Szczegóły publikacji
Opis bibliograficzny
Feature selection for automatic CT-based prostate segmentation / Artur KOS, Andrzej SKALSKI, Tomasz P. ZIELIŃSKI, Diana Gomes, Vítor Sá, Piotr Kedzierawski, Tomasz Kuszewski // W: IST 2016 : 2016 IEEE international conference on Imaging Systems & Techniques : October 4–6, 2016, Chania, Crete Island, Greece : proceedings / IEEE. — Piscataway, NJ, USA : IEEE, cop. 2016. — ISBN: 978-1-5090-1817-8. — S. 243–248. — Bibliogr. s. 248, Abstr.
Autorzy (7)
- AGHKos Artur
- AGHSkalski Andrzej
- AGHZieliński Tomasz
- Gomes Diana
- Sá Vítor
- Kedzierawski Piotr
- Kuszewski Tomasz
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 101823 |
|---|---|
| Data dodania do BaDAP | 2016-12-16 |
| Tekst źródłowy | URL |
| DOI | 10.1109/IST.2016.7738231 |
| Rok publikacji | 2016 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Konferencja | 2016 IEEE international conference on Imaging Systems & Techniques |
Abstract
The paper addresses a problem of feature selection for automatic prostate segmentation in Computed Tomography (CT) planning data for radiotherapy process. The following image descriptors have been tested in 2D and 3D scenarios: standard Hounsfield Unit (HU) profiles, histogram of oriented gradient (HoG), Haar wavelets, and Modality Independent Neighborhood Descriptor (MIND). The task was to distinguish a prostate interior and exterior. 22 CT volumes with different spatial resolution and different organ outlines have been used. The k-Nearest Neighbors (kNN) classifier was applied and the following recognition measures were evaluated, with 10-fold cross-validation: accuracy, precision, sensitivity and specificity. © 2016 IEEE.
