Key result
Automated annotation of the mitral annulus using pairwise and groupwise non-rigid image registration achieved accuracy comparable to inter-observer variability.
Why the study?
Morphological assessment of mitral annulus geometry and deformation in 4D-CT supports transcatheter mitral valve replacement development but is often performed manually, motivating automated landmark annotation.
Automated annotation of the mitral annulus in 4D-CT using non-rigid image registration achieves accuracy comparable to manual annotation, potentially streamlining morphological assessment for transcatheter mitral valve replacement.
Answers are grounded in this paper and cite their sources.
May streamline 4D-CT mitral annulus assessment for TMVR; leaves open prospective validation before clinical adoption.
The morphological assessment of the geometry and the deformation of the mitral annulus has the potential to support the development of minimally invasive solutions for patients suffering from mitral valve regurgitation. Cardiac 4D-CT allows such a morphological assessment, which is, however, often performed manually, by annotating the mitral annulus and other cardiac landmarks. The goal of this study is to automate the annotation of cardiac landmarks in 4D-CT by propagating them from one reference phase to all others. The method proposed is based on non-rigid image registration, and four alternative variations have been tested, based on pairwise and groupwise registration. Their accuracy is evaluated against inter-observer variability on eight 4D-CTs. The results show that the pairwise and groupwise approaches using independent 3D transforms have a comparable performance, with an accuracy comparable with the inter-observer variability; however, the latter approach was computationally more expensive. Instead, the spatio-temporal groupwise approach obtained significantly worse results. The technology has, therefore, the potential to make an efficient analysis of the deforming heart more attainable. Moreover, the manual annotation process confirms that the mitral annulus deforms significantly during the cardiac contraction, supporting the use of 4D imaging for a reliable morphological assessment.
No takes yet. Share an insight, caveat, or question.
Farotto et al. (2022) studied Mitral valve regurgitation (n=8). Automated annotation using non-rigid image registration vs. Manual annotation (inter-observer variability) was evaluated on Accuracy of automated annotation. Automated annotation of the mitral annulus using pairwise and groupwise non-rigid image registration achieved accuracy comparable to inter-observer variability.
Synapse has enriched 10 related papers. Consider them for comparative context: