Classification of Skin Lesion With Features Extraction Using Quantum Chebyshev Polynomials and Autoencoder From Wavelet-Transformed Images

Skin, a vital organ acting as a protective barrier to the external environment, plays a pivotal role in overall human health. Early detection of skin diseases is essential, as untreated conditions can escalate to serious issues such as skin cancer. This study presents an innovative automated system...

Full description

Saved in:
Bibliographic Details
Main Authors: Farhatullah, Xin Chen, Deze Zeng, Jiafeng Xu, Rab Nawaz, Rahmat Ullah
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10757392/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846107088315482112
author Farhatullah
Xin Chen
Deze Zeng
Jiafeng Xu
Rab Nawaz
Rahmat Ullah
author_facet Farhatullah
Xin Chen
Deze Zeng
Jiafeng Xu
Rab Nawaz
Rahmat Ullah
author_sort Farhatullah
collection DOAJ
description Skin, a vital organ acting as a protective barrier to the external environment, plays a pivotal role in overall human health. Early detection of skin diseases is essential, as untreated conditions can escalate to serious issues such as skin cancer. This study presents an innovative automated system designed for efficient classification of skin lesions, addressing the growing demand for advanced biomedical image analysis. Leveraging the power of Deep Learning, the proposed model incorporates several pre-processing techniques such as wavelet transformations, pooling methods, and normalization to enhance image clarity and remove extraneous artifacts. Two distinct feature extractors are used to extract key features: Quantum Chebyshev polynomials for initial feature extraction, followed by an Autoencoder (AE) for feature refinement and dimensionality reduction. These optimized features are classified using Long Short-Term Memory (LSTM). The experimental evaluation of the proposed model includes analysis with five different optimizers: Adam, RMSprop, SGD, Adadelta, and Adagrad, accross two widely recognized datasets, ISIC2017 and HAM10000. The resutlts reveals that the Adam optimizer consistently yields the highest scores across multiple evaluation matrices. For the ISIC2017 dataset, the model achieves 98.87% accuracy, 98.23% precision, 98.26% recall, F1-score 98.24%, and 98.16% specificity. The HAM10000 dataset exhibits even more remarkable metrics, with 99.58% accuracy, 97.84% precision, 97.49% recall, 97.66% F1-score, and 97.74% specificity. The proposed model surpasses the current state-of-the-art in skin lesion classification and holds the potential to serve as a valuable tool for medical professionals, aiding in the automated classification of skin cancer.
format Article
id doaj-art-bcbf77172de7484cbf3572f6c6f642f1
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-bcbf77172de7484cbf3572f6c6f642f12024-12-27T00:00:59ZengIEEEIEEE Access2169-35362024-01-011219392319393610.1109/ACCESS.2024.350251310757392Classification of Skin Lesion With Features Extraction Using Quantum Chebyshev Polynomials and Autoencoder From Wavelet-Transformed Images Farhatullah0Xin Chen1https://orcid.org/0000-0001-9924-6833Deze Zeng2Jiafeng Xu3https://orcid.org/0000-0001-8075-8556Rab Nawaz4https://orcid.org/0000-0002-7622-9632Rahmat Ullah5https://orcid.org/0000-0001-5162-5164School of Computer Science, China University of Geosciences, Wuhan, ChinaSchool of Automation, China University of Geosciences, Wuhan, ChinaSchool of Computer Science, China University of Geosciences, Wuhan, ChinaSchool of Automation, China University of Geosciences, Wuhan, ChinaSchool of Computer Science and Electronic Engineering, University of Essex, Colchester, U.K.School of Computer Science, China University of Geosciences, Wuhan, ChinaSkin, a vital organ acting as a protective barrier to the external environment, plays a pivotal role in overall human health. Early detection of skin diseases is essential, as untreated conditions can escalate to serious issues such as skin cancer. This study presents an innovative automated system designed for efficient classification of skin lesions, addressing the growing demand for advanced biomedical image analysis. Leveraging the power of Deep Learning, the proposed model incorporates several pre-processing techniques such as wavelet transformations, pooling methods, and normalization to enhance image clarity and remove extraneous artifacts. Two distinct feature extractors are used to extract key features: Quantum Chebyshev polynomials for initial feature extraction, followed by an Autoencoder (AE) for feature refinement and dimensionality reduction. These optimized features are classified using Long Short-Term Memory (LSTM). The experimental evaluation of the proposed model includes analysis with five different optimizers: Adam, RMSprop, SGD, Adadelta, and Adagrad, accross two widely recognized datasets, ISIC2017 and HAM10000. The resutlts reveals that the Adam optimizer consistently yields the highest scores across multiple evaluation matrices. For the ISIC2017 dataset, the model achieves 98.87% accuracy, 98.23% precision, 98.26% recall, F1-score 98.24%, and 98.16% specificity. The HAM10000 dataset exhibits even more remarkable metrics, with 99.58% accuracy, 97.84% precision, 97.49% recall, 97.66% F1-score, and 97.74% specificity. The proposed model surpasses the current state-of-the-art in skin lesion classification and holds the potential to serve as a valuable tool for medical professionals, aiding in the automated classification of skin cancer.https://ieeexplore.ieee.org/document/10757392/Skin lesion classificationdeep learningmedical diagnosisbiomedical image analysiswavelet transformationsquantum Chebyshev polynomials
spellingShingle Farhatullah
Xin Chen
Deze Zeng
Jiafeng Xu
Rab Nawaz
Rahmat Ullah
Classification of Skin Lesion With Features Extraction Using Quantum Chebyshev Polynomials and Autoencoder From Wavelet-Transformed Images
IEEE Access
Skin lesion classification
deep learning
medical diagnosis
biomedical image analysis
wavelet transformations
quantum Chebyshev polynomials
title Classification of Skin Lesion With Features Extraction Using Quantum Chebyshev Polynomials and Autoencoder From Wavelet-Transformed Images
title_full Classification of Skin Lesion With Features Extraction Using Quantum Chebyshev Polynomials and Autoencoder From Wavelet-Transformed Images
title_fullStr Classification of Skin Lesion With Features Extraction Using Quantum Chebyshev Polynomials and Autoencoder From Wavelet-Transformed Images
title_full_unstemmed Classification of Skin Lesion With Features Extraction Using Quantum Chebyshev Polynomials and Autoencoder From Wavelet-Transformed Images
title_short Classification of Skin Lesion With Features Extraction Using Quantum Chebyshev Polynomials and Autoencoder From Wavelet-Transformed Images
title_sort classification of skin lesion with features extraction using quantum chebyshev polynomials and autoencoder from wavelet transformed images
topic Skin lesion classification
deep learning
medical diagnosis
biomedical image analysis
wavelet transformations
quantum Chebyshev polynomials
url https://ieeexplore.ieee.org/document/10757392/
work_keys_str_mv AT farhatullah classificationofskinlesionwithfeaturesextractionusingquantumchebyshevpolynomialsandautoencoderfromwavelettransformedimages
AT xinchen classificationofskinlesionwithfeaturesextractionusingquantumchebyshevpolynomialsandautoencoderfromwavelettransformedimages
AT dezezeng classificationofskinlesionwithfeaturesextractionusingquantumchebyshevpolynomialsandautoencoderfromwavelettransformedimages
AT jiafengxu classificationofskinlesionwithfeaturesextractionusingquantumchebyshevpolynomialsandautoencoderfromwavelettransformedimages
AT rabnawaz classificationofskinlesionwithfeaturesextractionusingquantumchebyshevpolynomialsandautoencoderfromwavelettransformedimages
AT rahmatullah classificationofskinlesionwithfeaturesextractionusingquantumchebyshevpolynomialsandautoencoderfromwavelettransformedimages