Deep learning based melanoma diagnosis using dermoscopic images. / Wall, Conor; Young, Fraser; Zhang, Li; Phillips, Emma-Jane; Jiang, Richard ; Yu, Yonghong.

World Scientific Proceedings Series on Computer Engineering and Information Science. In: Developments of Artificial Intelligence Technologies in Computation and Robotics. World Scientific Proceedings Series on Computer Engineering and Information Science, 12. : World Scientific, Singapore, 2020. p. 907-914.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Published
  • Conor Wall
  • Fraser Young
  • Li Zhang
  • Emma-Jane Phillips
  • Richard Jiang
  • Yonghong Yu

Abstract

The most common malignancies in the world are skin cancers, with melanomas being the most lethal. The emergence of Convolutional Neural Networks (CNNs) has provided a highly compelling method for medical diagnosis. This research therefore conducts transfer learning with grid search based hyper-parameter fine-tuning using six state-of-the-art CNN models for the classification of benign nevus and malignant melanomas, with the models then being exported, implemented, and tested on a proof-of-concept Android application. Evaluated using Dermofit Image Library and PH2 skin lesion data sets, the empirical results indicate that the ResNeXt50 model achieves the highest accuracy rate with fast execution time, and a relatively small model size. It compares favourably with other related methods for melanoma diagnosis reported in the literature.
Original languageEnglish
Title of host publicationWorld Scientific Proceedings Series on Computer Engineering and Information Science
Place of PublicationIn: Developments of Artificial Intelligence Technologies in Computation and Robotics. World Scientific Proceedings Series on Computer Engineering and Information Science, 12.
PublisherWorld Scientific, Singapore
Pages907-914
Number of pages8
DOIs
Publication statusPublished - 15 Aug 2020
This open access research output is licenced under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 Unported License.

ID: 43383652