Szczegóły publikacji
Opis bibliograficzny
High-resolution cranial defect reconstruction by iterative, low-resolution, point cloud completion transformers / Marek WODZIŃSKI, Mateusz DANIOŁ, Daria HEMMERLING, Mirosław SOCHA // W: Medical Image Computing and Computer Assisted Intervention - MICCAI 2023 : 26th international conference : Vancouver, BC, Canada, October 8–12, 2023 : proceedings, Pt. 9 / eds. Hayit Greenspan, [et al.]. — Cham, Switzerland : Springer Nature Switzerland AG, cop. 2023. — (Lecture Notes in Computer Science ; ISSN 0302-9743 ; LNCS 14228). — ISBN: 978-3-031-43995-7; e-ISBN: 978-3-031-43996-4. — S. 333-343. — Bibliogr., Abstr. — Publikacja dostępna online od: 2023-10-01. — M. Wodziński - dod. afiliacja: University of Applied Sciences Western Switzerland (HES-SO Valais), Sierre, Switzerland
Autorzy (4)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 149686 |
|---|---|
| Data dodania do BaDAP | 2023-11-03 |
| DOI | 10.1007/978-3-031-43996-4_32 |
| Rok publikacji | 2023 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Konferencja | Medical Image Computing and Computer-Assisted Intervention 2023 |
| Czasopismo/seria | Lecture Notes in Computer Science |
Abstract
Each year thousands of people suffer from various types of cranial injuries and require personalized implants whose manual design is expensive and time-consuming. Therefore, an automatic, dedicated system to increase the availability of personalized cranial reconstruction is highly desirable. The problem of the automatic cranial defect reconstruction can be formulated as the shape completion task and solved using dedicated deep networks. Currently, the most common approach is to use the volumetric representation and apply deep networks dedicated to image segmentation. However, this approach has several limitations and does not scale well into high-resolution volumes, nor takes into account the data sparsity. In our work, we reformulate the problem into a point cloud completion task. We propose an iterative, transformer-based method to reconstruct the cranial defect at any resolution while also being fast and resource-efficient during training and inference. We compare the proposed methods to the state-of-the-art volumetric approaches and show superior performance in terms of GPU memory consumption while maintaining high-quality of the reconstructed defects.
