Szczegóły publikacji
Opis bibliograficzny
Detection and classification of pigment network in dermoscopic color images as one of the 7-point checklist criteria / Joanna JAWOREK-KORJAKOWSKA, Paweł KŁECZEK, Ryszard TADEUSIEWICZ // W: Recent developments and achievements in biocybernetics and biomedical engineering : proceedings of the 20th Polish Conference on Biocybernetics and Biomedical Engineering, Kraków, Poland, September 20-22, 2017 / eds. Piotr Augustyniak, Roman Maniewski, Ryszard Tadeusiewicz. — [Cham] : Springer International Publishing, cop. 2018. — (Advances in Intelligent Systems and Computing ; ISSN 2194-5357 ; vol. 647). — ISBN: 978-3-319-66904-5; e-ISBN: 978-3-319-66905-2. — S. 174–181. — Bibliogr. s. 181, Abstr.
Autorzy (3)
Dane bibliometryczne
| ID BaDAP | 109389 |
|---|---|
| Data dodania do BaDAP | 2017-10-24 |
| DOI | 10.1007/978-3-319-66905-2_15 |
| Rok publikacji | 2018 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | 20th Polish Conference on Biocybernetics and Biomedical Engineering |
| Czasopismo/seria | Advances in Intelligent Systems and Computing |
Abstract
Malignant melanoma, which is a dangerous proliferation of melanocytes, is commonly diagnosed in all people, regardless of age, gender, or race. In the last several years an increasing melanoma incidence and mortality rate has been observed worldwide and it is rising faster than other forms of cancer. In this paper we present a new approach to the detection and classification of pigment network, one of the major feature in a widely used diagnostic algorithm 7-point checklist. Accurate assessment of pigment network is clinically important due to a significantly different occurrence in benign and malignant skin lesions. We describe a complex algorithm containing following steps: image enhancement, lesion segmentation, pigment network detection as well as classification. The algorithm has been tested on 300 dermoscopic images and achieved 91% sensitivity and classification accuracy of 85%. Compared to state-of-the-art, we obtain improved classification accuracy. © 2018, Springer International Publishing AG.
