Paper
10 June 2022 The impact of learning rate and data size on CNN for skin cancer detection
Jingwen Pan
Author Affiliations +
Proceedings Volume 12179, Second International Conference on Medical Imaging and Additive Manufacturing (ICMIAM 2022); 1217908 (2022) https://doi.org/10.1117/12.2636723
Event: Second International Conference on Medical Imaging and Additive Manufacturing (ICMIAM 2022), 2022, Xiamen, China
Abstract
Skin cancer is one of the diseases which affect large population in the world. Artificial Intelligence (AI) has been introduced in skin cancer diagnosis in decades. The convolutional neural networks (CNNs) is a deep learning technology used in image classification for skin cancer diagnosis. The study in this article explores show data size and learning rate influence the accuracy of the CNN model. In the study, the best validation accuracy of the CNN model can reach 92.05%. The result shows that the CNN model can effectively diagnose skin cancer with the adjusted learning rate and data size.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Jingwen Pan "The impact of learning rate and data size on CNN for skin cancer detection", Proc. SPIE 12179, Second International Conference on Medical Imaging and Additive Manufacturing (ICMIAM 2022), 1217908 (10 June 2022); https://doi.org/10.1117/12.2636723
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Data modeling

Skin cancer

Image classification

Artificial intelligence

Image processing

Back to Top