Publication Details

Virtual 2D-3D Fracture Reduction with Bone Length Recovery Using Statistical Shape Models

KLÍMA Ondřej, MADEJA Roman, ŠPANĚL Michal, ČUTA Martin, ZEMČÍK Pavel, STOKLÁSEK Pavel and MIZERA Aleš. Virtual 2D-3D Fracture Reduction with Bone Length Recovery Using Statistical Shape Models. In: ShapeMI MICCAI 2018: Workshop on Shape in Medical Imaging Proceedings. LNCS. Granada: Springer International Publishing, 2018, pp. 207-219. ISBN 978-3-030-04746-7. ISSN 0302-9743.
Czech title
Virtuální 2D-3D repozice zlomeniny s odhadem délky založená na statistických tvarových modelech
Type
conference paper
Language
english
Authors
Klíma Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Madeja Roman, MUDr., Ph.D. (FNO)
Španěl Michal, Ing., Ph.D. (DCGM FIT BUT)
Čuta Martin, Mgr., Ph.D. (MUNI)
Zemčík Pavel, prof. Dr. Ing. (DCGM FIT BUT)
Stoklásek Pavel, Ing. (FAI UTB)
Mizera Aleš, Ing., Ph.D. (FAI UTB)
Keywords

Preoperative planning, Fracture reduction, Fixation devices, 2D-3D registration, Statistical shape model

Abstract

Computer-assisted 3D preoperative planning based on 2D stereo radiographs has been brought into focus recently in the field of orthopedic surgery. To enable planning, it is crucial to reconstruct a patient-specific 3D bone model from X-ray images. However, most of the existing studies deal only with uninjured bones, which limits their possible applications for planning. In this paper, we propose a method for the reconstruction of long bones with diaphyseal fractures from 2D radiographs of the individual fracture segments to 3D polygonal models of the intact bones. In comparison with previous studies, the main contribution is the ability to recover an accurate length of the target bone. The reconstruction is based on non-rigid 2D-3D registration of a single statistical shape model onto the radiographs of individual fragments, performed simultaneously with the virtual fracture reduction. The method was tested on a syntethic data set containing 96 virtual fractures and on real radiographs of dry cadaveric bones suffering peri-mortem injuries. The accuracy was evaluated using the Hausdorff distance between the reconstructed and ground-truth bone models. On the synthetic data set, the average surface error reached 1.48+1.16 mm. The method was built into preoperative planning software designated for the selection of the best-fitting fixation material. 

Published
2018
Pages
207-219
Journal
Lecture Notes in Computer Science, no. 11167, ISSN 0302-9743
Proceedings
ShapeMI MICCAI 2018: Workshop on Shape in Medical Imaging Proceedings
Series
LNCS
Conference
ShapeMI MICCAI 2018: Workshop on Shape in Medical Imaging, Granada, ES
ISBN
978-3-030-04746-7
Publisher
Springer International Publishing
Place
Granada, ES
DOI
EID Scopus
BibTeX
@INPROCEEDINGS{FITPUB11806,
   author = "Ond\v{r}ej Kl\'{i}ma and Roman Madeja and Michal \v{S}pan\v{e}l and Martin \v{C}uta and Pavel Zem\v{c}\'{i}k and Pavel Stokl\'{a}sek and Ale\v{s} Mizera",
   title = "Virtual 2D-3D Fracture Reduction with Bone Length Recovery Using Statistical Shape Models",
   pages = "207--219",
   booktitle = "ShapeMI MICCAI 2018: Workshop on Shape in Medical Imaging Proceedings",
   series = "LNCS",
   journal = "Lecture Notes in Computer Science",
   number = 11167,
   year = 2018,
   location = "Granada, ES",
   publisher = "Springer International Publishing",
   ISBN = "978-3-030-04746-7",
   ISSN = "0302-9743",
   doi = "10.1007/978-3-030-04747-4\_20",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/11806"
}
Back to top