An Empirical Study of Nail Fungus Classification Using Deep and Traditional Machine Learning Methods

Document Type : Original Article

Authors

1 Department of Mechanical Engineering and Engineering Science, University of North Carolina at Charlotte, Charlotte, USA

2 Department of Electrical and Computer, Science and Research Branch, Islamic Azad University, Tehran, Iran

10.22034/jbr.2021.295687.1043

Abstract

Some of the main human health hazards occur through the consumption of fungus. It is detrimental to food and threatens human health. Fungus’s symptom is not clear, making them extremely harmful to human and food resources. Over the past few decades, many studies have been conducted on the early detection of fungus existence in biological systems. Fungus’s symptom is not clear, making them extremely harmful to human and food resources. Over the past few decades, many studies have been conducted on the early detection of fungus existence in biological systems. In this paper, we study and implement machine learning methods that can detect and classify fungus using nail finger fungus images. Our study shows that the neural network-based method and more importantly deep learning method using state-of-the-art CNN models have higher predictive performance compared to that of other machine learning approaches.
Keywords: Deep Learning, Feature Extraction, Conventional Machine Learning, Nail Fungus

Keywords


[1] Jia Y, Zhang Y, Weiss RJ, Wang Q, Shen J, Ren F, Chen Z, Nguyen P, Pang R, Moreno IL, Wu Y. Transfer learning from speaker verification to multispeaker text-to-speech synthesis. arXiv preprint arXiv:1806.04558. 2018 Jun 12.
[2] Aldalbahi A, Shahabi F, Jasim M. Instantaneous Beam Prediction Scheme Against Link Blockage in mmWave Communications. Applied Sciences. 2021 Jan;11(12):5601.
[3] Lai Y, Liu Y, Feng Y, Huang S, Zhao D. Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models. arXiv preprint arXiv:2104.07204. 2021 Apr 15.
[4] Aldalbahi A, Shahabi F, Jasim M. BRNN-LSTM for Initial Access in Millimeter Wave Communications. Electronics. 2021 Jan;10(13):1505.
[5] Zeinali B, Ayatollahi A, Kakooei M. A novel method of applying directional filter bank (DFB) for finger-knuckle-print (FKP) recognition. In2014 22nd Iranian conference on electrical engineering (ICEE) 2014 May 20 (pp. 500-504). IEEE.
[6] Nguyen H, Zhuang D, Wu PY, Chang M. Autogan-based dimension reduction for privacy preservation. Neurocomputing. 2020 Apr 7;384:94-103.
[7] Zhuang D, Wang S, Chang JM. FRiPAL: Face recognition in privacy abstraction layer. In2017 IEEE Conference on Dependable and Secure Computing 2017 Aug 7 (pp. 441-448). IEEE.
[8] de Freitas LF, Hamblin MR. Proposed mechanisms of photobiomodulation or low-level light therapy. IEEE Journal of selected topics in quantum electronics. 2016 Jun 9;22(3):348-64.
[9] George J, Haghshenas H, d’Hemecourt D, Zhu W, Zhang L, Sorger V. Scattering and absorption control in biocompatible fibers towards equalized photobiomodulation. Biomedical Optics Express. 2017 Mar 1;8(3):1589-97.
[10] Isensee F, Kickingereder P, Wick W, Bendszus M, Maier-Hein KH. Brain tumor segmentation and radiomics survival prediction: Contribution to the brats 2017 challenge. InInternational MICCAI Brainlesion Workshop 2017 Sep 14 (pp. 287-297). Springer, Cham.
[11] Ng HP, Ong SH, Foong KW, Goh PS, Nowinski WL. Medical image segmentation using k-means clustering and improved watershed algorithm. In2006 IEEE southwest symposium on image analysis and interpretation 2006 Mar 26 (pp. 61-65). IEEE.
[12] Zanddizari H, Nguyen N, Zeinali B, Chang JM. A new preprocessing approach to improve the performance of CNN-based skin lesion classification. Medical & Biological Engineering & Computing. 2021 May;59(5):1123-31.
[13] Khoshnevis SA, Sankar R. Applications of higher order statistics in electroencephalography signal processing: a comprehensive survey. IEEE Reviews in biomedical engineering. 2019 Nov 4;13:169-83.
[14] Morovati M. Increase the accuracy of speech signal categories in high noise environments. Journal of Bioengineering Research. 2020 Sep 1;2(3).
[15] Adnani AA, Dokami A, Morovati M. Fault detection in high speed helical gears considering signal processing method in real simulation. Latin American Journal of Solids and Structures. 2016;13:2113-40.
[16] Zeinali B, Zhuang D, Chang JM. ESAI: Efficient Split Artificial Intelligence via Early Exiting Using Neural Architecture Search. arXiv preprint arXiv:2106.12549. 2021 Jun 21.
[17] Yorulmaz O, Pearson TC, Cetin AE. Detection of fungal damaged popcorn using image property covariance features. Computers and electronics in agriculture. 2012 Jun 1;84:47-52.
[18 Leiva G, Mondragón G, Mery D, Aguilera J. The automatic sorting using image processing improves postharvest blueberries storage quality. InProceedings of 11th international congress on engineering and food 2011 May.
[19] Kheiralipour K, Ahmadi H, Rajabipour A, Rafiee S, Javan-Nikkhah M, Jayas DS. Development of a new threshold based classification model for analyzing thermal imaging data to detect fungal infection of pistachio kernel. Agricultural Research. 2013 Jun;2(2):127-31.
[20] Tallada JG, Wicklow DT, Pearson TC, Armstrong PR. Detection of fungus-infected corn kernels using near-infrared reflectance spectroscopy and color imaging. Transactions of the ASABE. 2011;54(3):1151-8.
[21] Pujari JD, Yakkundimath R, Byadgi AS. Classification of fungal disease symptoms affected on cereals using color texture features. International Journal of Signal Processing, Image Processing and Pattern Recognition. 2013 Jun;6(6):321-30.
[22] Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. 2012;25:1097-105.
[23] Szegedy C, Ioffe S, Vanhoucke V, Alemi AA. Inception-v4, inception-resnet and the impact of residual connections on learning. InThirty-first AAAI conference on artificial intelligence 2017 Feb 12.
[24] Tan M, Le Q. Efficientnet: Rethinking model scaling for convolutional neural networks. InInternational Conference on Machine Learning 2019 May 24 (pp. 6105-6114). PMLR.
[25] Chollet F. Xception: Deep learning with depthwise separable convolutions. InProceedings of the IEEE conference on computer vision and pattern recognition 2017 (pp. 1251-1258).
[26] Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. InProceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 2818-2826).
[27] Zoph B, Vasudevan V, Shlens J, Le QV. Learning transferable architectures for scalable image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition 2018 (pp. 8697-8710).
[28] Huang G, Liu Z, Van Der Maaten L, Weinberger KQ. Densely connected convolutional networks. InProceedings of the IEEE conference on computer vision and pattern recognition 2017 (pp. 4700-4708).
[29] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition 2016 (pp. 770-778).
[30] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. 2014 Sep 4.
[31] Zoph B, Vasudevan V, Shlens J, Le QV. Learning transferable architectures for scalable image recognition. InProceedings of the IEEE conference on computer vision and pattern recognition 2018 (pp. 8697-8710).
[32] Sandler M, Howard A, Zhu M, Zhmoginov A, Chen LC. Mobilenetv2: Inverted residuals and linear bottlenecks. InProceedings of the IEEE conference on computer vision and pattern recognition 2018 (pp. 4510-4520).
[33] Ahonen T, Hadid A, Pietikainen M. Face description with local binary patterns: Application to face recognition. IEEE transactions on pattern analysis and machine intelligence. 2006 Oct 30;28(12):2037-41.
[34] Haralick RM, Shanmugam K, Dinstein IH. Textural features for image classification. IEEE Transactions on systems, man, and cybernetics. 1973 Nov(6):610-21.
[35] Khotanzad A, Hong YH. Invariant image recognition by Zernike moments. IEEE Transactions on pattern analysis and machine intelligence. 1990 May;12(5):489-97.
[36] Hu MK. Visual pattern recognition by moment invariants. IRE transactions on information theory. 1962 Feb;8(2):179-87.
[37] Liaw A, Wiener M. Classification and regression by randomForest. R news. 2002 Dec 3;2(3):18-22.
[38] Fix E, Hodges JL. Discriminatory analysis. Nonparametric discrimination: Consistency properties. International Statistical Review/Revue Internationale de Statistique. 1989 Dec 1;57(3):238-47.
[39] Friedman JH. Greedy function approximation: a gradient boosting machine. Annals of statistics. 2001 Oct 1:1189-232.
[40] Han SS, Park GH, Lim W, Kim MS, Na JI, Park I, Chang SE. Deep neural networks show an equivalent and often superior performance to dermatologists in onychomycosis diagnosis: Automatic construction of onychomycosis datasets by region-based convolutional deep neural network. PloS one. 2018 Jan 19;13(1):e0191493.
[41] Chollet F. Keras. https:⁄⁄ keras. io.
[42] Izadi V, Abedi M, Bolandi H. Supervisory algorithm based on reaction wheel modelling and spectrum analysis for detection and classification of electromechanical faults. IET Science, Measurement & Technology. 2017 Nov 9;11(8):1085-93.
[43] Bradski G. The opencv library. Dr Dobb's J. Software Tools. 2000;25:120-5.
[44] Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J. Scikit-learn: Machine learning in Python. the Journal of machine Learning research. 2011 Nov 1;12:2825-30.
[45] Izadi V, Shahri PK, Ahani H. A compressed-sensing-based compressor for ECG. Biomedical engineering letters. 2020 May;10(2):299-307.