnosis: 2D spectrum analysis of in vivo data with histology as gold standard. , 2009, Medical physics.

[25]  Dar-Ren Chen,et al.  Diagnosis of breast tumors with ultrasonic texture analysis using support vector machines , 2006, Neural Computing & Applications.

[26]  R. Chang,et al.  Improvement in breast tumor discrimination by support vector machines and speckle-emphasis texture analysis. , 2003, Ultrasound in medicine & biology.

[27]  L. Landini,et al.  Evaluation of the attenuation coefficients in normal and pathological breast tissue , 1986, Medical and Biological Engineering and Computing.

[28]  Goutam Ghoshal,et al.  On the estimation of backscatter coefficients using single-element focused transducers. , 2011, The Journal of the Acoustical Society of America.

[29]  Josep Malvehy,et al.  Diagnosis and treatment of melanoma: European consensus-based interdisciplinary guideline. , 2010, European journal of cancer.

[30]  Jonathan Mamou,et al.  Review of Quantitative Ultrasound: Envelope Statistics and Backscatter Coefficient Imaging and Contributions to Diagnostic Ultrasound , 2016, IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control.

[31]  Helmut Ermert,et al.  Ultrasonic multifeature tissue characterization for prostate diagnostics. , 2003, Ultrasound in medicine & biology.

[32]  Jitendra Virmani,et al.  SVM-Based Characterization of Liver Ultrasound Images Using Wavelet Packet Texture Descriptors , 2013, Journal of Digital Imaging.

[33]  H. Ermert,et al.  Tissue-characterization of the prostate using radio frequency ultrasonic signals , 1999, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[34]  Josep Malvehy,et al.  Diagnosis and treatment of melanoma. European consensus-based interdisciplinary guideline - Update 2016. , 2012, European journal of cancer.

[35]  Mackie,et al.  Clinical accuracy of the diagnosis of cutaneous malignant melanoma , 1998, The British journal of dermatology.

[36]  H. Kittler,et al.  Diagnostic accuracy of dermoscopy. , 2002, The Lancet. Oncology.

[37]  G Berger,et al.  Computerized ultrasound B-scan characterization of breast nodules. , 2000, Ultrasound in medicine & biology.

[38]  J C Bamber,et al.  High frequency, high resolution B‐scan ultrasound in the assessment of skin tumours , 1993, The British journal of dermatology.

[39]  W. Moon,et al.  Computer‐aided diagnosis using morphological features for classifying breast lesions on ultrasound , 2008, Ultrasound in obstetrics & gynecology : the official journal of the International Society of Ultrasound in Obstetrics and Gynecology.

[40]  A.F.C. Infantosi,et al.  Classification of breast tumours on ultrasound images using morphometric parameters , 2005, IEEE International Workshop on Intelligent Signal Processing, 2005..

[41]  P. Rutkowski,et al.  High frequency ultrasonography of the skin and its role as an auxillary tool in diagnosis of benign and malignant cutaneous tumors--a comparison of two clinical cases. , 2015, Acta dermatovenerologica Croatica : ADC.

[42]  Tian Liu,et al.  Ultrasonic tissue characterization using 2-D spectrum analysis and its application in ocular tumor diagnosis. , 2004, Medical physics.

[43]  A. Hauschild,et al.  Diagnosis and treatment of melanoma. European consensus-based interdisciplinary guideline--Update 2012. , 2012, European journal of cancer.

[44]  B Finlay,et al.  Scanning electron microscopy of the human dermis under uni-axial strain. , 1969, Biomedical engineering.

[45]  R. Raišutis,et al.  Automated Estimation of Melanocytic Skin Tumor Thickness by Ultrasonic Radiofrequency Data , 2016, Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine.

[46]  D. Miller,et al.  Determining skin thickness with pulsed ultra sound. , 1979, The Journal of investigative dermatology.

[47]  F Davignon,et al.  A parametric imaging approach for the segmentation of ultrasound data. , 2005, Ultrasonics.

[48]  M. Schwarz,et al.  [Ranking of 20 MHz sonography of malignant melanoma and pigmented lesions in routine diagnosis]. , 1999, Ultraschall in der Medizin.

[49]  Shulin Tian,et al.  Feature Vector Selection Method Using Mahalanobis Distance for Diagnostics of Analog Circuits Based on LS-SVM , 2012, J. Electron. Test..

[50]  Andrew Kalisz,et al.  Ultrasonic Multi-Feature Analysis Procedure for Computer-Aided Diagnosis of Solid Breast Lesions , 2011, Ultrasonic imaging.

[51]  Tian Liu,et al.  Ultrasonic tissue characterization via 2-D spectrum analysis: theory and in vitro measurements. , 2007, Medical physics.

[52]  Claus Garbe,et al.  Melanoma epidemiology and trends. , 2009, Clinics in dermatology.

[53]  Ruey-Feng Chang,et al.  Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks. , 2002, Ultrasound in medicine & biology.