KIT | KIT-Bibliothek | Impressum | Datenschutz

A Statistical Shape Model Pipeline to Enable the Creation of Synthetic 3D Liver Data

Krnjaca, Denis 1; Krames, Lorena 1; Schaufelberger, Matthias ORCID iD icon 1; Nahm, Werner 1
1 Institut für Biomedizinische Technik (IBT), Karlsruher Institut für Technologie (KIT)

Abstract:

The application of machine learning approaches in medical technology is gaining more and more attention.
Due to the high restrictions for collecting intraoperative patient data, synthetic data is increasingly used to support the training of artificial neural networks. We present a pipeline to create a statistical shape model (SSM) using 28 segmented clinical liver CT scans. Our pipeline consists of four steps: data preprocessing, rigid alignment, template morphing, and statistical modeling. We compared two different template morphing approaches: Laplace-Beltrami-regularized projection (LBRP) and nonrigid iterative closest points translational (N-ICP-T) and evaluated both morphing approaches and their corresponding shape model performance using six metrics. LBRP achieved a smaller mean vertex-to-nearest-neighbor distances (2.486 ± 0.897 mm) than N-ICP-T (5.559 ± 2.413 mm). Generalization and specificity errors for LBRP were consistently lower than those of N-ICP-T. The first principal components of the SSM showed realistic anatomical ariations. The performance of the SSM was comparable to a state-of-the-art model.


Verlagsausgabe §
DOI: 10.5445/IR/1000163270
Veröffentlicht am 24.10.2023
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Biomedizinische Technik (IBT)
Publikationstyp Zeitschriftenaufsatz
Publikationsdatum 20.09.2023
Sprache Englisch
Identifikator ISSN: 2364-5504
KITopen-ID: 1000163270
Erschienen in Current Directions in Biomedical Engineering
Verlag De Gruyter
Band 9
Heft 1
Seiten 138 – 141
Vorab online veröffentlicht am 15.09.2023
Nachgewiesen in Dimensions
Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page