Shear wave imaging and classification using extended Kalman filter and decision tree algorithm

Tran Quang-Huy; Phuc Thinh Doan; Nguyen Thi Hoang Yen; Duc-Tan Tran; Tran Quang-Huy; Phuc Thinh Doan; Nguyen Thi Hoang Yen; Duc-Tan Tran

doi:10.3934/mbe.2021378

Mathematical Biosciences and Engineering

2021, Volume 18, Issue 6: 7631-7647. doi: 10.3934/mbe.2021378

Previous Article Next Article

Research article Special Issues

Shear wave imaging and classification using extended Kalman filter and decision tree algorithm

1.
Faculty of Physics, Hanoi Pedagogical University 2, Hanoi, Vietnam
2.
NTT Hi-Tech Institute – Nguyen Tat Thanh University, HoChiMinh City, Vietnam
3.
Faculty of Mechanical, Electrical, Electronic and Automotive Engineering, Nguyen Tat Thanh University, Ho Chi Minh 700000, Vietnam
4.
Faculty of Technology and education, Hanoi National University of Education, Hanoi, Vietnam
5.
Faculty of Electrical and Electronic Engineering, Phenikaa University, Hanoi 12116, Vietnam

Received: 25 July 2021 Accepted: 01 September 2021 Published: 03 September 2021

Shear wave ultrasound elastography is a quantitative imaging approach in soft tissues based on viscosity-elastic properties. Complex shear modulus (CSM) estimation is an effective solution to analyze tissues' physical properties for elasticity and viscosity based on the wavenumber and attenuation coefficient. CSM offers a way to detect and classify some types of soft tissues. However, CSM-based elastography inherits some obstacles, such as estimation precision and calculation complexity. This work proposes an approach for two-dimensional CSM estimation and soft tissue classification using the Extended Kalman Filter (EKF) and Decision Tree (DT) algorithm, named the EKF-DT approach. CSM estimation is obtained by applying EKF to exploit shear wave propagation at each spatial point. Afterward, the classification of tissues is done by a direct and efficient decision tree algorithm categorizing three types of normal, cirrhosis, and fibrosis liver tissues. Numerical simulation scenarios have been employed to illustrate the recovered quality and practicality of the proposed method's liver tissue classification. With the EKF, the estimated wave number and attenuation coefficient are close to the ideal values, especially the estimated wave number. The states of three liver tissue types were automatically classified by applying the DT coupled with two proposed thresholds of elasticity and viscosity: (2.310 kPa, 1.885 Pa.s) and (3.620 kPa 3.146 Pa.s), respectively. The proposed method shows the feasibility of CSM estimation based on the wavenumber and attenuation coefficient by applying the EKF. Moreover, the DT can automate the classification of liver tissue conditions by proposing two thresholds. The proposed EKF-DT method can be developed by 3D image reconstruction and empirical data before applying it in medical practice.
- Shear wave elastography elasticity,
- viscosity,
- complex shear modulus,
- extended Kalman filter, decision tree
Citation: Tran Quang-Huy, Phuc Thinh Doan, Nguyen Thi Hoang Yen, Duc-Tan Tran. Shear wave imaging and classification using extended Kalman filter and decision tree algorithm[J]. Mathematical Biosciences and Engineering, 2021, 18(6): 7631-7647. doi: 10.3934/mbe.2021378

Related Papers:

Abstract

Shear wave ultrasound elastography is a quantitative imaging approach in soft tissues based on viscosity-elastic properties. Complex shear modulus (CSM) estimation is an effective solution to analyze tissues' physical properties for elasticity and viscosity based on the wavenumber and attenuation coefficient. CSM offers a way to detect and classify some types of soft tissues. However, CSM-based elastography inherits some obstacles, such as estimation precision and calculation complexity. This work proposes an approach for two-dimensional CSM estimation and soft tissue classification using the Extended Kalman Filter (EKF) and Decision Tree (DT) algorithm, named the EKF-DT approach. CSM estimation is obtained by applying EKF to exploit shear wave propagation at each spatial point. Afterward, the classification of tissues is done by a direct and efficient decision tree algorithm categorizing three types of normal, cirrhosis, and fibrosis liver tissues. Numerical simulation scenarios have been employed to illustrate the recovered quality and practicality of the proposed method's liver tissue classification. With the EKF, the estimated wave number and attenuation coefficient are close to the ideal values, especially the estimated wave number. The states of three liver tissue types were automatically classified by applying the DT coupled with two proposed thresholds of elasticity and viscosity: (2.310 kPa, 1.885 Pa.s) and (3.620 kPa 3.146 Pa.s), respectively. The proposed method shows the feasibility of CSM estimation based on the wavenumber and attenuation coefficient by applying the EKF. Moreover, the DT can automate the classification of liver tissue conditions by proposing two thresholds. The proposed EKF-DT method can be developed by 3D image reconstruction and empirical data before applying it in medical practice.

References

[1]	J. Bercoff, A. Criton, C. C. Bacrie, J. Souquet, A. Athanasiou, ShearWave™ Elastography A new real time imaging mode for assessing quantitatively soft tissue viscoelasticity, IEEE Ultrasonics Symposium, IEEE, (2008), 321-324.
[2]	A. P. Sarvazyan, O. V. Rudenko, S. D. Swanson, J. B. Fowlkes, S. Y. Emelianov, Shear wave elasticity imaging: A new ultrasonic technology of medical diagnostics, Ultrasound Med. Biol., 24 (1998), 1419-1435. doi: 10.1016/S0301-5629(98)00110-0
[3]	J. L. Gennisson, T. Deffieux, M. Fink, M. Tanter, Ultrasound elastography: Principles and techniques, Diagn. Interv. Imaging, 94 (2013), 487-495. doi: 10.1016/j.diii.2013.01.022
[4]	E. Budelli, J. Brum, M. Bernal, T. Deffieux, M. Tanter, P. Lema, et al., A diffraction correction for storage and loss moduli imaging using radiation force based elastography, Phys. Med. Biol., 62 (2017), 91-106. doi: 10.1088/1361-6560/62/1/91
[5]	J. Marcon, M. Trottmann, J. R¨ubenthaler, M. D' Anastasi, C. Stief, M. Reiser, et al., Three-dimensional vs. two-dimensional shear-wave elastography of the testes-preliminary study on a healthy collective, Clin. Hemorheol. Microcirc., 64 (2016), 447-456.
[6]	K. Skerl, C. Sandy, E. Andrew, First step to facilitate long-term and multi-centre studies of shear wave elastography in solid breast lesions using a computer-assisted algorithm, Int. J. Comput. Assist. Radiol. Surg., 12 (2017), 1533-1542. doi: 10.1007/s11548-017-1596-3
[7]	Y. Wang, H. G. Nasief, S. Kohn, A. Milkowski, T. Clary, S. Barnes, et al., Three-dimensional ultrasound elasticity imaging on an automated breast volume scanning system, Ultrason. Imaging, 39 (2017), 369-392. doi: 10.1177/0161734617712238
[8]	Y. Atsushi, Y. Yamakoshi, T. Ohsawa, H. Shitara, T. Ichinose, H. Shiozawa, et al., Shear wave velocity measurement of upper trapezius muscle by color Doppler shear wave imaging, J. Med. Ultrasound, 45 (2018), 129-136.
[9]	C. Zhang, Z. Zhang, 2D ultrasonic elastography using beam steering and iterative correction, J Med. Imaging Health Inform., 7 (2017), 211-216. doi: 10.1166/jmihi.2017.2008
[10]	C. J. Moore, M. M. Hossain C. M. Gallippi, 2D ARFI and viscoelastic response (visr) anisotropy imaging in skeletal muscle, International Ultrasonics Symposium, IEEE, 2017, 1-4.
[11]	C. Papadacci, E. A. Bunting, E. E. Konofagou, 3D quasi-static ultrasound elastography with plane wave in vivo, IEEE Trans. Med. Imaging, 36 (2017), 357-365. doi: 10.1109/TMI.2016.2596706
[12]	A.P. Sarvazyan, O.V. Rudenko, S.D. Swanson, J.B. Fowlkes, S.Y. Emelianov, Shear wave elasticity imaging: A new ultrasonic technology of medical diagnostics, Ultrasound Med. Biol., 24 (1998), 1419-1435. doi: 10.1016/S0301-5629(98)00110-0
[13]	J. L. Gennisson, T. Deffieux, M. Fink, M. Tanter, Ultrasound elastography: principles and techniques, Diagn. Interv. Imaging, 94 (2013), 487-495. doi: 10.1016/j.diii.2013.01.022
[14]	G. Ferraioli, P. Parekh, A.B. Levitov, C. Filice, Shear wave elastography for evaluation of liver fibrosis, J. Ultrasound Med., 33(2014), 197-203. doi: 10.7863/ultra.33.2.197
[15]	K. Hoyt, K. J. Parker, D. J. Rubens, Real-time shear velocity imaging using sonoelastographic techniques, Ultrasound Med. Biol., 33 (2007), 1086-1097. doi: 10.1016/j.ultrasmedbio.2007.01.009
[16]	K. Nightingale, S. McAleavey, G. Trahey, Shear-wave generation using acoustic radiation force: In vivo and ex vivo results, Ultrasound Med. Biol., 29 (2003), 1715-1723. doi: 10.1016/j.ultrasmedbio.2003.08.008
[17]	K. Hiroshi, Propagation of vibration caused by electrical excitation in the normal human heart, Ultrasound Med. Biol., 35 (2009), 936-948. doi: 10.1016/j.ultrasmedbio.2008.12.013
[18]	M. Orescanin, Y. Wang, M. F. Insana, 3-D FDTD simulation of shear waves for evaluation of complex modulus imaging, IEEE Trans. Ultrason. Ferroelectr. Freq. Control, 58 (2011), 389-398. doi: 10.1109/TUFFC.2011.1816
[19]	M. Denis, A. Gregory, M. Bayat, R.T. Fazzio, D.H. Whaley, K. Ghosh, et al., Correlating tumor stiffness with immunohistochemical subtypes of breast cancers: prognostic value of comb-push ultrasound shear elastography for differentiating luminal subtypes, PloS ONE, 11 (2016), e0165003. doi: 10.1371/journal.pone.0167791
[20]	M. Orescanin, M. F. Insana, Shear modulus estimation with vibrating needle stimulation, IEEE Trans. Ultrason. Ferroelectr. Freq. Control, 57 (2010), 1358-1367. doi: 10.1109/TUFFC.2010.1555
[21]	T. E. Oliphant, R. R. Kinnick, A. Manduca, R. L. Ehman, J. F. Greenleaf, An error analysis of Helmholtz inversion for incompressible shear, vibration elastography with application to filter-design for tissue characterization, Ultrasonics Symposium, IEEE, 2 (2000), 1795-1798.
[22]	M. Orescanin, M. F. Insana, Model-based complex shear modulus reconstruction: A Bayesian approach, Ultrasonics Symposium, IEEE, 2 (2010), 61-67.
[23]	T. Tran-Duc, Y. Wang, N. Linh-Trung, M. N. Do, M. F. Insana, Complex Shear Modulus Estimation Using Maximum Likelihood Ensemble Filters, 4th International Conference on Biomedical Engineering in Vietnam, Springer Berlin Heidelberg, (2013), 313-316.
[24]	Q. H. Luong, M. C. Nguyen, T. Duc-Tan, A frequency dependent investigation of complex shear modulus estimation, International Conference on Advances in Information and Communication Technology, Springer International Publishing, 2016, 31-40.
[25]	M. Zupanski, Maximum Likelihood Ensemble Filter: Theoretical aspects, Mon. Weather Rev., 133 (2005), 1710-1726. doi: 10.1175/MWR2946.1
[26]	L. Huwart, F. Peeters, R. Sinkus, L. Annet, N. Salameh, L.C. Ter Beek, et al., Liver fibrosis: non-invasive assessment with MR elastography, NMR Biomed., 19 (2006), 173-179. doi: 10.1002/nbm.1030
[27]	J. B. Veyrieres, F. Albarel, J. V. Lombard, J. Berbis, F. Sebag, Threshold value in Shear Wave elastography to rule out malignant thyroid nodules: a reality?. Eur. J. Radiol., 81 (2012), 3965-3972.
[28]	Y. Xiao, J. Zeng, M. Qian, R. Zheng, H. Zheng, Quantitative analysis of peri-tumor tissue elasticity based on shear-wave elastography for breast tumor classification, 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2013, 1128-1131.
[29]	D. C. Olgun, B. Korkmazer, F. Kılıç, A. S. Dikici, M. Velidedeoğlu, F. Aydoğan, et al., Use of shear wave elastography to differentiate benign and malignant breast lesions, Diagn. Interv. Radiol., 20 (2014), 239. doi: 10.5152/dir.2014.13306
[30]	G. Welch, G. Bishop, An introduction to the Kalman filter, University of North, 1995, 127-132.
[31]	N. T. Hao, T. Thuy-Nga, V. Dinh-Long, T. Duc-Tan, N. Linh-Trung, 2D Shear wave imaging using maximum likelihood ensemble filter, International Conference on Green and Human Information Technology, 2013, 88-94.
[32]	S. R. Safavian, D. Landgrebe, A survey of decision tree classifier methodology, IEEE Trans. Syst. Man. Cybern., 21 (1991), 660-674. doi: 10.1109/21.97458
[33]	A. Myles, R. N. Feudale, Y. Liu, N. A. Woody, S. D. Brown, An introduction to decision tree modeling, J. Chemom., 18 (2004), 275-285. doi: 10.1002/cem.873
[34]	K. Krishna, M. N. Murty, Genetic K-means algorithm, IEEE Trans. Syst. Man. Cybern., 29 (1999), 433-439. doi: 10.1109/3477.764879
[35]	B. Pundarikaksha, R. B. Chinnam, HMMs for diagnostics and prognostics in machining processes, Int. J. Prod. Res., 43 (2005), 1275-1293. doi: 10.1080/00207540412331327727
[36]	S. V. M. Vishwanathan, M. N. Murty, SSVM: A simple SVM algorithm, International Joint Conference on Neural Networks, IEEE, 3 (2002), 2393-2398.
[37]	Y. Zheng, S. Chen, W. Tan, R. Kinnick, J.F. Greenleaf, Detection of tissue harmonic motion induced by ultrasonic radiation force using pulse-echo ultrasound and Kalman filter, IEEE Trans. Ultrason. Ferroelectr. Freq. Control, 54 (2007), 290-300. doi: 10.1109/TUFFC.2007.243
[38]	M. W. Urban, S. Chen, J. F. Greenleaf, Error in estimates of tissue material properties from shear wave dispersion ultrasound vibrometry, IEEE Trans. Ultrason. Ferroelectr. Freq. Control, 56 (2009), 748-758. doi: 10.1109/TUFFC.2009.1097
[39]	W. N. Findley, J.S. Lai, K. Onaran, R. M. Christensen, Creep and relaxation of nonlinear viscoelastic materials with an introduction to linear viscoelasticity, J. Appl. Mech., 44 (1977), 364-365.
[40]	M. F. Insana, C. Pellot-Barakat, M. Sridhar, K. K. Lindfors, Viscoelastic imaging of breast tumor microenvironment with ultrasound, J. Mammary Gland. Biol. Neoplasia., 9 (2004), 393-404. doi: 10.1007/s10911-004-1409-5
[41]	M. Orescanin. M. F. Insana, Shear modulus estimation with vibrating needle stimulation, IEEE Trans. Ultrason. Ferroelectr. Freq. Control, 57 (2010), 1358-1367. doi: 10.1109/TUFFC.2010.1555
[42]	L. Quang Hai, D. T. Tran, N. L. Trung, H. T. Huynh, M. N. Do, Simulation study of 2D viscoelastic imaging of soft tissues using the extended Kalman filter for tumor detection, SIMUL-T. SOC. MOD. SIM., 96 (2020), 435-447.
[43]	Y. C. Fung, Biomechanics: mechanical properties of living tissues, Springer Science & Business Media, (2013).
[44]	P. R. Harper, A review and comparison of classification algorithms for medical decision making, Health Policy, 71 (2005), 315-331. doi: 10.1016/j.healthpol.2004.05.002
[45]	Q. Zhang, Y. Xiao, W. Dai, J. Suo, C. Wang, J. Shi, H. Zheng, Deep learning based classification of breast tumors with shear-wave elastography, Ultrasonics, 72 (2016), 150-157. doi: 10.1016/j.ultras.2016.08.004
[46]	P. Kapetas, R. Woitek, P. Clauser, M. Bernathova, K. Pinker, T. H. Helbich, et al., A simple ultrasound based classification algorithm allows differentiation of benign from malignant breast lesions by using only quantitative parameters, Mol. Imaging Biol., 20 (2018), 1053-1060. doi: 10.1007/s11307-018-1187-x
[47]	N. Winn, J. Baldwin, V. Cassar-Pullicino, P. Cool, M. Ockendon, B. Tins, et al., Characterization of soft tissue tumours with ultrasound, shear wave elastography and MRI, Skelet. Radiol., 49 (2020), 869-881.
[48]	P. T. Thu-Ha, L. Quang-Hai, N. Van-Dung, T. Duc-Tan, H. Huu-Tue, Two-dimensional complex shear modulus imaging of soft tissues by integration of Algebraic Helmoltz Inversion and LMS filter into dealing with noisy data: a simulation study, Math. Biosci. Eng., 17 (2020), 404-417. doi: 10.3934/mbe.2020022
[49]	P. Zhou, Y. Zhang, Y. Yu, W. Cai, G. Zhou, 3D shape measurement based on structured light field imaging, Math. Biosci. Eng., 17(2020), 654-668. doi: 10.3934/mbe.2020034
[50]	X. Deng, Y. Liu, H. Chen, Three-dimensional image reconstruction based on improved U-net network for anatomy of pulmonary segmentectomy, Math. Biosci. Eng., 18 (2021), 3313-3322. doi: 10.3934/mbe.2021165

Reader Comments

Your name:*

Email:*
© 2021 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)