An Ensemble of Statistical Metadata and CNN Classification of Class Imbalanced Skin Lesion Data

• Autorzy: Nayak Sachin , Vincent Shweta , Sumathi K. , Kumar Om Prakash , Pathan Sameena

Identyfikatory

DOI

10.24425/ijet.2022.139875

• Języki publikacji: EN

Abstrakty

EN

Skin Cancer is one of the most widely present forms of cancer. The correct classification of skin lesions as malignant or benign is a complex process that has to be undertaken by experienced specialists. Another major issue of the class imbalance of data causes a bias in the results of classification. This article presents a novel approach to the usage of metadata of skin lesions images to classify them. The usage of techniques addresses the problem of class imbalance to nullify the imbalances. Further, the use of a convolutional neural network (CNN) is proposed to finetune the skin lesion data classification. Ultimately, it is proven that an ensemble of statistical metadata analysis and CNN usage would result in the highest accuracy of skin color classification instead of using the two techniques separately.

Słowa kluczowe

EN

classification; convolutional neural networks; ensemble learning; machine learning; metadata

• Wydawca: Polish Academy of Sciences, Committee of Electronics and Telecommunication
• Czasopismo: International Journal of Electronics and Telecommunications
• Rocznik: 2022
• Tom: Vol. 68, No. 2
• Strony: 251--257
• Opis fizyczny: Bibliogr. 25 poz., tab.

Twórcy

autor

Nayak Sachin

• Department of Mechatronics Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India

autor

Vincent Shweta

• Department of Mechatronics Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India

autor

Sumathi K.

• Department of Mathematics, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India

autor

Kumar Om Prakash

• Department of Electronics and Communication Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India

autor

Pathan Sameena

• Department of Information and Communication Technology, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Karnataka, India

Bibliografia

• [1] R. L. Siegel, K. D. Miller, S. A. Fedewa, D. J. Ahnen, R. G. S. Meester, A. Barzi, A. Jemal, “Cancer statistics,” CA: A cancer journal for Clinicians, 67(1), 7–30, 2017. https://doi.org/10.3322/caac.21395
• [2] Z. Apalla, D. Nashan, R. B. Weller, X. Castellsagué, “Skin Cancer: Epidemiology, Disease Burden, Pathophysiology, Diagnosis, and Therapeutic Approaches,” Dermatology and Therapy, 7(1), 5–19, 2017. http://dx.doi.org/10.1007/s13555-016-0165-y
• [3] K. Pai, A. Giridharan, “Convolutional Neural Networks for classifying skin lesions,” Proceedings of TENCON 2019 IEEE conference, 1794-1796, 2019. https://doi.org/10.1109/TENCON.2019.8929461
• [4] A. Mikołajczyk, M. Grochowski, “Data augmentation for improving deep learning in image classification problem,” Proceedings of 2018 International Interdisciplinary PhD Workshop (IIPhDW), 117-122, 2018. http://dx.doi.org/10.1109/IIPHDW.2018.8388338
• [5] B. Harangi, “Skin lesion classification with ensembles of deep convolutional neural networks,” Journal of Biomedical Informatics, 86, 25-32, 2018. http://dx.doi.org/10.1016/j.jbi.2018.08.006
• [6] E. Ayan, H. U. Ünver, “Data Augmentation Importance for Classification of Skin Lesions via Deep Learning,” Proceedings of 2018 Electric Electronics, Computer Science, Biomedical Engineering Meeting(EBBT), 10-15, 2018. http://dx.doi.org/10.1109/EBBT.2018.8391469
• [7] N. Gessert, T. Sentker, F. Madesta, R. Schmitz, H. Kniep, I. Baltruschat, R. Werner, A. Schlaefer, “Skin Lesion Classification Using CNNs with Patch-Based Attention and Diagnosis-Guided Loss Weighting,” IEEE Transactions on Biomedical Engineering, 1-1, 99, 2019. http://dx.doi.org/10.1109/TBME.2019.2915839
• [8] K. M. Hosny, M. A. Kassen, M. M. Foaud, “Classification of skin lesions using transfer learning and augmentation with Alex-net,” PLOS One, 17-20, 2019. http://dx.doi.org/10.1371/journal.pone.0217293
• [9] N. Hameed, A. M. Shabut, M. A. Hossain, “Multi-Class Skin Diseases Classification Using Deep Convolutional Neural Network and Support Vector Machine,” Proceedings of 12th International Conference on Software, Knowledge, Information Management and Applications (SKIMA), 23-30, 2019 http://dx.doi.org/10.1109/SKIMA.2018.8631525
• [10] M. A. Albahar, “Skin Lesion Classification Using Convolutional Neural Network With Novel Regularizer,” IEEE Access, 7, 2019. http://dx.doi.org/10.1109/ACCESS.2019.2906241
• [11] A. Hekler, J. S. Utikal, A. H. Enk, “Superior skin cancer classification by the combination of human and artificial intelligence,” European Journal of Cancer, 120, 114-121, 2019. http://dx.doi.org/10.1016/j.ejca.2019.07.019
• [12] H. Kittler, H. Pehamberger, K. Wolff, M. Binder, “Diagnostic accuracy of Dermatoscopy,” Lancet Oncology, 3(3), 159-165, 2002. https://doi.org/10.1016/s1470-2045(02)00679-4
• [13] M. Maragoudakis, I. Maglogiannis, “Skin lesion diagnosis from images using novel ensemble classification techniques,” in Information Technology and Applications in Biomedicine (ITAB), 2010 10th IEEE International Conference , 1–5, 2010. http://dx.doi.org/10.1109/ITAB.2010.5687620
• [14] J. Kawahara, G. Hamarneh, “Multi-resolution-tract CNN with hybrid pretrained and skin-lesion trained layers,” in International Workshop on Machine Learning in Medical Imaging. Springer, 164–171, 2016. http://dx.doi.org/10.1007/978-3-319-47157-0_20
• [15] P. Tschandl, C. Rosendahl, H. Kittler, “The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions,” Scientific Data, 5, 180161, 2018. http://dx.doi.org/10.1038/sdata.2018.161
• [16] S. S. Shapiro, M. B. Wilk, “An analysis of variance test for normality (complete samples) ,” Biometrika, 52(3–4), 591–611, 1965. https://doi.org/10.2307/2333709
• [17] B. Ralph, D. E. E. Cureton, “Test of Normality Against Skewed Alternatives,” Psychological Bulletin, 78, 262-265, 1972. 2 https://dx.doi.org/10.1037/h0033113
• [18] M. A. Stephens, “EDF Statistics for Goodness of Fit and Some Comparisons,” Journal of the American Statistical Association. , 69: 730–737, 1974. https://doi.org/10.2307/2286009
• [19] W. H. Kruskal, W. A. Wallis, “Use of ranks in one-criterion variance analysis,” Journal of American Statistics Association, 583–621, 1952. https://doi.org/10.2307/2280779
• [20] N. Nachar, “The Mann-Whitney U: A test for assessing whether two independent samples come from the same distribution,” Tutorials in Quantitative Methods for Psychology, 4(1), 13-20, 2008. http://dx.doi.org/10.20982/tqmp.04.1.p013
• [21] S. W. Scheff, “Chapter 8- Nano-parametric Statistics,” Fundamental Statistical Principles for the Neurobiologist-A Survival Guide, 157-182, 2016.
• [22] K. K. G. Lan, Y. Soo, C. Siu, M. Wang, “The use of Weighted Z-tests in Medical Research,” Journal of Biopharmaceutical Statistics, 15(4), 625-639, 2005. http://dx.doi.org/10.1081/BIP-200062284
• [23] H. Yusop, F. F. Yeng, A. Jumadi, A. Mahadi, M. N. Ali, N. Johari, “The Effectiveness of Excellence Camp: A study on Paired Sample,” Procedia Economics and Finance, 31, 453-461, 2015. https://doi.org/10.1016/S2212-5671(15)01174-0
• [24] H. Abdi, L. J. Williams, “Tukey’s Honestly Significant Difference (HSD) Test”, Encyclopedia of Research Design., 2010.
• [25] D. Fraiman, R. Fraiman, “An ANOVA approach for statistical comparisons of brain networks,” Scientific Repository, 8, 4746, 2018. https://doi.org/10.1038/s41598-018-23152-5

Uwagi

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).