Melanoma is a malignant skin cancer that causes high mortality. Early detection of melanoma can save patients’ lives. The features of the skin lesion images can be extracted using computer techniques to differentiate early between melanoma and benign skin lesions.
OBJECTIVE:
A new model of empirical wavelet decomposition (EWD) based on tan hyperbolic modulated filter banks (THMFBs) (EWD-THMFBs) was used to obtain the features of skin lesion images by MATLAB software.
METHODS:
The EWD-THMFBs model was compared with the empirical short-time Fourier decomposition method based on THMFBs (ESTFD-THMFBs) and the empirical Fourier decomposition method based on THMFBs (EFD-THMFBs).
RESULTS:
The accuracy rates obtained for EWD-THMFBs, ESTFD-THMFBs, and EFD-THMFBs models were 100%, 98.89%, and 83.33%, respectively. The area under the curve (AUC) was 1, 0.97, and 0.91, respectively.
CONCLUSION:
The EWD-THMFBs model performed best in extracting features from skin lesion images. This model can be programmed on a mobile to detect skin lesions in rural areas by a nurse before consulting a dermatologist.
AaqibMGhaniMKhanA. Deep Learning-Based Identification of Skin Cancer on Any Suspicious Lesion. 4th International Conference on Computing, Mathematics and Engineering Technologies (iCoMET), Sukkur, Pakistan. (2023); 1-6. doi: 10.1109/iCoMET57998.2023.10099160.
3.
TembhurneJVHebbarNPatilHYDiwanT. Skin cancer detection using ensemble of machine learning and deep learning techniques. Multimedia Tools Application.2023 Feb 16; 82: 27501-27524. doi: 10.1007/s11042-023-14697-3.
4.
HemalathaDLathaKNLathaPM. Skin Cancer Detection Using Deep Learning Technique. 2nd International Conference for Innovation in Technology (INOCON) Bangalore, India. 2023; 1-5. doi: 10.1109/INOCON57975.2023.10101344.
5.
SanvordekarMKuppiliVModiC. Machine Learning Approach for Skin Melanoma Classification. International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON), Bangalore, India.2022; 1-5. doi: 10.1109/SMARTGENCON56628.2022.10083665.
6.
NigarNUmarMShahzadMKIslamSAbaloD. A Deep Learning Approach Based on Explainable Artificial Intelligence for Skin Lesion Classification. IEEE Access.2022; 10: 113715-113725. doi: 10.1109/ACCESS.2022.3217217.
7.
SafdarKAkbarSGullS. An Automated Deep Learning based Ensemble Approach for Malignant Melanoma Detection using Dermoscopy Images. International Conference on Frontiers of Information Technology (FIT), Islamabad, Pakistan.2021; 206-211. doi: 10.1109/FIT53504.2021.00046.
8.
DasS. Automated Bias Reduction in Deep Learning Based Melanoma Diagnosis using a Semi-Supervised Algorithm. IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Houston, TX, USA.2021; 1719-1726. doi: 10.1109/BIBM52615.2021.9669772.
9.
JavaidASadiqMAkramF. Skin Cancer Classification Using Image Processing and Machine Learning. International Bhurban Conference on Applied Sciences and Technologies (IBCAST), Islamabad, Pakistan.2021; 439-444. doi: 10.1109/IBCAST51254.2021.9393198.
10.
GautamARamanB. Skin Cancer Classification from Dermoscopic Images using Feature Extraction Methods. IEEE REGION 10 CONFERENCE (TENCON), Osaka, Japan. 2020; 958-963. doi: 10.1109/TENCON50793.2020.9293863.
11.
VidyaMKarkiMV. Skin Cancer Detection using Machine Learning Techniques. IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), Bangalore, India.2020; 1-5. doi: 10.1109/CONECCT50063.2020.9198489.
12.
KassemMAHosnyKMFouadMM. Skin Lesions Classification Into Eight Classes for ISIC 2019 Using Deep Convolutional Neural Network and Transfer Learning. IEEE Access.2020; 8: 114822-114832. doi: 10.1109/ACCESS.2020.3003890.
13.
MahbodASchaeferGWangCEckerREllingeI. Skin Lesion Classification Using Hybrid Deep Neural Networks. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.2019; 1229-1233. doi: 10.1109/ICASSP.2019.8683352.
14.
RehmanMUKhanSHRizviSMDAbbasZZafarA. Classification of Skin Lesion by Interference of Segmentation and Convolution Neural Network. 2nd International Conference on Engineering Innovation (ICEI), Bangkok, Thailand. 2018; 81-85. doi: 10.1109/ICEI18.2018.8448814.
15.
LopezARGiro-i-NietoXBurdickJMarquesO. Skin lesion classification from dermoscopic images using deep learning techniques. 13th IASTED International Conference on Biomedical Engineering (BioMed), Innsbruck, Austria. 2017; 49-54. doi: 10.2316/P.2017.852-053.
16.
SimanjuntakTI, et al. Analysis of Detection of Drow and Entire CoOccurrence Matrix GLCM Method on The Classification of Image. J. Phys.: Conf. Ser.2019; 1361: 1-10, 012028. doi: 10.1088/1742-6596/1361/1/012028.
17.
ZhouWFengZXuYFWangXLvH. Empirical Fourier decomposition: An accurate signal decomposition method for nonlinear and non-stationary time series analysis. Mechanical Systems and Signal Processing.2022 Jan 15; 163: 108155. doi: 10.1016/j.ymssp.2021.108155.
18.
ElliottDF. Handbook of digital signal processing: Engineering application. 1988 Jan 11; ISBN-13: 987-0122370755, ISBN-10: 0122370759.
19.
AddisonPS. The Illustrated Wavelet Transform Handbook Introductory Theory and Applications in Science, Engineering, Medicine and Finance, Second Edition. CRC Press, 2020 Jun 30; 1-472; ISBN 9780367574000.
20.
ParmarKSKumarAKalitaU. ECG signal based automated hypertension detection using Fourier decomposition method and cosine modulated filter banks. Biomedical Signal Processing and Control.2022; 76: 103629. doi: 10.1016/j.bspc.2022.103629.
21.
FaustOHagiwaraYHongTJLihOSAcharyaUR. Deep learning for healthcare applications based on physiological signals: A review. Computer Methods and Programs in Biomedicine.2018 Jul; 161: 1-13. doi: 10.1016/j.cmpb.2018.04.005.
22.
GutmanDCodellaNCFCelebiEHelbaBMarchettiMMishraNHalpernA. Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) hosted by the International Skin Imaging Collaboration (ISIC). arXiv:1605.01397. 2016 May 4; 1-5. doi: 10.48550/arXiv.1605.01397.
23.
YuLChenHDouQQinJHengPA. Automated Melanoma Recognition in Dermoscopy Images via Very Deep Residual Networks. IEEE Transactions on Medical Imaging.2017 Apr; 36(4): 994-1004. doi: 10.1109/TMI.2016.2642839.
KaurRGholamHosseiniHSinhaRLindénM. Melanoma Classification Using a Novel Deep Convolutional Neural Network with Dermoscopic Images. Sensors.2022 Feb 2; 22(3): 1134. doi: 10.3390/s22031134.
26.
WuJHuWWenYTuWLiuX. Skin Lesion Classification Using Densely Connected Convolutional Networks with Attention Residual Learning. Sensors (Basel).2020 Dec 10; 20(24): 7080. doi: 10.3390/s20247080.
27.
BoulahiaSYBenatiaMABouzarA.Att2ResNet: A deep attention-based approach for melanoma skin cancer classification. Int. J. Imag. Syst. Technol.2021 Dec 9; 32(2): 476-489. doi: 10.1002/ima.22687.
28.
AliAAAl-MarzouqiH. Melanoma detection using regular convolutional neural networks. Proc. Int. Conf. Electr. Comput. Technol. Appl. (ICECTA).2017 Nov; 1-5. doi: 10.1109/ICECTA.2017.8252041.
