Automated Tracking of the Mitral Valve Annulus Motion in Apical Echocardiographic Images Using Multidimensional Dynamic Programming

Nevo, S.T.; Stralen, Marijn van; Vossepoel, Albert M.; Reiber, J. H. C.; Jong, Nico de; Steen, Antonius F.W. van der; Bosch, Johan G.

doi:10.1016/j.ultrasmedbio.2007.03.007

Cited by 27 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these techniques required a human operator to identify the sampling location in order to produce a trace for subsequent automated analysis. Nevo et al [10] developed a semi-automated system to track mitral valve annulus motion using multidimensional dynamic programming and apodized block matching, however this again required initial manual selection of annulus points.…”

Section: Introductionmentioning

confidence: 99%

A new automated system to identify a consistent sampling position to make tissue Doppler and transmitral Doppler measurements of E, E′ and E/E′

Dhutia

Cole

Willson

et al. 2012

International Journal of Cardiology

View full text Add to dashboard Cite

BackgroundTransmitral pulse wave (PW) Doppler and annular tissue Doppler velocity measurements provide valuable diagnostic and prognostic information. However, they depend on an echocardiographer manually selecting positions to make the measurements. This is time-consuming and open to variability, especially by less experienced operators. We present a new, automated method to select consistent Doppler velocity sites to measure blood flow and muscle function.MethodsOur automated algorithm combines speckle tracking and colour flow mapping to locate the septal and lateral mitral valve annuli (to measure peak early diastolic velocity, E′) and the mitral valve inflow (to measure peak inflow velocity, E). We also automate peak velocity measurements from resulting PW Doppler traces. The algorithm-selected locations and time taken to identify them were compared against a panel of echo specialists — the current “gold standard”.ResultsThe algorithm identified positions to measure Doppler velocities within 3.6 ± 2.2 mm (mitral inflow), 3.2 ± 1.8 mm (septal annulus) and 3.8 ± 1.5 mm (lateral annulus) of the consensus of 3 specialists. This was less than the average 4 mm fidelity with which the specialists could themselves identify the points. The automated algorithm could potentially reduce the time taken to make these measurements by 60 ± 15%.ConclusionsOur automated algorithm identified sampling positions for measurement of mitral flow, septal and lateral tissue velocities as reliably as specialists. It provides a rapid, easy method for new specialists and potentially non-specialists to make automated measurements of key cardiac physiological indices. This could help support decision-making, without introducing delay and extend availability of echocardiography to more patients.

show abstract

Section: Introductionmentioning

confidence: 99%

A new automated system to identify a consistent sampling position to make tissue Doppler and transmitral Doppler measurements of E, E′ and E/E′

Dhutia

Cole

Willson

et al. 2012

International Journal of Cardiology

View full text Add to dashboard Cite

show abstract

“…Multidimensional dynamic programing [12] is a more robust technique and much more time consuming method. [22] The computation times reported for multidimensional dynamic programing [12] makes the real time application of this approach more difficult. The algorithm developed here provides results comparable to those obtained with multidimensional dynamic programing with much lower computation times.…”

Section: Discussionmentioning

confidence: 99%

“…Over the years, several filters have been proposed for despeckling of ultrasound B-Mode images, including the state-of-the-art Non-Local means filter. [12,13] In this work the filters described and compared in the work by Loizou et al [15] and the Non-Local means filter implemented by Coupe et al [16] were considered. This last filter provides a greater smoothing effect and better preserves the edges but requires a computation time around eight times larger than that required by the filters proposed by Loizou et al To choose a filter for our work, the tracking algorithm was run on videos despeckled with the different filters.…”

Section: Preprocessingmentioning

confidence: 99%

“…Unlike the work by Nevo et al [12] which used the correlations modality, the SAD was chosen here. The SAD modality was chosen since low correlation coefficients were observed at phase changes (e.g.…”

Section: Block Matchingmentioning

confidence: 99%

“…Good results have been obtained using a dynamic programming based algorithm. [12] However, this algorithm has been implemented only for tracking the mitral valve in apical four chamber (A4C) echocardiograms and was tested only in patients with acute myocardial infarction and not with randomly selected subjects. Additionally, reported computation times are of about two minutes for single cycle echocardiograms, recorded with a frame rate of 25 fps.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A semiautomatic tracking algorithm for mitral annular plane excursion: A mode for cardiac function evaluation

Goldsztejn¹,

Avraham

Zurakhov

et al. 2017

JBEI

View full text Add to dashboard Cite

Reduced long-axis deformation as derived from the temporal excursion of the mitral annular plane correlates well with left ventricle systolic and diastolic dysfunction. Since this parameter is barely compensated at the onset of ventricular dysfunction, it is proposed as an early marker of a dysfunction. The lack of a rapid, yet accurate tool for the evaluation of mitral annular plane excursion (MAPE) prevents this measurement from being used routinely in the clinic. Here, a semiautomatic tracking algorithm of the mitral annulus was developed. Describing the MAPE in clear geometrical terms together with state-of-the-art speckle tracking and speckle reduction algorithms, facilitated the development of such an algorithm. The performance of the algorithm was evaluated using a cohort of 48 apical views of subjects chosen randomly from a set of routine examinations done at Rambam Hospital. The curves obtained using the proposed algorithm were compared using a cross-correlation test with the standard global strain. The average cross-correlation coefficient obtained was 0.92, with standard deviation of 0.07.

show abstract

Mitral valve prolapse: a source of arrhythmias?

Wall

Schalij

2009

Int J Cardiovasc Imaging

View full text Add to dashboard Cite

Automated Tracking of the Mitral Valve Annulus Motion in Apical Echocardiographic Images Using Multidimensional Dynamic Programming

Cited by 27 publications

References 21 publications

A new automated system to identify a consistent sampling position to make tissue Doppler and transmitral Doppler measurements of E, E′ and E/E′

A new automated system to identify a consistent sampling position to make tissue Doppler and transmitral Doppler measurements of E, E′ and E/E′

A semiautomatic tracking algorithm for mitral annular plane excursion: A mode for cardiac function evaluation

Mitral valve prolapse: a source of arrhythmias?

Contact Info

Product

Resources

About