NORMA eResearch @NCI Library

Skin Cancer Classification Using Convolution Neural Network and Meta Learning

Tevaramani, Siddharud (2023) Skin Cancer Classification Using Convolution Neural Network and Meta Learning. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (2MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Skin cancer is a potentially fatal disease that can affect the entire body. There are seven types of skin cancer, including the potentially deadly melanoma. Early detection of skin cancer is crucial because delays in diagnosis can result in more serious health consequences. In the past, researchers have used machine learning algorithms to detect different types of skin cancer based on skin lesions. One such experiment involved the use of a convolutional neural network and a meta-learning technique. Highly imbalanced data is balanced by image augmentation, optimized using adam optimizerand Model has been trained using highest number of epochs by using early stopping and model checkpoint. Meta-learning is an evolving field that has shown promising output in terms of few-shot training specially when data availability is very low. In this study, multi-layer perceptron and random forest trained with a meta-learner showed an accuracy of 80%, outperforming other models that were tested.

Item Type: Thesis (Masters)
Cosgrave, Noel
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: 27 May 2023 11:03
Last Modified: 27 May 2023 11:03

Actions (login required)

View Item View Item