NORMA eResearch @NCI Library

Identification and Detection of Skin Cancer Using Deep Learning

Sane, Rahul Manikrao (2022) Identification and Detection of Skin Cancer Using Deep Learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (5MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Among all types of cancer, skin cancer is the most serious and common.due to its complicated signs, skin cancer detection has been a cancer can be diagnosed sooner by studying abnormal skin changes.Since skin cancer cases are on the rise, it has a high mortality rate, and expensive healthcare treatments, it is essential to identify its abnormalities as soon as possible.different Deep Learning Neural Networks have found skin cancer.malignant and benign tumor images have comparable optics, making it challenging to achieve precise results.this technical report helps diagnose skin cancer automatically by classifying melanoma and benign images using deep learning models, minimizing lesion images are augmented and preprocessed to enhance the model’s accuracy, and then the model’s accuracy and loss are evaluated.this research uses the ResNet 50 neural network model, which outperforms past research article models with 98 % accuracy.

Item Type: Thesis (Masters)
Mulwa, Catherine
Uncontrolled Keywords: Skin Cancer; Skin lession Images; ResNet50; Loss Function; Data Augmentation; Convolution Neural Network; Optimization
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
R Medicine > RC Internal medicine > RC0254 Neoplasms. Tumors. Oncology (including Cancer)
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 25 May 2023 15:42
Last Modified: 25 May 2023 15:42

Actions (login required)

View Item View Item