Home // SIMUL 2021, The Thirteenth International Conference on Advances in System Simulation // View article

Evaluation of Spinal Anatomy Segmentation Methods using Synthetic Computed Tomography Volumes

Authors:
Austin Tapp
Michel Audette

Keywords: patient-specific modeling; osseoligamentous mesh; synthetic CT; in silico validation; adolescent idiopathic scoliosis

Abstract:
Severe adolescent idiopathic scoliosis (AIS) is corrected by surgical procedures that necessitate ligament releases. To determine appropriate release allotments, soft tissues must be localized on a patient-specific basis. However, routine computed tomography (CT) imaging precludes traditional, voxel-based soft tissue localization. Fortunately, recent studies have proposed top-down segmentation methods, which elucidate soft tissues using pre-operative CT volumes. While the accuracy of vertebral segmentations obtained from these methods has been determined, the accuracy of soft tissue segmentations has not. To ensure the soft tissue segmentation methods are clinically applicable, soft tissue validation must occur. This study presents an evaluation measure for surmised soft tissues, accomplished through the use of synthetic CT (sCT) volumes. The sCTs have geometrically scoliotic shapes and provide ground truth information, which was used to evaluate soft tissue segmentations and establish their clinical utility. This proposed validation method is achieved fully in silico and is generically applicable, allowing future soft tissue elucidation methods to be assessed.

Pages: 14 to 19

Copyright: Copyright (c) IARIA, 2021

Publication date: October 3, 2021

Published in: conference

ISSN: 2308-4537

ISBN: 978-1-61208-898-3

Location: Barcelona, Spain

Dates: from October 3, 2021 to October 7, 2021