New Hybrid Method for Left Ventricular Ejection Fraction Assessment from Radionuclide Ventriculography Images

Author(s): Halima Dziri*, Mohamed Ali Cherni, Dorra Ben-Sellem

Journal Name: Current Medical Imaging
Formerly: Current Medical Imaging Reviews

Volume 17 , Issue 5 , 2021


Become EABM
Become Reviewer
Call for Editor

Graphical Abstract:


Abstract:

Background: In this paper, we propose a new efficient method of radionuclide ventriculography image segmentation to estimate the left ventricular ejection fraction. This parameter is an important prognostic factor for diagnosing abnormal cardiac function.

Methods: The proposed method combines the Chan-Vese and the mathematical morphology algorithms. It was applied to diastolic and systolic images obtained from the Nuclear Medicine Department of Salah AZAIEZ Institute. In order to validate our proposed method, we compare the obtained results to those of two methods present in the literature. The first one is based on mathematical morphology, while the second one uses the basic Chan-Vese algorithm. To evaluate the quality of segmentation, we compute accuracy, positive predictive value and area under the ROC curve. We also compare the left ventricle ejection fraction estimated by our method to that of the reference given by the software of the gamma-camera and validated by the expert, using Pearson’s correlation coefficient, ANOVA test and linear regression.

Results: Static results show that the proposed method is very efficient for the detection of the left ventricle. The accuracy was 98.60%, higher than that of the other two methods (95.52% and 98.50%).

Conclusion: Likewise, the positive predictive value was the highest (86.40% vs. 83.63% 71.82%). The area under the ROC curve was also the most important (0.998% vs. 0.926% 0.919%). On the other hand, Pearson's correlation coefficient was the highest (99% vs. 98% 37%). The correlation was significantly positive (p<0.001).

Keywords: Image segmentation, systolic image, diastolic image, left ventricle ejection fraction, radionuclide ventriculography, cardiac function.

[1]
Michael JW, Steven RB, John U D, et al. 2013 multimodality appropriate use criteria for the detection and risk assessment of stable ischemic heart disease: a report of the American College of Cardiology foundation appropriate use criteria task force, American Heart Association, American Society of Echocardiography, American Society of Nuclear Cardiology, Heart Failure Society of America, Heart Rhythm Society, Society for Cardiovascular Angiography and Interventions, Society of Cardiovascular. J Am Coll Cardiol 2014; 63(4): 380-406.
[2]
Garg N, Dresser T, Aggarwal K, Gupta V, Mittal MK, Alpert MA. Comparison of left ventricular ejection fraction values obtained using invasive contrast left ventriculography, two-dimensional echocardiography, and gated single-photon emission computed tomography. SAGE Open Med 2016; 4: 2050312116655940.
[http://dx.doi.org/10.1177/2050312116655940] [PMID: 27621804]
[3]
Hung GU, Wang YF, Su HY, Hsieh TC, Ko CL, Yen RF. New trends in radionuclide myocardial perfusion imaging. Acta Cardiol Sin 2016; 32(2): 156-66.
[PMID: 27122946]
[4]
Slomka PJ, Germano G, Berman DS. Gated SPECT MPI Processing and Quantitation.Nuclear Cardiac Imaging: Principles and Applications. 5th ed. . Oxford, UK: Oxford University Press 2015; p.9. https://oxfordmedicine.com/view/10.1093/med/978019939 20 94.001.0001/med-9780199392094-chapter-7
[5]
Singh RM, Singh BM, Mehta JL. Role of cardiac CTA in estimating left ventricular volumes and ejection fraction. World J Radiol 2014; 6(9): 669-76.
[http://dx.doi.org/10.4329/wjr.v6.i9.669] [PMID: 25276310]
[6]
Lairez O, Delmas C, Fournier P, et al. Feasibility and accuracy of gated blood pool SPECT equilibrium radionuclide ventriculography for the assessment of left and right ventricular volumes and function in patients with left ventricular assist devices. J Nucl Cardiol 2018; 25(2): 625-34.
[http://dx.doi.org/10.1007/s12350-016-0670-5] [PMID: 27905008]
[7]
Vanhove C, Franken PR, Defrise M, Momen A, Everaert H, Bossuyt A. Automatic determination of left ventricular ejection fraction from gated blood-pool tomography. J Nucl Med 2001; 42(3): 401-7.
[PMID: 11337514]
[8]
Van Kriekinge SD, Berman DS, Germano G. Automatic quantification of left ventricular ejection fraction from gated blood pool SPECT. J Nucl Cardiol 1999; 6(5): 498-506.
[http://dx.doi.org/10.1016/S1071-3581(99)90022-3] [PMID: 10548145]
[9]
Vanhove C, Franken PR. Left ventricular ejection fraction and volumes from gated blood pool tomography: comparison between two automatic algorithms that work in three-dimensional space. J Nucl Cardiol 2001; 8(4): 466-71.
[http://dx.doi.org/10.1067/mnc.2001.115518] [PMID: 11481569]
[10]
Germano G, Kavanagh PB, Fish MB, et al. “Same-Patient Processing” for multiple cardiac SPECT studies. 1. Improving LV segmentation accuracy. J Nucl Cardiol 2016; 23(6): 1435-41.
[http://dx.doi.org/10.1007/s12350-016-0673-2] [PMID: 27743294]
[11]
Germano G, Kavanagh PB, Ruddy TD, et al. “Same-patient processing” for multiple cardiac SPECT studies. 2. Improving quantification repeatability. J Nucl Cardiol 2016; 23(6): 1442-53.
[http://dx.doi.org/10.1007/s12350-016-0674-1] [PMID: 27743297]
[12]
Massalha S, Clarkin O, Thornhill R, Wells G, Chow BJW. Decision support tools, systems, and artificial intelligence in cardiac imaging. Can J Cardiol 2018; 34(7): 827-38.
[http://dx.doi.org/10.1016/j.cjca.2018.04.032] [PMID: 29960612]
[13]
Poujol J, Desvignes M, Broisat A. Myocardium segmentation on 3d spect images. 2015 IEEE International Conference on Image Processing (ICIP). Quebec City, QC. 2015; pp. 4788-92.
[http://dx.doi.org/10.1109/ICIP.2015.7351716]
[14]
Khalifa N, Ettaeib S, Wahabi Y, Hamrouni K. Left ventricle tracking in isotopic ventriculography using statistical deformable models. Int Arab J Inf Technol 2010; 7(2): 213-22.
[15]
Ettaieb S, Hamrouni K, Ruan S. Active Shape Model based on a spatio-temporal a priori knowledge: applied to left ventricle tracking in scintigraphic sequences. Int J Image Process 2012; 6(6): 422.
[16]
Paragios N, Mellina-Gottardo O, Ramesh V. Gradient vector flow fast geodesic active contours. Proceedings Eighth IEEE International Conference on Computer Vision. 2001 July 7-14; Vancouver, BC, Canada. 1: 67-73.
[http://dx.doi.org/10.1109/ICCV.2001.937500]
[17]
Sibille L, Bouallegue FB, Bourdon A, Micheau A, Vernhet-Kovacsik H, Mariano-Goulart D. Comparative values of gated blood-pool SPECT and CMR for ejection fraction and volume estimation. Nucl Med Commun 2011; 32(2): 121-8.
[PMID: 21057340]
[18]
De Bondt P, Claessens T, Rys B, et al. Accuracy of 4 different algorithms for the analysis of tomographic radionuclide ventriculography using a physical, dynamic 4-chamber cardiac phantom. J Nucl Med 2005; 46(1): 165-71.
[PMID: 15632048]
[19]
Alexiou S, Georgoulias P, Angelidis G, et al. Myocardial perfusion and left ventricular quantitative parameters obtained using gated myocardial SPECT: Comparison of three software packages. J Nucl Cardiol 2018; 25(3): 911-24.
[http://dx.doi.org/10.1007/s12350-016-0730-x] [PMID: 27873167]
[20]
Bresser P, De Beer J, De Wet Y. A study investigating variability of left ventricular ejection fraction using manual and automatic processing modes in a single setting. Radiography 2015; 21(1): e41-4.
[http://dx.doi.org/10.1016/j.radi.2014.10.002]
[21]
Belo R, Alves C, Carvalhal C, Figueiredo S, Carolino E, Vieira LO. MUGA processing: intra and interoperator variability impact using manual and automated methods. Saúde & Tecnologia 2019; 22-7.
[22]
HuangC, Shan X, Lan Y, et al. A hybrid active contour segmentation method for myocardial D-SPECT images. IEEE Access 2018; 6: 39334-43.
[23]
Yang R, Mirmehdi M, Xie X, Hall D. Shape and appearance priors for level set-based left ventricle segmentation. IET Comput Vis 2013; 7(3): 170-83.
[http://dx.doi.org/10.1049/iet-cvi.2012.0081]
[24]
Medeiros AG, Silva FH, Ohata EF, Peixoto SA, Filho PPR. An automatic left ventricle segmentation on echocardiogram exams via morphological geodesic active contour with adaptive external energy. J Artif Intell Syst 2019; 1: 77-95.
[http://dx.doi.org/10.33969/AIS.2019.11005]
[25]
Amin Y, Banday SA, Mir AH. A comparative study on left and right endocardium segmentation using gradient vector field and adaptive diffusion flow algorithms. Int J Biosci Biotechnol 2016; 8(1): 105-20.
[http://dx.doi.org/10.14257/ijbsbt.2016.8.1.10]
[26]
Bhan A, Goyal A, Ray V. Fast fully automatic multiframe segmentation of left ventricle in cardiac MRI images using local adaptive k-means clustering and connected component labeling. 2nd International Conference on Signal Processing and Integrated Networks (SPIN); 2015 Feb 19-20; Noida, India: IEEE. 114-9.
[http://dx.doi.org/10.1109/SPIN.2015.7095354]
[27]
Wu EJH, De Andrade ML, Nicolosi DE, Pontes SC Jr. Artificial neural network: border detection in echocardiography. Med Biol Eng Comput 2008; 46(9): 841-8.
[http://dx.doi.org/10.1007/s11517-008-0372-5] [PMID: 18626675]
[28]
Dahiya N, Yezzi A, Piccinelli M, Garcia E. Integrated 3D anatomical model for automatic myocardial segmentation in cardiac CT imagery. Comput Methods Biomech Biomed Eng Imaging Vis 2019; 690-706.
[29]
Messadi M, Bessaid A, Mariano-Goulart D, Bouallègue FB. Development and clinical validation of a hybrid method for semiautomated left ventricle endocardial and epicardial boundary extraction on cine-magnetic resonance images. J Med Imaging (Bellingham) 2018; 5(2): 024002.
[http://dx.doi.org/10.1117/1.JMI.5.2.024002] [PMID: 29662919]
[30]
Jafari MH, Girgis H, Van Woudenberg N, et al. Automatic biplane left ventricular ejection fraction estimation with mobile point-of-care ultrasound using multi-task learning and adversarial training. Int J CARS 2019; 14(6): 1027-37.
[http://dx.doi.org/10.1007/s11548-019-01954-w] [PMID: 30941679]
[31]
Chan TF, Vese LA. Active contours without edges. IEEE Trans Image Process 2001; 10(2): 266-77.
[http://dx.doi.org/10.1109/83.902291] [PMID: 18249617]
[32]
Korfiatis VC, Asvestas PA, Matsopoulos GK. Automatic local parameterization of the Chan Vese active contour model’s force coefficients using edge information. J Vis Commun Image Represent 2015; 29: 71-8.
[http://dx.doi.org/10.1016/j.jvcir.2015.02.008]
[33]
Popovic A, de la Fuente M, Engelhardt M, Radermacher K. Statistical validation metric for accuracy assessment in medical image segmentation. Int J Comput Assist Radiol Surg 2007; 169-81.
[http://dx.doi.org/10.1007/s11548-007-0125-1]
[34]
Fenster A, Chiu B. Evaluation of segmentation algorithms for medical imaging. 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference. Shanghai, China. . 2006; pp.. 7186-9.
[35]
Hanley JA, McNeil BJ. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology 1982; 143(1): 29-36.
[http://dx.doi.org/10.1148/radiology.143.1.7063747] [PMID: 7063747]
[36]
Powers DM. Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation. J Mach Learn Technol 2011; 2(1): 37-63.
[37]
Taha AA, Hanbury A. Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool. BMC Med Imaging 2015; 15(1): 29.
[http://dx.doi.org/10.1186/s12880-015-0068-x] [PMID: 26263899]
[38]
Taylor R. Interpretation of the correlation coefficient: A basic review. J Diagn Med Sonogr 1990; 6(1): 35-9.
[http://dx.doi.org/10.1177/875647939000600106]


open access plus

Rights & PermissionsPrintExport Cite as

Article Details

VOLUME: 17
ISSUE: 5
Year: 2021
Published on: 18 November, 2020
Page: [623 - 633]
Pages: 11
DOI: 10.2174/1573405616666201118122509

Article Metrics

PDF: 27