Background: Cardiovascular magnetic resonance (CMR) feature tracking is increasingly used to quantify cardiac mechanics from cine CMR imaging, although validation against reference standard techniques has been limited. Furthermore, studies have suggested that commonly-derived metrics, such as peak global strain (reported in 63% of feature tracking studies), can be quantified using contours from just two frames – end-diastole (ED) and end-systole (ES) – without requiring tracking software. We hypothesized that mechanics derived from feature tracking would not agree with those derived from a reference standard (displacement-encoding with stimulated echoes (DENSE) imaging), and that peak strain from feature tracking would agree with that derived using simple processing of only ED and ES contours.
Methods: We retrospectively identified 88 participants with 186 pairs of DENSE and balanced steady state free precession (bSSFP) image slices acquired at the same locations across two institutions. Left ventricular (LV) strains, torsion, and dyssynchrony were quantified from both feature tracking (TomTec Imaging Systems, Circle Cardiovascular Imaging) and DENSE. Contour-based strains from bSSFP images were derived from ED and ES contours. Agreement was assessed with Bland-Altman analyses and coefficients of variation (CoV). All biases are reported in absolute percentage.
Results: Comparison results were similar for both vendor packages (TomTec and Circle), and thus only TomTec Imaging System data are reported in the abstract for simplicity. Compared to DENSE, mid-ventricular circumferential strain (Ecc) from feature tracking had acceptable agreement (bias: − 0.4%, p = 0.36, CoV: 11%). However, feature tracking significantly overestimated the magnitude of Ecc at the base (bias: − 4.0% absolute, p < 0.001, CoV: 18%) and apex (bias: − 2.4% absolute, p = 0.01, CoV: 15%), underestimated torsion (bias: − 1.4 deg/cm, p < 0.001, CoV: 41%), and overestimated dyssynchrony (bias: 26 ms, p < 0.001, CoV: 76%). Longitudinal strain (Ell) had borderline-acceptable agreement (bias: − 0.2%, p = 0.77, CoV: 19%). Contour-based strains had excellent agreement with feature tracking (biases: − 1.3–0.2%, CoVs: 3–7%).
Conclusion: Compared to DENSE as a reference standard, feature tracking was inaccurate for quantification of apical and basal LV circumferential strains, longitudinal strain, torsion, and dyssynchrony. Feature tracking was only accurate for quantification of mid LV circumferential strain. Moreover, feature tracking is unnecessary for quantification of whole-slice strains (e.g. base, apex), since simplified processing of only ED and ES contours yields very similar results to those derived from feature tracking. Current feature tracking technology therefore has limited utility for quantification of cardiac mechanics.
Digital Object Identifier (DOI)
This work was supported by a National Institutes of Health (NIH) Director’s Early Independence Award (DP5 OD-012132), NIH T32 HL-072743, NIH P20 GM103527, and NIH grant number UL1TR000117 from the National Center for Research Resources and the National Center for Advancing Translational Sciences.
The datasets generated and/or analyzed during the current study are available on reasonable request with approval of the corresponding author.
Wehner, Gregory J.; Jing, Linyuan; Haggerty, Christopher M.; Suever, Jonathan D.; Chen, Jing; Hamlet, Sean M.; Feindt, Jared A.; Mojsejenko, Walter Dimitri; Fogel, Mark A.; and Fornwalt, Brandon K., "Comparison of Left Ventricular Strains and Torsion Derived from Feature Tracking and DENSE CMR" (2018). Biomedical Engineering Faculty Publications. 31.
Additional file 1: Literature Review.
12968_2018_485_MOESM2_ESM.docx (143 kB)
Additional file 2: Comparison between Endocardial Strain from Feature Tracking and DENSE.
12968_2018_485_MOESM3_ESM.docx (190 kB)
Additional file 3: Comparison of Strain Calculations.
12968_2018_485_MOESM4_ESM.docx (302 kB)
Additional file 4: Validation using a Second Feature Tracking Software.