Hybrid Feature Fusion and Machine Learning Approaches for Melanoma Skin Cancer Detection

Abstract

Skin cancer is an exquisite disease globally nowadays. Because of the poor contrast and apparent resemblance between skin and lesions, automatic identification of skin cancer is complicated. The rate of human death can be massively reduced if melanoma skin cancer can be detected quickly using dermoscopy images. In this research, an anisotropic diffusion filtering method is used on dermoscopy images to remove multiplicative speckle noise and the fast-bounding box (FBB) method is applied to segment the skin cancer region. Furthermore, the paper consists of two feature extractor parts. One of the two features extractor parts is the hybrid feature extractor (HFE) part and another is the convolutional neural network VGG19 based CNN feature extractor part. The HFE portion combines three feature extraction approaches into a single fused feature vector: Histogram-Oriented Gradient (HOG), Local Binary Pattern (LBP), and Speed Up Robust Feature (SURF). The CNN method also is used to extract additional features from test and training datasets. This two-feature vector is fused to design the classification model. This classifier performs the classification of dermoscopy images whether it is melanoma or non-melanoma skin cancer. The proposed methodology is performed on two ordinary datasets and achieved the accuracy 99.85%, sensitivity 91.65%, and specificity 95.70%, which makes it more successful than previous machine learning algorithms.

A novel artificial intelligence-based predictive analytics technique to detect skin cancer

“…The designed AGEbRF technique is implemented using a Python program, and several metrics like accuracy, sensitivity, specificity, F1-measure, and precision are measured. Additionally, the developed approach is verified using established techniques such as hybrid feature fusion and ML (HFF) ( Rahman et al, 2022 ), skin cancer classification (SCC) ( Mijwil, 2021 ), modified thermal exchange (MTE) ( Wei et al, 2021 ), and diagnosis of skin cancer by ML (DSC) ( Murugan et al, 2021 ), region extraction and classification of skin cancer (RCSC) ( Saba et al, 2019 ) and the ensemble lightweight technique (ELT) ( Wei, Ding & Hu, 2020 ).…”

“…The suggested AGEbRF model’s F1-score is determined and validated using widely used techniques such as hybrid feature fusion and ML (HFF) ( Rahman et al, 2022 ), SCC ( Mijwil, 2021 ), MTE ( Wei et al, 2021 ), and DSC ( Murugan et al, 2021 ), and RCSC ( Saba et al, 2019 ) approaches. The results are listed in the Table 6 .…”

“…The memory and control mechanism in the contemporary ML allows it to carry out the procedure better ( Botvinick et al, 2019 ). To segment the damaged section and control the degree of disease by early-stage prediction, filtering technique ( Rahman et al, 2022 ), automatic and optimal pipeline approach ( Wei et al, 2021 ), etc . The suggested approach is capable of identifying and classifying the area affected by skin cancer.…”

“…It is more difficult to detect similarities and weak contrast between lesions and skin. Rahman et al (2022) suggested a method for filtering the dataset’s noise using dermoscopic images like anisotropic diffusion. Additionally, the affected region of the skin cancer is segmented using the quick bounding box technique.…”

Detection of Skin Cancer Based on Skin Lesion Images Using Deep Learning

“…Data Set Techniques Used Number of Classes [25] 300 HAM10000 CNN with XGBoost Five [26] 1323 HAM10000 InSiNet Two [27] [33] 7470 HAM10000 ResNet50 Seven [34] 3753 ImageNet ECOC SVM Two [35] 16,170 HAM10000 Anisotropic diffusion filtering Two [36] 1000 ISIC SVM + RF Eight [37] 6705 HAM10000 DCNN Two [38] 279 ImageNet DCNN VGG-16 Two [39] 10,015 HAM10000 AlexNet Seven [40] 10,015 HAM10000 CNN Seven Timely screening and prediction have been found to enhance the probability of proper medication and reduce mortality. However, most of these studies focused solely on applying DL models to actual images rather than preprocessed images, limiting the ultimate classification network's ability to adapt.…”