Cargando…

A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI

Skin cancer is a serious disease that affects people all over the world. Melanoma is an aggressive form of skin cancer, and early detection can significantly reduce human mortality. In the United States, approximately 97,610 new cases of melanoma will be diagnosed in 2023. However, challenges such a...

Descripción completa

Detalles Bibliográficos
Autores principales: Ahmad, Naveed, Shah, Jamal Hussain, Khan, Muhammad Attique, Baili, Jamel, Ansari, Ghulam Jillani, Tariq, Usman, Kim, Ye Jin, Cha, Jae-Hyuk
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10281646/
https://www.ncbi.nlm.nih.gov/pubmed/37346069
http://dx.doi.org/10.3389/fonc.2023.1151257
_version_ 1785061045380841472
author Ahmad, Naveed
Shah, Jamal Hussain
Khan, Muhammad Attique
Baili, Jamel
Ansari, Ghulam Jillani
Tariq, Usman
Kim, Ye Jin
Cha, Jae-Hyuk
author_facet Ahmad, Naveed
Shah, Jamal Hussain
Khan, Muhammad Attique
Baili, Jamel
Ansari, Ghulam Jillani
Tariq, Usman
Kim, Ye Jin
Cha, Jae-Hyuk
author_sort Ahmad, Naveed
collection PubMed
description Skin cancer is a serious disease that affects people all over the world. Melanoma is an aggressive form of skin cancer, and early detection can significantly reduce human mortality. In the United States, approximately 97,610 new cases of melanoma will be diagnosed in 2023. However, challenges such as lesion irregularities, low-contrast lesions, intraclass color similarity, redundant features, and imbalanced datasets make improved recognition accuracy using computerized techniques extremely difficult. This work presented a new framework for skin lesion recognition using data augmentation, deep learning, and explainable artificial intelligence. In the proposed framework, data augmentation is performed at the initial step to increase the dataset size, and then two pretrained deep learning models are employed. Both models have been fine-tuned and trained using deep transfer learning. Both models (Xception and ShuffleNet) utilize the global average pooling layer for deep feature extraction. The analysis of this step shows that some important information is missing; therefore, we performed the fusion. After the fusion process, the computational time was increased; therefore, we developed an improved Butterfly Optimization Algorithm. Using this algorithm, only the best features are selected and classified using machine learning classifiers. In addition, a GradCAM-based visualization is performed to analyze the important region in the image. Two publicly available datasets—ISIC2018 and HAM10000—have been utilized and obtained improved accuracy of 99.3% and 91.5%, respectively. Comparing the proposed framework accuracy with state-of-the-art methods reveals improved and less computational time.
format Online
Article
Text
id pubmed-10281646
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-102816462023-06-21 A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI Ahmad, Naveed Shah, Jamal Hussain Khan, Muhammad Attique Baili, Jamel Ansari, Ghulam Jillani Tariq, Usman Kim, Ye Jin Cha, Jae-Hyuk Front Oncol Oncology Skin cancer is a serious disease that affects people all over the world. Melanoma is an aggressive form of skin cancer, and early detection can significantly reduce human mortality. In the United States, approximately 97,610 new cases of melanoma will be diagnosed in 2023. However, challenges such as lesion irregularities, low-contrast lesions, intraclass color similarity, redundant features, and imbalanced datasets make improved recognition accuracy using computerized techniques extremely difficult. This work presented a new framework for skin lesion recognition using data augmentation, deep learning, and explainable artificial intelligence. In the proposed framework, data augmentation is performed at the initial step to increase the dataset size, and then two pretrained deep learning models are employed. Both models have been fine-tuned and trained using deep transfer learning. Both models (Xception and ShuffleNet) utilize the global average pooling layer for deep feature extraction. The analysis of this step shows that some important information is missing; therefore, we performed the fusion. After the fusion process, the computational time was increased; therefore, we developed an improved Butterfly Optimization Algorithm. Using this algorithm, only the best features are selected and classified using machine learning classifiers. In addition, a GradCAM-based visualization is performed to analyze the important region in the image. Two publicly available datasets—ISIC2018 and HAM10000—have been utilized and obtained improved accuracy of 99.3% and 91.5%, respectively. Comparing the proposed framework accuracy with state-of-the-art methods reveals improved and less computational time. Frontiers Media S.A. 2023-06-06 /pmc/articles/PMC10281646/ /pubmed/37346069 http://dx.doi.org/10.3389/fonc.2023.1151257 Text en Copyright © 2023 Ahmad, Shah, Khan, Baili, Ansari, Tariq, Kim and Cha https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Oncology
Ahmad, Naveed
Shah, Jamal Hussain
Khan, Muhammad Attique
Baili, Jamel
Ansari, Ghulam Jillani
Tariq, Usman
Kim, Ye Jin
Cha, Jae-Hyuk
A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI
title A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI
title_full A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI
title_fullStr A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI
title_full_unstemmed A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI
title_short A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI
title_sort novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable ai
topic Oncology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10281646/
https://www.ncbi.nlm.nih.gov/pubmed/37346069
http://dx.doi.org/10.3389/fonc.2023.1151257
work_keys_str_mv AT ahmadnaveed anovelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT shahjamalhussain anovelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT khanmuhammadattique anovelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT bailijamel anovelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT ansarighulamjillani anovelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT tariqusman anovelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT kimyejin anovelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT chajaehyuk anovelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT ahmadnaveed novelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT shahjamalhussain novelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT khanmuhammadattique novelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT bailijamel novelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT ansarighulamjillani novelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT tariqusman novelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT kimyejin novelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai
AT chajaehyuk novelframeworkofmulticlassskinlesionrecognitionfromdermoscopicimagesusingdeeplearningandexplainableai