Open Access Te Herenga Waka-Victoria University of Wellington
Browse

Genetic Programming for Multiple Feature Construction in Skin Cancer Image Classification

Download (763.09 kB)
conference contribution
posted on 2022-07-10, 23:07 authored by Qurrat Ul Ain, Bing XueBing Xue, Harith Al-Sahaf, Mengjie ZhangMengjie Zhang
Skin cancer is a common cancer worldwide, with melanoma being the most deadly form which is treatable when diagnosed at an early stage. This study develops a novel classification approach using multi-tree genetic programming (GP), which not only targets melanoma detection but is also capable of distinguishing between ten different classes of skin cancer effectively from lesion images. Selecting a suitable feature extraction method and the way different types of features are combined are important aspects to achieve performance gains. Existing approaches remain unable to effectively design a way to combine various features. Moreover, they have not used multi-channel multi-resolution spatial/frequency information for effective feature construction. In this work, wavelet-based texture features from multiple color channels are employed which preserve all the local, global, color and texture information concurrently. Local Binary Pattern, lesion color variation, and geometrical border shape features are also extracted from various color channels. The performance of the proposed method is evaluated using two skin image datasets and compared with an existing multi-tree GP method, ten single-tree GP methods, and six commonly used classification algorithms. The results reveal the goodness of the proposed method which significantly outperformed all these classification methods and demonstrate the potential to help dermatologist in making a diagnosis in real-time situations.

History

Preferred citation

Ain, Q. U., Xue, B., Al-Sahaf, H. & Zhang, M. (2019, January). Genetic Programming for Multiple Feature Construction in Skin Cancer Image Classification. In Proceedings of the 34th International Conference on Image and Vision Computing New Zealand (IVCNZ 2019) 2019 International Conference on Image and Vision Computing New Zealand (IVCNZ) (2019-December pp. 1-6). IEEE. https://doi.org/10.1109/IVCNZ48456.2019.8961001

Conference name

2019 International Conference on Image and Vision Computing New Zealand (IVCNZ)

Conference start date

2019-12-02

Conference finish date

2019-12-04

Title of proceedings

Proceedings of the 34th International Conference on Image and Vision Computing New Zealand (IVCNZ 2019)

Volume

2019-December

Publication or Presentation Year

2019-01-01

Pagination

1-6

Publisher

IEEE

Publication status

Published

ISSN

2151-2191

eISSN

2151-2205

Usage metrics

    Conference papers

    Categories

    No categories selected

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC