<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>Malignant melanoma is considered to be one of the deadliest types of skin cancer, and it is responsible for the death of a large number of people worldwide. However, distinguishing whether melanoma is benign or malignant has been a challenging task. Many Computer Aided Diagnosis and Detection Systems have been developed in the past for this task. This paper presents a deep learning framework based approach for melanoma diagnosis and recognition. In the proposed method, the original skin mirror image is first preprocessed and then passed to the VGG16 convolutional neural network for tumor property classification. VGG16 uses smaller convolutional kernels instead of a larger convolutional kernel to achieve a reduction in network parameters and thus improve network performance. The system is trained using segmented RGB images generated from ground truth images of the ISIC2016 dataset, and finally a softmax classifier is used for pixel-level classification of melanoma lesions. In this study, a new method to become a lesion classifier was designed to classify melanoma lesion regions into benign and malignant tumors based on the results of pixel-level classification, and experiments were conducted on two well-established public test datasets, ISIC2016 and ISIC2017, with a final accuracy of 96.1%. The results indicate that convolutional neural networks are suitable for melanoma diagnosis identification. This study is of great relevance for advanced cancer caused by malignant melanoma.</p>
</abstract>

Malignant melanoma is considered to be one of the deadliest types of skin cancer, and it is responsible for the death of a large number of people worldwide. However, distinguishing whether melanoma is benign or malignant has been a challenging task. Many Computer Aided Diagnosis and Detection Systems have been developed in the past for this task. This paper presents a deep learning framework based approach for melanoma diagnosis and recognition. In the proposed method, the original skin mirror image is first preprocessed and then passed to the VGG16 convolutional neural network for tumor property classification. VGG16 uses smaller convolutional kernels instead of a larger convolutional kernel to achieve a reduction in network parameters and thus improve network performance. The system is trained using segmented RGB images generated from ground truth images of the ISIC2016 dataset, and finally a softmax classifier is used for pixel-level classification of melanoma lesions. In this study, a new method to become a lesion classifier was designed to classify melanoma lesion regions into benign and malignant tumors based on the results of pixel-level classification, and experiments were conducted on two well-established public test datasets, ISIC2016 and ISIC2017, with a final accuracy of 96.1%. The results indicate that convolutional neural networks are suitable for melanoma diagnosis identification. This study is of great relevance for advanced cancer caused by malignant melanoma.

Deep Learning Based Melanoma Diagnosis Identification

School of Computer Science and Engineering

International Journal of Advanced Network, Monitoring and Controls

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

{"article-title":"Deep Learning Based Melanoma Diagnosis Identification"}

Malignant melanoma is considered to be one of the deadliest types of skin cancer, and it is responsible for the death of a large number of people worldwide....

Assuming: feature_map = 28*28	Convolution step = 1	Padding = 0
1-Layer 5×5 convolutional kernel	2-Layer 3×3 convolutional kernel
Layer1: (28-5) / 1 + 1 = 24	Layer1:(28-3) / 1 + 1 = 26
Output: Feature map = 24×24	Layer2:(26-3) / 1 + 1 = 24
Output: Feature map = 24×24	Output:Feature map = 24×24

Confusion Matrix		Predict
Confusion Matrix		0	1
Real	0	a	b
Real	1	c	d

Deep Learning Based Melanoma Diagnosis Identification

Published Online: Aug 16, 2023

Page range: 20 - 26

DOI: https://doi.org/10.2478/ijanmc-2023-0053

Keywords
Melanoma, Convolutional Neural Network, Convolutional Neural Network, Lesion Area, Pixel-Level Classification

© 2023 Gaole Duan et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Figure 10.

Feasibility of 33 Convolution Kernels Replace 55 Convolution Kernels

Confusion matrix under binary classification

Deep Learning Based Melanoma Diagnosis Identification

Published Online: Aug 16, 2023

Page range: 20 - 26

DOI: https://doi.org/10.2478/ijanmc-2023-0053

KeywordsMelanoma, Convolutional Neural Network, Convolutional Neural Network, Lesion Area, Pixel-Level Classification

© 2023 Gaole Duan et al., published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Figure 2.

Figure 3.

Figure 4.

Figure 5.

Figure 6.

Figure 7.

Figure 8.

Figure 9.

Figure 10.

Feasibility of 3*3 Convolution Kernels Replace 5*5 Convolution Kernels

Confusion matrix under binary classification

Keywords
Melanoma, Convolutional Neural Network, Convolutional Neural Network, Lesion Area, Pixel-Level Classification

Feasibility of 33 Convolution Kernels Replace 55 Convolution Kernels