Critical appraisal of left ventricular function assessment by the automated border detection method on echocardiography. Is it good enough?

Clinical utility of automated assessment of left ventricular ejection fraction using artificial intelligence-assisted border detection

BACKGROUND

Ejection fraction (EF) calculated from 2-dimensional echocardiography provides important prognostic and therapeutic information in patients with heart disease. However, quantification of EF requires planimetry and is time-consuming. As a result, visual assessment is frequently used but is subjective and requires extensive experience. New computer software to assess EF automatically is now available and could be used routinely in busy digital laboratories (>15,000 studies per year) and in core laboratories running large clinical trials. We tested Siemens AutoEF software (Siemens Medical Solutions, Erlangen, Germany) to determine whether it correlated with visual estimates of EF, manual planimetry, and cardiac magnetic resonance (CMR).

METHODS

Siemens AutoEF is based on learned patterns and artificial intelligence. An expert and a novice reader assessed EF visually by reviewing transthoracic echocardiograms from consecutive patients. An experienced sonographer quantified EF in all studies using Simpson's method of disks. AutoEF results were compared to CMR.

RESULTS

Ninety-two echocardiograms were analyzed. Visual assessment by the expert (R = 0.86) and the novice reader (R = 0.80) correlated more closely with manual planimetry using Simpson's method than did AutoEF (R = 0.64). The correlation between AutoEF and CMR was 0.63, 0.28, and 0.51 for EF, end-diastolic and end-systolic volumes, respectively.

CONCLUSION

The discrepancies in EF estimates between AutoEF and manual tracing using Simpson's method and between AutoEF and CMR preclude routine clinical use of AutoEF until it has been validated in a number of large, busy echocardiographic laboratories. Visual assessment of EF, with its strong correlation with quantitative EF, underscores its continued clinical utility.

Doppler echocardiography and tissue Doppler imaging in the healthy rabbit: differences of cardiac function during awake and anaesthetised examination

OBJECTIVE

In the past years, Doppler echocardiography has evolved into a commonly used technique. More recent sophisticated advances in imaging quality have substantially improved spatial and temporal resolution allowing the adaptation of this technique to small animal models, particularly in rabbits but even in mice. Recently, parameters obtained by Tissue Doppler Imaging (TDI) have been shown to be more independent of pre- and afterload than classic hemodynamic Doppler measurements. Exploration of animal models may require anaesthesia but there is only very little information on the effect of anaesthesia on echocardiographic parameters in rabbits.

METHODS

We therefore performed Doppler-echocardiographic examinations of 20 wild-type New Zealand White rabbits in awake state and under light ketamine-xylazine anaesthesia. Special focus was put on the evaluation of global and regional left ventricular systolic and diastolic function using TDI and the myocardial performance index (Tei-index).

RESULTS

Doppler-echocardiographic measurements including TDI in rabbits were feasible to assess cardiac morphology and function within a short examination time. There were some distinct changes of functional parameters during anaesthesia. Exemplary for systolic function, fractional shortening, cardiac output and systolic TDI velocity of the lateral wall decreased distinctly. Global left ventricular function measured by the Tei-index deteriorated.

CONCLUSIONS

Doppler echocardiography and TDI can be performed easily, quickly and safely in the rabbit. Anaesthesia with the cardiodepressive ketamine-xylazine shows some distinct Doppler-echocardiographically measurable negative effects on cardiac function. Thus, echocardiography with less cardiodepressive anaesthetic regimes or even without anaesthesia after training of the animals should be considered as alternatives whenever possible.

Semiautomatic detection of left ventricular contours in contrast-enhanced echocardiographic images: Comparison with magnetic resonance imaging

The aim of this study was to evaluate the accuracy of a semiautomatic contour detection method for left ventricular (LV) volume calculation in contrast-enhanced echocardiographic images. In 26 patients, LV volumes were automatically measured by magnetic resonance imaging and second harmonic echocardiography after intravenous Levovist administration. LV cavity edges were manually drawn and semiautomatically outlined using the active contour algorithm, improved by a nonlinear anisotropic filter; LV volumes were calculated by the modified Simpson's rule. Manual and semiautomatic analysis of echocardiographic images lasted 45 +/- 6 and 20 +/- 8 seconds, respectively. Contrast echocardiography volumes were smaller than those by magnetic resonance imaging (mean difference: 16 mL for manual and 18 mL for automatic analysis). LV volumes by echocardiography closely related with those by magnetic resonance imaging using both manual (r = 0.955) and semiautomatic (r = 0.945) analysis; the correlation was closer for end-systolic than for end-diastolic volumes. In conclusion, this method provides a fast measure of LV volumes in contrast-enhanced images while reducing operator dependency.

Reliability of reporting left ventricular systolic function by echocardiography: a systematic review of 3 methods

BACKGROUND

An accurate assessment of left ventricular (LV) systolic function is of central importance to the diagnosis and management of heart failure. Echocardiography is currently the technique most widely used for this purpose.

METHODS

A systematic review was performed of the evidence for the accuracy of 3 echocardiographic methods--Simpson's rule, wall motion index (WMI), and subjective visual assessment--compared with radionuclide or contrast ventriculography for the assessment of LV ejection fraction (LVEF).

RESULTS

Twenty-five studies were identified in which data on agreement between echocardiography and reference methods were obtainable. A further 18 studies provided correlation data alone. For Simpson's rule, Bland-Altman limits of agreement (95% CI) ranged from LVEF +/-7% to +/-25% (median +/-18%); for WMI +/-13% to +/-20% (median +/-16%); and for subjective visual assessment +/-16% to +/-24% (median +/-19%). Subject echogenicity, the nature of underlying disease, and the use of additional imaging technology, including secondary harmonic imaging and contrast agents, is likely to influence the accuracy of different methods. No method appears to systematically under- or overestimate LVEF to any major extent.

CONCLUSION

These findings have important implications for the investigation of heart failure and for the practice and reporting of echocardiography.