Automating skin cancer screening: a deep learning
Abstract Skin cancer presents in various forms, including squamous cell carcinoma (SCC), basal cell carcinoma (BCC), and melanoma. Established risk factors include ultraviolet (UV) radiation exposure from solar or artificial sources, lighter skin pigmentation, a history of sunburns, and a family his...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2025-01-01
|
| Series: | Journal of Engineering and Applied Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s44147-024-00573-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594704881942528 |
|---|---|
| author | Nada M. Rashad Noha MM. Abdelnapi Ahmed F. Seddik M. A. Sayedelahl |
| author_facet | Nada M. Rashad Noha MM. Abdelnapi Ahmed F. Seddik M. A. Sayedelahl |
| author_sort | Nada M. Rashad |
| collection | DOAJ |
| description | Abstract Skin cancer presents in various forms, including squamous cell carcinoma (SCC), basal cell carcinoma (BCC), and melanoma. Established risk factors include ultraviolet (UV) radiation exposure from solar or artificial sources, lighter skin pigmentation, a history of sunburns, and a family history of the disease. Early detection and prompt intervention are crucial for achieving a favorable prognosis. Traditionally, treatment modalities include surgery, radiation therapy, and chemotherapy. Recent advancements in immunotherapy have revolutionized skin cancer diagnosis, but manual identification remains time-consuming. Artificial intelligence (AI) has shown potential in skin cancer classification, leading to automated screening methods. To support dermatologists, we improved the model for classifying images. This model is able to recognize seven different kinds of skin lesions. On the ISIC dataset, an analysis has been done. This study offers a novel approach to early skin cancer diagnosis based on image processing. Our approach leverages the high accuracy of a specific convolutional neural network architecture, utilizing transfer learning with pre-trained data to further enhance detection performance. Our findings demonstrate that the employed ResNet-50 transfer learning model achieves a remarkable accuracy of 97%, while ResNet50 without augmentation gives an accuracy of 81.57% and an F1-score of 75.75%. |
| format | Article |
| id | doaj-art-8c12139badda4c428ac4c003a002ef64 |
| institution | Kabale University |
| issn | 1110-1903 2536-9512 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Engineering and Applied Science |
| spelling | doaj-art-8c12139badda4c428ac4c003a002ef642025-01-19T12:25:20ZengSpringerOpenJournal of Engineering and Applied Science1110-19032536-95122025-01-0172111810.1186/s44147-024-00573-wAutomating skin cancer screening: a deep learningNada M. Rashad0Noha MM. Abdelnapi1Ahmed F. Seddik2M. A. Sayedelahl3Department of Computer Science, Faculty of Computers and Information, Suez UniversityDepartment of Computer Science, Faculty of Computers and Information, Suez UniversityBiomedical Engineering Department, Faculty of Engineering, Helwan UniversityDepartment of Computer Science, Faculty of Computers and Information, Damanhour UniversityAbstract Skin cancer presents in various forms, including squamous cell carcinoma (SCC), basal cell carcinoma (BCC), and melanoma. Established risk factors include ultraviolet (UV) radiation exposure from solar or artificial sources, lighter skin pigmentation, a history of sunburns, and a family history of the disease. Early detection and prompt intervention are crucial for achieving a favorable prognosis. Traditionally, treatment modalities include surgery, radiation therapy, and chemotherapy. Recent advancements in immunotherapy have revolutionized skin cancer diagnosis, but manual identification remains time-consuming. Artificial intelligence (AI) has shown potential in skin cancer classification, leading to automated screening methods. To support dermatologists, we improved the model for classifying images. This model is able to recognize seven different kinds of skin lesions. On the ISIC dataset, an analysis has been done. This study offers a novel approach to early skin cancer diagnosis based on image processing. Our approach leverages the high accuracy of a specific convolutional neural network architecture, utilizing transfer learning with pre-trained data to further enhance detection performance. Our findings demonstrate that the employed ResNet-50 transfer learning model achieves a remarkable accuracy of 97%, while ResNet50 without augmentation gives an accuracy of 81.57% and an F1-score of 75.75%.https://doi.org/10.1186/s44147-024-00573-wSkin cancerEarly detectionArtificial intelligenceSkin cancer classificationAutomated screening methodsConvolutional neural networks |
| spellingShingle | Nada M. Rashad Noha MM. Abdelnapi Ahmed F. Seddik M. A. Sayedelahl Automating skin cancer screening: a deep learning Journal of Engineering and Applied Science Skin cancer Early detection Artificial intelligence Skin cancer classification Automated screening methods Convolutional neural networks |
| title | Automating skin cancer screening: a deep learning |
| title_full | Automating skin cancer screening: a deep learning |
| title_fullStr | Automating skin cancer screening: a deep learning |
| title_full_unstemmed | Automating skin cancer screening: a deep learning |
| title_short | Automating skin cancer screening: a deep learning |
| title_sort | automating skin cancer screening a deep learning |
| topic | Skin cancer Early detection Artificial intelligence Skin cancer classification Automated screening methods Convolutional neural networks |
| url | https://doi.org/10.1186/s44147-024-00573-w |
| work_keys_str_mv | AT nadamrashad automatingskincancerscreeningadeeplearning AT nohammabdelnapi automatingskincancerscreeningadeeplearning AT ahmedfseddik automatingskincancerscreeningadeeplearning AT masayedelahl automatingskincancerscreeningadeeplearning |