TY - JOUR
T1 - A novel framework of multiclass skin lesion recognition from dermoscopic images using deep learning and explainable AI
AU - Ahmad, Naveed
AU - Shah, Jamal Hussain
AU - Khan, Muhammad Attique
AU - Baili, Jamel
AU - Ansari, Ghulam Jillani
AU - Tariq, Usman
AU - Kim, Ye Jin
AU - Cha, Jae Hyuk
N1 - Publisher Copyright:
Copyright © 2023 Ahmad, Shah, Khan, Baili, Ansari, Tariq, Kim and Cha.
PY - 2023
Y1 - 2023
N2 - 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.
AB - 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.
KW - deep features
KW - dermoscopic images
KW - explainable AI
KW - feature selection
KW - skin cancer
UR - http://www.scopus.com/inward/record.url?scp=85162215480&partnerID=8YFLogxK
U2 - 10.3389/fonc.2023.1151257
DO - 10.3389/fonc.2023.1151257
M3 - Article
AN - SCOPUS:85162215480
SN - 2234-943X
VL - 13
JO - Frontiers in Oncology
JF - Frontiers in Oncology
M1 - 1151257
ER -