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

Abstract

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.

Keywords: deep features; dermoscopic images; explainable AI; feature selection; skin cancer.

Figure 1

Types of skin cancer such as melanoma or non-melanoma (3).

Figure 2

Sample dermoscopic images: (A) benign skin lesion and (B) malignant skin lesions (29).

Figure 3

Flow diagram of the proposed skin lesion classification using two-stream deep learning architecture.

Figure 4

Training of fine-tuned models using transfer learning for skin lesion classification.

Figure 5

A framework of Xception and Shufflenet deep model for feature extraction of the proposed skin lesion classification.

Figure 6

Sample images of the HAM-10000 datasets (52).

Figure 7

Sample images of the ISIC 2018 dataset (56).

Figure 8

Confusion matrix of recall on Fine KNN using BOA feature selection.

Figure 9

Accuracy comparison of all the intermediate steps on the HAM10000 dataset.

Figure 10

Time-based comparison of all the intermediate steps on the HAM10000 dataset.

Figure 11

Confusion matrix of recall on Cubic SVM.

Figure 12

Accuracy comparison of all the intermediate steps on the ISIC 2018 dataset.

Figure 13

Time-based comparison of all the intermediate steps on the ISIC 2018 dataset.

Figure 14

GradCAM-based visualization shows that the brown color is the most important part.

Figure 15

Proposed framework labeled results. (A) and (C) showing the original images, whereas the (B) and (D) show the proposed predicted labeled image.