Advanced Biomedical Engineering
Online ISSN : 2187-5219
ISSN-L : 2187-5219
Hyperparameter Optimization for Deep Learning-based Automatic Melanoma Diagnosis System
Takashi Nagaoka
Author information
JOURNAL OPEN ACCESS

2020 Volume 9 Pages 225-232

Details
Abstract

Deep learning is widely used in the development of automatic diagnosis systems for melanoma. However, there are some parameters called hyperparameters which should be set arbitrarily. Optimum setting of hyperparameters is challenging. The dermoscopic images on the database are trained on GoogLeNet. The hyperparameters verified in this study were random seed, solver type, base learning rate, epoch, and batch size. By using a genetic algorithm, these hyperparameters were optimized to obtain higher validation accuracy than other methods such as brute force or Bayesian optimization. The highest validation accuracy was 89.75%. The best hyperparameter settings were: 2 for random seed, RMSProp for solver type, 0.0001 for base learning rate, 30 for epoch, 32 for batch size, and 368 seconds for training time. Using the genetic algorithm, we successfully set the hyperparameters for efficient deep learning. Using the system developed in this study, we plan to search for a broader range of hyperparameters and identify multiple groups including lesions other than melanoma.

Content from these authors
© 2020 Japanese Society for Medical and Biological Engineering

Copyright: ©2020 The Author(s). This is an open access article distributed under the terms of the Creative Commons BY 4.0 International (Attribution) License (https://creativecommons.org/licenses/by/4.0/legalcode), which permits the unrestricted distribution, reproduction and use of the article provided the original source and authors are credited.
https://creativecommons.org/licenses/by/4.0/legalcode
Previous article Next article
feedback
Top