Classification of Melanoma Cancer Using Deep Convolutional Neural Networks
Accurate detection of skin diseases is crucial in healthcare, with early diagnosis being particularly vital for effective treatment. Melanoma, a form of skin cancer with a high potential for metastasis, requires early detection to significantly improve treatment success and prevent further spread ac...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Çanakkale Onsekiz Mart University
2024-12-01
|
| Series: | Journal of Advanced Research in Natural and Applied Sciences |
| Subjects: | |
| Online Access: | https://dergipark.org.tr/en/download/article-file/4025852 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832095405686390784 |
|---|---|
| author | Emrah Dönmez Ali Güneş |
| author_facet | Emrah Dönmez Ali Güneş |
| author_sort | Emrah Dönmez |
| collection | DOAJ |
| description | Accurate detection of skin diseases is crucial in healthcare, with early diagnosis being particularly vital for effective treatment. Melanoma, a form of skin cancer with a high potential for metastasis, requires early detection to significantly improve treatment success and prevent further spread across the skin. This study investigates the application of machine learning techniques to diagnose skin lesions, focusing on differentiating between benign moles and malignant melanoma. A Convolutional Neural Network (CNN) model was developed to explore machine learning's efficacy in this context. The initial model featured a primary architecture, progressively refined by adding additional layers and filters to increase its complexity. This iterative enhancement aimed to improve the model’s capability to extract and analyze features from skin images. Each model configuration was meticulously evaluated through a series of experiments to determine its diagnostic performance. The results revealed that the proposed CNN model achieved a high accuracy rate of 91\%. This significant finding demonstrates the effectiveness of machine learning approaches in the early diagnosis and management of melanoma. The study confirms that advanced CNN architectures can enhance diagnostic precision, thereby contributing to improved patient outcomes in detecting and treating skin diseases. |
| format | Article |
| id | doaj-art-a0fd5ec3c9cd4138b30017514eac6228 |
| institution | Kabale University |
| issn | 2757-5195 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Çanakkale Onsekiz Mart University |
| record_format | Article |
| series | Journal of Advanced Research in Natural and Applied Sciences |
| spelling | doaj-art-a0fd5ec3c9cd4138b30017514eac62282025-02-05T18:13:02ZengÇanakkale Onsekiz Mart UniversityJournal of Advanced Research in Natural and Applied Sciences2757-51952024-12-01104996100610.28979/jarnas.1505804453Classification of Melanoma Cancer Using Deep Convolutional Neural NetworksEmrah Dönmez0https://orcid.org/0000-0003-3345-8344Ali Güneş1https://orcid.org/0000-0003-3116-1184BANDIRMA ONYEDİ EYLÜL ÜNİVERSİTESİ, MÜHENDİSLİK VE DOĞA BİLİMLERİ FAKÜLTESİOrzax IncAccurate detection of skin diseases is crucial in healthcare, with early diagnosis being particularly vital for effective treatment. Melanoma, a form of skin cancer with a high potential for metastasis, requires early detection to significantly improve treatment success and prevent further spread across the skin. This study investigates the application of machine learning techniques to diagnose skin lesions, focusing on differentiating between benign moles and malignant melanoma. A Convolutional Neural Network (CNN) model was developed to explore machine learning's efficacy in this context. The initial model featured a primary architecture, progressively refined by adding additional layers and filters to increase its complexity. This iterative enhancement aimed to improve the model’s capability to extract and analyze features from skin images. Each model configuration was meticulously evaluated through a series of experiments to determine its diagnostic performance. The results revealed that the proposed CNN model achieved a high accuracy rate of 91\%. This significant finding demonstrates the effectiveness of machine learning approaches in the early diagnosis and management of melanoma. The study confirms that advanced CNN architectures can enhance diagnostic precision, thereby contributing to improved patient outcomes in detecting and treating skin diseases.https://dergipark.org.tr/en/download/article-file/4025852cnnartificial learningmelanomamole (nevus)skin cancer |
| spellingShingle | Emrah Dönmez Ali Güneş Classification of Melanoma Cancer Using Deep Convolutional Neural Networks Journal of Advanced Research in Natural and Applied Sciences cnn artificial learning melanoma mole (nevus) skin cancer |
| title | Classification of Melanoma Cancer Using Deep Convolutional Neural Networks |
| title_full | Classification of Melanoma Cancer Using Deep Convolutional Neural Networks |
| title_fullStr | Classification of Melanoma Cancer Using Deep Convolutional Neural Networks |
| title_full_unstemmed | Classification of Melanoma Cancer Using Deep Convolutional Neural Networks |
| title_short | Classification of Melanoma Cancer Using Deep Convolutional Neural Networks |
| title_sort | classification of melanoma cancer using deep convolutional neural networks |
| topic | cnn artificial learning melanoma mole (nevus) skin cancer |
| url | https://dergipark.org.tr/en/download/article-file/4025852 |
| work_keys_str_mv | AT emrahdonmez classificationofmelanomacancerusingdeepconvolutionalneuralnetworks AT aligunes classificationofmelanomacancerusingdeepconvolutionalneuralnetworks |