Szczegóły publikacji
Opis bibliograficzny
Unsupervised learning-based nonrigid registration of high resolution histology images / Marek WODZIŃSKI, Henning Müller // W: Machine Learning in Medical Imaging : 11th international workshop, MLMI 2020 : held in conjunction with MICCAI 2020 : Lima, Peru, October 4, 2020 : proceedings / eds. Mingxia Liu, [et al.]. — Cham : Springer Nature Switzerland, cop. 2020. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 12436. Image Processing, Computer Vision, Pattern Recognition, and Graphics). — ISBN: 978-3-030-59860-0; e-ISBN: 978-3-030-59861-7. — S. 484–493. — Bibliogr., Abstr. — Publikacja dostępna online od: 2020-09-29
Autorzy (2)
- AGHWodziński Marek
- Müller Henning
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 130526 |
|---|---|
| Data dodania do BaDAP | 2020-10-05 |
| DOI | 10.1007/978-3-030-59861-7_49 |
| Rok publikacji | 2020 |
| 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
The use of different dyes during histological sample preparation reveals distinct tissue properties and may improve the diagnosis. Nonetheless, the staining process deforms the tissue slides and registration is necessary before further processing. The importance of this problem led to organizing an open challenge named Automatic Non-rigid Histological Image Registration Challenge (ANHIR), organized jointly with the IEEE ISBI 2019 conference. The challenge organizers provided 481 image pairs and a server-side evaluation platform making it possible to reliably compare the proposed algorithms. The majority of the methods proposed for the challenge were based on the classical, iterative image registration, resulting in high computational load and arguable usefulness in clinical practice due to the long analysis time. In this work, we propose a deep learning-based unsupervised nonrigid registration method, that provides results comparable to the solutions of the best scoring teams, while being significantly faster during the inference. We propose a multi-level, patch-based training and inference scheme that makes it possible to register images of almost any size, up to the highest resolution provided by the challenge organizers. The median target registration error is close to 0.2% of the image diagonal while the average registration time, including the data loading and initial alignment, is below 3 s. We freely release both the training and inference code making the results fully reproducible.
