Szczegóły publikacji
Opis bibliograficzny
Measuring the angle of hallux valgus using segmentation of bones on X-ray images / Konrad Kwolek, Henryk Liszka, Bogdan KWOLEK, Artur Gądek // W: Artificial neural networks and machine learning - ICANN 2019 : workshop and special sessions : 28th International Conference on Artificial Neural Networks : Munich, Germany, September 17–19, 2019 : proceedings / eds. Igor V. Tetko, [et al.]. — Cham : Springer Nature Switzerland, cop. 2019. — ( Lecture Notes in Computer Science ; ISSN 0302-9743 ; 11731 ). — ISBN: 978-3-030-30492-8; e-ISBN: 978-3-030-30493-5. — S. 313–325. — Bibliogr. s. 323–325, Abstr. — Publikacja dostępna online od: 2019-09-09
Autorzy (4)
- Kwolek Konrad
- Liszka Henryk
- AGHKwolek Bogdan
- Gądek Artur
Dane bibliometryczne
| ID BaDAP | 124586 |
|---|---|
| Data dodania do BaDAP | 2020-12-28 |
| Tekst źródłowy | URL |
| DOI | 10.1007/978-3-030-30493-5_32 |
| Rok publikacji | 2019 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | International Conference on Artificial Neural Networks 2019 |
| Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
Hallux valgus is a common feet problem. A hallux valgus deformity is when there is medial deviation of the first metatarsal and lateral deviation of the great toe. In this work, we introduce an algorithm for automatic recognition of hallux valgus on X-ray images with feet. The bones are segmented on the basis of U-Net convolutional neural network. The neural network has been trained on thirty manually segmented images by an orthopedist. We present both qualitative and quantitative segmentation results on ten test images. We present algorithms for great toe extraction and hallux valgus angle (HVA) estimation. The HVA is estimated as the angle between two lines fitted to big toe skeleton. We compare results that were obtained manually, by computer-assisted programs that are used by radiologists, and by the proposed algorithm.
