Segmentation of the melanoma lesion and its border

• Autorzy: Surówka Grzegorz , Ogorzałek Maciej

Identyfikatory

DOI

10.34768/amcs-2022-0047

• Języki publikacji: EN

Abstrakty

EN

Segmentation of the border of the human pigmented lesions has a direct impact on the diagnosis of malignant melanoma. In this work, we examine performance of (i) morphological segmentation of a pigmented lesion by region growing with the adaptive threshold and density-based DBSCAN clustering algorithm, and (ii) morphological segmentation of the pigmented lesion border by region growing of the lesion and the background skin. Research tasks (i) and (ii) are evaluated by a human expert and tested on two data sets, A and B, of different origins, resolution, and image quality. The preprocessing step consists of removing the black frame around the lesion and reducing noise and artifacts. The halo is removed by cutting out the dark circular region and filling it with an average skin color. Noise is reduced by a family of Gaussian filters 3×3−7×7 to improve the contrast and smooth out possible distortions. Some other filters are also tested. Artifacts like dark thick hair or ruler/ink markers are removed from the images by using the DullRazor closing images for all RGB colors for a hair brightness threshold below a value of 25 or, alternatively, by the BTH transform. For the segmentation, JFIF luminance representation is used. In the analysis (i), out of each dermoscopy image, a lesion segmentation mask is produced. For the region growing we get a sensitivity of 0.92/0.85, a precision of 0.98/0.91, and a border error of 0.08/0.15 for data sets A/B, respectively. For the density-based DBSCAN algorithm, we get a sensitivity of 0.91/0.89, a precision of 0.95/0.93, and a border error of 0.09/0.12 for data sets A/B, respectively. In the analysis (ii), out of each dermoscopy image, a series of lesion, background, and border segmentation images are derived. We get a sensitivity of about 0.89, a specificity of 0.94 and an accuracy of 0.91 for data set A, and a sensitivity of about 0.85, specificity of 0.91 and an accuracy of 0.89 for data set B. Our analyses show that the improved methods of region growing and density-based clustering performed after proper preprocessing may be good tools for the computer-aided melanoma diagnosis.

Słowa kluczowe

EN

computer aided diagnosis; DBSCAN; malignant melanoma; region growing

PL

diagnoza wspomagana komputerowo; DBSCAN; czerniak złośliwy; rozrost regionów

• Wydawca: Oficyna Wydawnicza Uniwersytetu Zielonogórskiego
• Czasopismo: International Journal of Applied Mathematics and Computer Science
• Rocznik: 2022
• Tom: Vol. 32, no. 4
• Strony: 683--699
• Opis fizyczny: Bibliogr. 62 poz., rys., tab.

Twórcy

autor

Surówka Grzegorz

• Department of Physics, Astronomy and Applied Computer Science, Jagiellonian University, ul. prof. Stanisława Łojasiewicza 11, 30-348 Kraków, Poland

autor

Ogorzałek Maciej

• Department of Physics, Astronomy and Applied Computer Science, Jagiellonian University, ul. prof. Stanisława Łojasiewicza 11, 30-348 Kraków, Poland

Bibliografia

• [1] ACS (2020). Key statistics for melanoma skin cancer, American Cancer Society, Atlanta, https://www.cancer.org /cancer/melanoma-skin-cancer/about/key-statistics.html.
• [2] Agarwal, A., Issac, A. and Dutta, M. (2017). A region growing based imaging method for lesion segmentation from dermoscopic images, 4th IEEE Uttar Pradesh Section International Conference on Electrical, Computer and Electronics, Mathura, India, pp. 632–637.
• [3] Ahn, E., Kim, J., Bi, L., Kumar, A., Li, C., Fulham, M. and Feng, D. (2017). Saliency-based lesion segmentation via background detection in dermoscopic images, Journal of Biomedical and Health Informatics 21(6): 1685–1693.
• [4] Ali, A.-R., Li, J., Yang, G. and O’Shea, S. (2020). A machine learning approach to automatic detection of irregularity in skin lesion border using dermoscopic images, PeerJ Computer Science 6: e268.
• [5] Aljanabi,M., Özok, Y., Rahebi, J. and Abdullah, A. (2018). Skin lesion segmentation method for dermoscopy images using artificial bee colony algorithm, Symmetry 10(8): 347.
• [6] Ankerst, M., Breunig, M., Kriegel, H. and Sander, J. (1999). Optics: Ordering points to identify the clustering structure, ACM Sigmod Record 28(2): 49–60.
• [7] Ashour, A., Hawas, A., Guo, Y. and Wahba, M. (2018). A novel optimized neutrosophic k-means using genetic algorithm for skin lesion detection in dermoscopy images, Signal, Image and Video Processing 12(7): 1311–1318.
• [8] Bentley, J. (1975). Multidimensional binary search trees used for associative searching, Communications of the ACM 18(9): 509–517.
• [9] Bi, L., Kim, J., Ahn, E., Feng, D. and Fulham, M. (2016). Automated skin lesion segmentation via image-wise supervised learning and multi-scale superpixel based cellular automata, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI), Prague, Czech Republic, pp. 1059–1062.
• [10] Bi, L., Kim, J., Ahn, E., Kumar, A., Fulham, M. and Feng, D. (2017). Dermoscopic image segmentation via multistage fully convolutional networks, IEEE Transactions on Biomedical Engineering 64(9): 2065–2074.
• [11] Bozorgtabar, B., Abedini, M. and Garnavi, R. (2016). Sparse coding based skin lesion segmentation using dynamic rule-based refinement, International Workshop on Machine Learning in Medical Imaging, Athens, Greece, pp. 254–261.
• [12] Campello, R., Moulavi, D. and Sander, J. (2013). Density-based clustering based on hierarchical density estimates, Pacific-Asia Conference on Knowledge Discovery and Data Mining, Gold Coast, Australia, pp. 160–172.
• [13] Celebi, E., Codella, N. and Halpern, A. (2019). Dermoscopy image analysis: Overview and future directions, Journal of Biomedical and Health Informatics 23(2): 474–478.
• [14] Celebi, E., Wen, Q., Hwang, S., Iyatomi, H. and Schaefer, G. (2013). Lesion border detection in dermoscopy images using ensembles of thresholding methods, Skin Research and Technology 19(1): e252–e258.
• [15] Celebi, M., Kingravi, H. and Iyatomi, H. (2008). Border detection in dermoscopy images using statistical region merging, Skin Research and Technology 14(3): 347–353.
• [16] Celebi, M., Kingravi, H. and Uddin, B. (2007). A methodological approach to the classification of dermoscopy images, Computerized Medical Imaging and Graphics 31(6): 362–373.
• [17] Celebi, M., Wen, Q., Iyatomi, H., Shimizu, K., Zhou, H. and Schaefer, G. (2015). A state-of-the-art survey on lesion border detection in dermoscopy images, Dermoscopy Image Analysis 10: 97–129.
• [18] Codella, N., Rotemberg, V., Tschandl, P., Celebi, M., Dusza, S., Gutman, D., Helba, B., Kalloo, A., Liopyris, K., Marchetti, M., Kittler, H. and Halpern, A. (2019). Skin lesion analysis toward melanoma detection 2018: A challenge hosted by the International Skin Imaging Collaboration (ISIC), arXiv 1902.03368.
• [19] De Vita, V., Di Leo, G., Fabbrocini, G., Liguori, C., Paolillo, A. and Sommella, P. (2012). Statistical techniques applied to the automatic diagnosis of dermoscopic images, Acta Imeko 1(1): 7–18.
• [20] Ester, M., Kriegel, H., Sander, J. and Xu, X. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise, Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining, Portland, USA, pp. 226–231.
• [21] Esteva, A., Kuprel, B., Novoa, R., Ko, J., Swetter, S., Blau, H. and Thrun, S. (2017). Dermatologist-level classification of skin cancer with deep neural networks, Nature 542(7639): 115–118.
• [22] Ferreira, P., Mendona, T. and Rocha, P. (2013). A wide spread of algorithms for automatic segmentation of dermoscopic images, Iberian Conference on Pattern Recognition and Image Analysis, Madeira, Portugal, pp. 592–599.
• [23] Goyal, M., Oakley, A., Bansal, P., Dancey, D. and Yap, M. (2019). Skin lesion segmentation in dermoscopic images with ensemble deep learning methods, IEEE Access 8: 4171–4181.
• [24] Guaragnella, C. and Rizzi, M. (2020). Simple and accurate border detection algorithm for melanoma computer aided diagnosis, Diagnostics 10(6): 423.
• [25] Hahsler, M. (2021). Density based clustering of applications with noise (DBSCAN) and related algorithms—R package, https://github.com/mhahsler/dbscan.
• [26] Hahsler, M., Piekenbrock, M. and Doran, D. (2019). DBSCAN: Fast density-based clustering with R, Journal of Statistical Software 91: 1–30.
• [27] Hinneburg, A. and Keim, D. A. (1998). An efficient approach to clustering in large multimedia databases with noise, Proceedings of the 4th International Conference on Knowledge Discovery and Data Mining, New York, USA, pp. 58–65.
• [28] Hornik, K. (2021). The Comprehensive R Archive Network, https://cran.r-project.org.
• [29] Indraswari, R., Herulambang, W. and Rokhana, R. (2017). Melanoma classification using automatic region growing for image segmentation, Proceeding of the International Conference on Technology and Applications, Surabaya, Indonesia, pp. 165–172.
• [30] Jaworek-Korjakowska, J. and Tadeusiewicz, R. (2013). Hair removal from dermoscopic color images, Bio-Algorithms and Med-Systems 9(2): 53–58.
• [31] Jensen, D. and Elewski, B. (2015). The ABCDEF rule: Combining the ‘ABCDE RULE’ and the ‘ugly duckling sign’ in an effort to improve patient self-screening examinations, Journal of Clinical and Aesthetic Dermatology 8(2): 15.
• [32] Keefe, M., Dick, D. and Wakeel, R. (1990). A study of the value of the seven-point checklist in distinguishing benign pigmented lesions from melanoma, Clinical and Experimental Dermatology 15(3): 167–171.
• [33] Khan, M., Akram, T., Sharif, M., Shahzad, A., Aurangzeb, K., Alhussein, M., Haider, S. and Altamrah, A. (2018). An implementation of normal distribution based segmentation and entropy controlled features selection for skin lesion detection and classification, BMC Cancer 18(1): 1–20.
• [34] Kockara, S., Mete, M., Chen, B. and Aydin, K. (2010). Analysis of density based and fuzzy c-means clustering methods on lesion border extraction in dermoscopy images, BMC Bioinformatics 11(6): 1–11.
• [35] Kroon, D. (2004). Region growing, https://www.mathworks.com/matlabcentral/fileexchange/19084-region-growing.
• [36] Lee, T., Ng, V., Gallagher, R., Coldman, A. and McLean, D. (1997). DullRazor: A software approach to hair removal from images, Computers in Biology and Medicine 27(6): 533–543.
• [37] Louhichi, S., Gzara, M. and Abdallah, H. (2018). Skin lesion segmentation using multiple density clustering algorithm mdcut and region growing, IEEE/ACIS 17th International Conference on Computer and Information Science, Singapore, Singapore, pp. 74–79.
• [38] Louhichi, S., Gzara, M. and Ben-Abdallah, H. (2017). Unsupervised varied density based clustering algorithm using spline, Pattern Recognition Letters 93: 48–57.
• [39] Masood, A. and Al-Jumaily, A. (2013). Computer aided diagnostic support system for skin cancer: A review of techniques and algorithms, International Journal of Biomedical Imaging 7: 323268.
• [40] Melanoma ML (2018). Data set, https://easy.dans.knaw.nl/ui/datasets/id/easy-dataset:114463, DOI: 10.17026/dans-zue-zz2y.
• [41] Mendonça, T., Ferreira, P., Marques, J., Marcal, A. and Rozeira, J. (2013). Ph2—A dermoscopic image database for research and benchmarking, 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Osaka, Japan, pp. 5437–5440.
• [42] Mete, M., Kockara, S. and Aydin, K. (2011). Fast density-based lesion detection in dermoscopy images, Computerized Medical Imaging and Graphics 35(2): 128–136.
• [43] Mete, M. and Sirakov, N. (2010). Lesion detection in dermoscopy images with novel density-based and active contour approaches, BMC Bioinformatics 11(6): 1–13.
• [44] Mishra, N. and Celebi, M. (2016). An overview of melanoma detection in dermoscopy images using image processing and machine learning, arXiv 1601.07843.
• [45] Møllersen, K., Kirchesch, H.M., Schopf, T.G. and Godtliebsen, F. (2010). Unsupervised segmentation for digital dermoscopic images, Skin Research and Technology 16(4): 401–407.
• [46] Mount, D. and Arya, S. (2010). ANN: A library for approximate nearest neighbor searching, https://github.com/dials/annlib.
• [47] Oliveira, R., Mercedes, F., Ma, Z., Papa, J., Pereira, A. and Tavares, J. (2016). Computational methods for the image segmentation of pigmented skin lesions: A review, Computer Methods and Programs in Biomedicine 131: 127–141.
• [48] Oliveira, R., Papa, J. and Pereira, A. (2018). Computational methods for pigmented skin lesion classification in images: Review and future trends, Neural Computing and Applications 29(3): 613–636.
• [49] Olugbara, O., Taiwo, T. and Heukelman, D. (2018). Segmentation of melanoma skin lesion using perceptual color difference saliency with morphological analysis, Mathematical Problems in Engineering 2018, Article ID: 1524286.
• [50] Pathan, S., Prabhu, K. and Siddalingaswamy, P. (2018a). Hair detection and lesion segmentation in dermoscopic images using domain knowledge, Medical & Biological Engineering & Computing 56(11): 2051–2065.
• [51] Pathan, S., Prabhu, K. and Siddalingaswamy, P. (2018b). Techniques and algorithms for computer aided diagnosis of pigmented skin lesions—A review, Biomedical Signal Processing and Control 39: 237–262.
• [52] Patiño, D., Avendaño, J. and Branch, J. (2018). Automatic skin lesion segmentation on dermoscopic images by the means of superpixel merging, International Conference on Medical Image Computing and Computer-Assisted Intervention, Granada, Spain, pp. 728–736.
• [53] Pennisi, A., Bloisi, D., Nardi, D., Giampetruzzi, A., Mondino, C. and Facchiano, A. (2016). Skin lesion image segmentation using Delaunay triangulation for melanoma detection, Computerized Medical Imaging and Graphics 52: 89–103.
• [54] Pradhan, R., Kumar, S., Agarwal, R., Pradhan, M.P. and Ghose, M. (2010). Contour line tracing algorithm for digital topographic maps, International Journal of Image Processing 4(2): 156–163.
• [55] Rizzi, M. and Guaragnella, C. (2020). Skin lesion segmentation using image bit-plane multilayer approach, Applied Sciences 10(9): 3045.
• [56] Sadeghi, M., Razmara, M., Lee, T. and Atkins, M. (2011). A novel method for detection of pigment network in dermoscopic images using graphs, Computerized Medical Imaging and Graphics 35(2): 137–143.
• [57] Smaoui, N. and Bessassi, S. (2013). Melanoma skin cancer detection based on region growing segmentation, International Journal of Computer Vision and Signal Processing 1(1): 1–7.
• [58] Stanley, R., Stoecker, W. and Moss, R. (2007). A relative color approach to color discrimination for malignant melanoma detection in dermoscopy images, Skin Research and Technology 13(1): 62–72.
• [59] Suer, S., Kockara, S. and Mete, M. (2011). An improved border detection in dermoscopy images for density based clustering, BMC Bioinformatics 12(10): 1–10.
• [60] Vestergaard, M., Macaskill, P., Holt, P. and Menzies, S. (2008). Dermoscopy compared with naked eye examination for the diagnosis of primary melanoma: A meta-analysis of studies performed in a clinical setting, British Journal of Dermatology 159(3): 669–676.
• [61] Wang, H., Moss, R., Chen, X. and Stanley, R. (2011). Modified watershed technique and post-processing for segmentation of skin lesions in dermoscopy images, Computerized Medical Imaging and Graphics 35(2): 116–120.
• [62] Zhou, H., Schaefer, G., Celebi, M., Lin, F. and Liu, T. (2011). Gradient vector flow with mean shift for skin lesion segmentation, Computerized Medical Imaging and Graphics 35(2): 121–127.

Uwagi

PL

Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023)