Skin Lesion Segmentation Detection Using U-Net Architecture
skin tumours; CNN; U-net architecture
Skin tumours account for the bulk of malignancies worldwide. The two main categories of skin cancer are melanoma and nonmelanoma. Examples of nonmelanoma skin cancer include basal cell carcinoma and squamous cell carcinoma. The two biggest risk factors are having fair skin and frequently being exposed to UVB rays. The initial and most crucial step in computer-based skin cancer diagnosis is segmentation because other activities heavily rely on correctly segmented lesions. In the segmentation of skin cancer disorders, deep learning with convolutional neural networks (CNNs) was reported as a unique technique that offers effective disease segmentation. The suggested approach makes use of a CNN that has been trained using a publicly available dataset of photos representing a skin cancer condition together with the corresponding mask images. In order to diagnose diseases, it was shown that neural networks can record the colours and textures of lesions particular to those diseases, which is similar to human decision-making.
"Skin Lesion Segmentation Detection Using U-Net Architecture", TIJER - TIJER - INTERNATIONAL RESEARCH JOURNAL (www.TIJER.org), ISSN:2349-9249, Vol.11, Issue 2, page no.398-402, February-2024, Available :https://tijer.org/TIJER/papers/TIJERB001062.pdf
Volume 11
Issue 2,
February-2024
Pages : 398-402
Paper Reg. ID: TIJER_151058
Published Paper Id: TIJERB001062
Downloads: 000291
Research Area: Science and Technology
Country: Thiruvallur, TamilNadu, India
ISSN: 2349-9249 | IMPACT FACTOR: 8.57 Calculated By Google Scholar | ESTD YEAR: 2014
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.57 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: TIJER (IJ Publication) Janvi Wave
