Szczegóły publikacji
Opis bibliograficzny
Multi-step, learning-based, semi-supervised image registration algorithm / Marek WODZIŃSKI // W: Segmentation, classification, and registration of multi-modality medical imaging data : MICCAI 2020 Challenges, ABCs 2020, L2R 2020, TN-SCUI 2020 held in conjunction with MICCAI 2020 : Lima, Peru, October 4–8, 2020 : proceedings / eds. Nadya Shusharina, Mattias P. Heinrich, Ruobing Huang. — Cham : Springer Nature Switzerland, cop. 2021. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 12587. Image Processing, Computer Vision, Pattern Recognition, and Graphics). — ISBN: 978-3-030-71826-8; e-ISBN: 978-3-030-71827-5. — S. 94–99. — Bibliogr., Abstr. — Publikacja dostępna online od: 2021-03-13. — Referat w ramach The Learn2Reg Challenge (Learn2Reg 2020)
Autor
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 133026 |
|---|---|
| Data dodania do BaDAP | 2021-03-16 |
| DOI | 10.1007/978-3-030-71827-5_12 |
| Rok publikacji | 2021 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | Medical Image Computing and Computer-Assisted Intervention 2020 |
| Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
This paper presents a contribution to the Learn2Reg challenge organized jointly with the MICCAI 2020, more specifically, to the task related to inter-patient hippocampus registration in magnetic resonance images. The proposed algorithm is a multi-step, learning-based, and semi-supervised procedure. The method consists of a sequentially stacked U-Net-like architecture, trained in alternation. The method was ranked as the second-best (for the hippocampus registration task) in terms of the combined challenge evaluation criteria.
