Shape Analysis of Segmentation Variability - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2020

Shape Analysis of Segmentation Variability

Abstract

Patient-specific cardiac simulation rely on accurate geometric models extracted from medical images. Segmentation of cardiac images is a key, yet possibly error-prone part of patient-specific simulations, e.g., heart propagation models, ECG forward simulation, and ECG Imaging. In this study, we performed shape analysis on multiple segmentations of the same patient to quantify variability. We found that segmentation shape varied most in the basal region of the ventricles and the right ventricular outflow tract in all three structures, which could have significant impact on pipelines that depend on geometric models. The statistical shape-model generated using ShapeWorks provides a pathway to subsequently quantify the impact of the segmentation variability on modeling pipelines with uncertainty quantification.
Fichier principal
Vignette du fichier
146_Preprint.pdf (1.7 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03805404 , version 1 (07-10-2022)

Identifiers

Cite

Jess D Tate, Nejib Zemzemi, Wilson W Good, Peter van Dam, Dana H Brooks, et al.. Shape Analysis of Segmentation Variability. CinC 2020 - Computing in Cardiology Conference, Sep 2020, Rimini, Italy. ⟨10.22489/CinC.2020.466⟩. ⟨hal-03805404⟩
27 View
76 Download

Altmetric

Share

Gmail Facebook X LinkedIn More