Melanoma Detection using Convolutional Neural Network with Transfer Learning on Dermoscopic and Macroscopic Images
Downloads
Background: Melanoma is a skin cancer that starts when the melanocytes that produce the skin color pigment start to grow out of control and form a cancer. Detecting melanoma early before it spreads to the lymph nodes and other parts of the body is very important because it makes a big difference to the patient's 5-year life expectancy. Screening is the process of conducting a skin examination to suspect a mole is melanoma using dermoscopic or macroscopic images. However, manual screening takes a long time. Therefore, automatic melanoma detection is needed to speed up the melanoma detection process. The previous studies still have weakness because it has low precision or recall, which means the model cannot predict melanoma accurately. The distribution of melanoma and moles datasets is imbalanced where the number of melanomas is less than moles. In addition, in previous study, comparisons of several CNN transfer learning architectures have not been carried out on dermoscopic and macroscopic images.
Objective: This study aims to detect melanoma using the Convolutional Neural Network (CNN) with transfer learning on dermoscopic and macroscopic melanoma images. CNN with Transfer learning is a popular method for classifying digital images with high accuracy.
Methods: This study compares four CNN with transfer learning architectures, namely MobileNet, Xception, VGG16, and ResNet50 on dermoscopic and macroscopic image. This research also uses black-hat filtering and inpainting at the preprocessing stage to remove hair from the skin image.
Results: MobileNet is the best model for classifying melanomas or moles in this experiment which has 83.86% of F1 score and 11 second of training time per epoch.
Conclusion: MobileNet and Xception have high average F1 scores of 84.42% and 80.00%, so they can detect melanoma accurately even though the number of melanoma datasets is less than moles. Therefore, it can be concluded that MobileNet and Xception are suitable models for classifying melanomas and moles. However, MobileNet has the fastest training time per epoch which is 11 seconds. In the future, oversampling method can be implemented to balance the number of datasets to improve the performance of the classification model.
A. C. Society, "Key Statistics for Melanoma Skin Cancer”, [Online]. Available: https://www.cancer.org/cancer/melanoma-skin-cancer/about/key-statistics.html
D. K. DePalo, K. M. Elleson, M. J. Carr, P. E. Spiess, and J. S. Zager, "Genitourinary melanoma: An overview for the clinician,” Asian J. Urol., Jun. 2022, doi: 10.1016/J.AJUR.2022.01.003.
A. Murugan, S. A. H. Nair, and K. P. S. Kumar, "Detection of Skin Cancer Using SVM, Random Forest and kNN Classifiers,” J. Med. Syst., vol. 43, no. 8, 2019, doi: 10.1007/s10916-019-1400-8.
"ISIC Archive.” https://www.isic-archive.com/#!/topWithHeader/wideContentTop/main (accessed Jul. 05, 2022).
J. Kavitha, S. A, and N. D, "Melanoma Detection in Dermoscopic Images using Global and Local Feature Extraction,” Int. J. Multimed. Ubiquitous Eng., vol. 12, no. 5, pp. 19–28, May 2017, doi: 10.14257/IJMUE.2017.12.5.02.
M. Ramezani, A. Karimian, and P. Moallem, "Automatic Detection of Malignant Melanoma using Macroscopic Images,” vol. 4, no. 4, 2014.
"Dermnet.com.” https://dermnet.com/ (accessed Aug. 20, 2022).
R. L. Hasanah and D. Riana, "Classification of Dermoscopic Image of Skin Cancer Using the GLCM Method and Multi-SVM Algorithm,” Rekayasa, vol. 14, no. 3, pp. 407–415, Dec. 2021, doi: 10.21107/REKAYASA.V14I3.12213.
T. Mendonca, P. M. Ferreira, J. S. Marques, A. R. S. Marcal, and J. Rozeira, "PH2 - A dermoscopic image database for research and benchmarking,” Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc. EMBS, pp. 5437–5440, 2013, doi: 10.1109/EMBC.2013.6610779.
V. Pillay and S. Viriri, "Skin Cancer Detection from Macroscopic Images,” 2019 Conf. Inf. Commun. Technol. Soc., pp. 1–9, 2019, doi: 10.1109/ICTAS.2019.8703611.
R. B. Oliveira, N. Marranghello, A. S. Pereira, J. Manuel, and R. S. Tavares, "A computational approach for detecting pigmented skin lesions in macroscopic images,” vol. 61, pp. 53–63, 2016, doi: 10.1016/j.eswa.2016.05.017.
"Loyola University Dermatology Medical Education Website.” http://www.meddean.luc.edu/lumen/meded/medicine/dermatology/melton/hello1.htm (accessed Aug. 24, 2022).
"YSP Dermatology Image Database.” http://ysp.in.coocan.jp/index_eng.htm (accessed Aug. 24, 2022).
"Interactive Dermatology Atlas.” https://www.dermatlas.net/ (accessed Jul. 05, 2022).
R. Abdelkader, N. Ramou, M. Khorchef, N. Chetih, and Y. Boutiche, "Segmentation of x-ray image for welding defects detection using an improved Chan-Vese model,” Mater. Today Proc., vol. 42, pp. 2963–2967, Jan. 2021, doi: 10.1016/J.MATPR.2020.12.806.
J. Hurtado and F. Reales, "A machine learning approach for the recognition of melanoma skin cancer on macroscopic images,” TELKOMNIKA Telecommun. Comput. Electron. Control, vol. 19, no. 4, pp. 1357–1368, 2021, doi: 10.12928/TELKOMNIKA.v19i4.20292.
"Dermatology database used in MED-NODE.” https://www.cs.rug.nl/~imaging/databases/melanoma_naevi/ (accessed Jul. 07, 2022).
A. Pacheco et al., "PAD-UFES-20: a skin lesion dataset composed of patient data and clinical images collected from smartphones,” vol. 1, 2020, doi: 10.17632/ZR7VGBCYR2.1.
M. B. Assad and R. Kiczales, "Deep Biomedical Image Classification Using Diagonal Bilinear Interpolation and residual network,” Int. J. Intell. Networks, vol. 1, pp. 148–156, Jan. 2020, doi: 10.1016/J.IJIN.2020.11.001.
M. Liao, Y. Q. Zhao, X. H. Wang, and P. S. Dai, "Retinal vessel enhancement based on multi-scale top-hat transformation and histogram fitting stretching,” Opt. Laser Technol., vol. 58, pp. 56–62, 2014, doi: 10.1016/J.OPTLASTEC.2013.10.018.
A. H. Khan, D. N. F. A. Iskandar, J. F. Al-Asad, and S. El-Nakla, "Classification of skin lesion with hair and artifacts removal using black-hat morphology and total variation,” Int. J. Comput. Digit. Syst., vol. 10, no. 1, 2021, doi: 10.12785/IJCDS/100157.
B. Li, B. Zheng, H. Li, and Y. Li, "Detail-enhanced image inpainting based on discrete wavelet transforms,” Signal Processing, vol. 189, p. 108278, Dec. 2021, doi: 10.1016/J.SIGPRO.2021.108278.
F. Farhangi, "Investigating the role of data preprocessing, hyperparameters tuning, and type of machine learning algorithm in the improvement of drowsy EEG signal modeling,” Intell. Syst. with Appl., vol. 15, p. 200100, Sep. 2022, doi: 10.1016/J.ISWA.2022.200100.
A. Michele, V. Colin, and D. D. Santika, "Mobilenet convolutional neural networks and support vector machines for palmprint recognition,” Procedia Comput. Sci., vol. 157, pp. 110–117, 2019, doi: 10.1016/J.PROCS.2019.08.147.
K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition,” Sep. 2015. Accessed: May 27, 2021. [Online]. Available: http://www.robots.ox.ac.uk/
F. Chollet, "XCeption: Deep Learning with Depthwise Separable Convolutions,” Comput. Vis. Found., 2016, doi: 10.4271/2014-01-0975.
K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 770–778, 2016, doi: 10.1109/CVPR.2016.90.
Copyright (c) 2022 The Authors. Published by Universitas Airlangga.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
All accepted papers will be published under a Creative Commons Attribution 4.0 International (CC BY 4.0) License. Authors retain copyright and grant the journal right of first publication. CC-BY Licenced means lets others to Share (copy and redistribute the material in any medium or format) and Adapt (remix, transform, and build upon the material for any purpose, even commercially).
