Using Deep Learning to Deploy a Detection Model for Skin Lesion Diagnosis
B. Buvaneswari
, S. Priyanka , P. Priyanka , A. Sabarika shree , P. Padmaja
Skin cancer ,effective treatment ,early detection,application of artificial intelligence (AI),convolutional neural network (CNN) architecture
Skin cancer is the most common type of cancer worldwide, accounting for more than 5 million new cases annually. Skin cancer survival rates and effective treatment depend on early detection. Currently, dermatologists detect skin lesions through subjective and time-consuming eye examination. By providing a precise and dependable diagnosis of skin abnormalities, the application of artificial intelligence (AI) in dermatology has the potential to aid in the early detection of skin cancer.
A deep learning-based automated method for diagnosing skin lesions is the focus of this study. Using a convolutional neural network (CNN) architecture, our method divides skin lesions into benign and malignant groups. In order to train our system, we made use of a sizable collection of photographs of skin lesions that were obtained from public sources. We analyzed the system's performance using a different test dataset, and our accuracy was 95%.
Our system outperformed traditional machine learning models and demonstrated high sensitivity and specificity in detecting malignant skin lesions. We also conducted a comparative analysis with existing state-of-the-art skin lesion diagnosis systems and found that our system achieved comparable or better results.
Our results demonstrate the potential of deep learning-based automated skin lesion diagnosis systems in improving the accuracy and efficiency of skin lesion diagnosis. Our proposed system can assist dermatologists in making accurate and timely diagnoses, leading to improved patient outcomes. Future work can involve the integration of additional clinical data and the expansion of our dataset to include a wider range of skin lesions.
"Using Deep Learning to Deploy a Detection Model for Skin Lesion Diagnosis", TIJER - TIJER - INTERNATIONAL RESEARCH JOURNAL (www.TIJER.org), ISSN:2349-9249, Vol.11, Issue 2, page no.530-533, February-2024, Available :https://tijer.org/TIJER/papers/TIJERB001084.pdf
Volume 11
Issue 2,
February-2024
Pages : 530-533
Paper Reg. ID: TIJER_151052
Published Paper Id: TIJERB001084
Downloads: 000270
Research Area: Science and Technology
Country: Thiruvallur, Chennai, 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
