Towards the automatic detection of skin lesion shape asymmetry, color variegation and diameter in dermoscopic images

Asymmetry, color variegation and diameter are considered strong indicators of malignant melanoma. The subjectivity inherent in the first two features and the fact that 10% of melanomas tend to be missed in the early diagnosis due to having a diameter less than 6mm, deem it necessary to develop an objective computer vision system to evaluate these criteria and aid in the early detection of melanoma which could eventually lead to a higher 5-year survival rate. This paper proposes an approach for evaluating the three criteria objectively, whereby we develop a measure to find asymmetry with the aid of a decision tree which we train on the extracted asymmetry measures and then use to predict the asymmetry of new skin lesion images. A range of colors that demonstrate the suspicious colors for the color variegation feature have been derived, and Feret’s diameter has been utilized to find the diameter of the skin lesion. The decision tree is 80% accurate in determining the asymmetry of skin lesions, and the number of suspicious colors and diameter values are objectively identified.

[1]  Tim K. Lee,et al.  Determining the asymmetry of skin lesion with fuzzy borders , 2005, Comput. Biol. Medicine.

[2]  S. B. Whitaker.  Oral and maxillofacial pathology. , 2000, Journal of the American Dental Association.

[3]  L. R. Dice.  Measures of the Amount of Ecologic Association Between Species , 1945 .

[4]  G. Grammatikopoulos,et al.  Automated malignant melanoma detection using MATLAB , 2006 .

[5]  P Barbini,et al.  Digital dermoscopy analysis for the differentiation of atypical nevi and early melanoma: a new quantitative semiology. , 1999, Archives of dermatology.

[6]  Pavlos I. Lazaridis,et al.  Simple Matlab Tool for Automated Malignant Melanoma Diagnosis , 2007 .

[7]  Harald Kittler,et al.  Descriptor : The HAM 10000 dataset , a large collection of multi-source dermatoscopic images of common pigmented skin lesions , 2018 .

[8]  Jingdong Wang,et al.  Salient Object Detection: A Discriminative Regional Feature Integration Approach , 2013, International Journal of Computer Vision.

[9]  Philip J. Morrow,et al.  Determination of Optimal Axes for Skin Lesion Asymmetry Quantification , 2007, 2007 IEEE International Conference on Image Processing.

[10]  Massimo Ferri,et al.  Qualitative asymmetry measure for melanoma detection , 2004, 2004 2nd IEEE International Symposium on Biomedical Imaging: Nano to Macro (IEEE Cat No. 04EX821).

[11]  A. Tenenhaus,et al.  Detection of melanoma from dermoscopic images of naevi acquired under uncontrolled conditions , 2010, Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging.

[12]  M. Vinceti,et al.  Relationship between histological and computer-based assessment of melanoma diameter and thickness in head versus trunk-limbs melanomas , 2013 .

[13]  G Pellacani,et al.  Digital videomicroscopy and image analysis with automatic classification for detection of thin melanomas. , 1999, Melanoma research.

[14]  Santosh Pandey,et al.  Skin Cancer Diagnostics with an All-Inclusive Smartphone Application , 2019, Symmetry.

[15]  Chi-Keung Tang,et al.  KNN Matting , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Yuxiang Sun,et al.  Active Perception for Foreground Segmentation: An RGB-D Data-Based Background Modeling Method , 2019, IEEE Transactions on Automation Science and Engineering.

[17]  Noel C. F. Codella,et al.  Skin lesion analysis toward melanoma detection: A challenge at the 2017 International symposium on biomedical imaging (ISBI), hosted by the international skin imaging collaboration (ISIC) , 2016, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[18]  Weidong Xu,et al.  Irregularity and Asymmetry Analysis of Skin Lesions Based on Multi-Scale Local Fractal Distributions , 2009, 2009 2nd International Congress on Image and Signal Processing.

[19]  Ali Gooya,et al.  Supervised Saliency Map Driven Segmentation of Lesions in Dermoscopic Images , 2017, IEEE Journal of Biomedical and Health Informatics.

[20]  P. Groenen,et al.  Fuzzy Clustering with Minkowski Distance Functions , 2007 .

[21]  Reda Kasmi,et al.  Classification of malignant melanoma and benign skin lesions: implementation of automatic ABCD rule , 2016, IET Image Process..

[22]  George S. Sebestyen,et al.  Decision-making processes in pattern recognition , 1962 .

[23]  Dan S. Bloomberg,et al.  Measuring document image skew and orientation , 1995, Electronic Imaging.

[24]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[25]  W V Stoecker,et al.  Automatic detection of asymmetry in skin tumors. , 1992, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[26]  W. Walton,et al.  Feret's Statistical Diameter as a Measure of Particle Size , 1948, Nature.

[27]  P. Pardalos,et al.  Clustering challenges in biological networks , 2009 .

[28]  Chen Li.  Content-based microscopic image analysis , 2016 .

[29]  W. Stolz,et al.  The ABCD rule of dermatoscopy. High prospective value in the diagnosis of doubtful melanocytic skin lesions. , 1994, Journal of the American Academy of Dermatology.

[30]  Thomas P. Trappenberg,et al.  Supervised Versus Unsupervised Deep Learning Based Methods for Skin Lesion Segmentation in Dermoscopy Images , 2019, Canadian Conference on AI.

[31]  James Bailey,et al.  Computer-Aided Diagnosis of Melanoma Using Border- and Wavelet-Based Texture Analysis , 2012, IEEE Transactions on Information Technology in Biomedicine.

[32]  Thomas P. Trappenberg,et al.  A Deep Learning Based Approach to Skin Lesion Border Extraction With a Novel Edge Detector in Dermoscopy Images , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[33]  Gary S. Rogers,et al.  Diagnosis and Treatment of Early Melanoma: NIH Consensus Development Panel on Early Melanoma , 1992 .

[34]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[35]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[36]  In consideration of the E in the melanoma ABCDE mnemonic. , 2006, Archives of dermatology.

[37]  Wayne Ieee,et al.  Entropy Nets: From Decision Trees to Neural Networks , 1990 .

[38]  G. Argenziano,et al.  Dermoscopy of pigmented skin lesions. , 2001, European journal of dermatology : EJD.

[39]  Lars Kai Hansen,et al.  A probabilistic framework for classification of dermatoscopic images , 1999 .

[40]  Ihab Zaqout,et al.  Diagnosis of Skin Lesions Based on Dermoscopic Images Using Image Processing Techniques , 2016, Pattern Recognition - Selected Methods and Applications.

[41]  Abder-Rahman Ali,et al.  A machine learning approach to automatic detection of irregularity in skin lesion border using dermoscopic images , 2020, PeerJ Comput. Sci..

[42]  V. Ng,et al.  Measuring asymmetries of skin lesions , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[43]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[44]  J. MacQueen.  Some methods for classification and analysis of multivariate observations , 1967 .

[45]  David G. Lowe,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004, International Journal of Computer Vision.

[46]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.