Classification for liver ultrasound tomography by posterior attenuation correction with a phantom study

Abstract

The B-mode ultrasound usually contains scattering speckle noise which reduces the detailed resolution of the target and is regarded as an intrinsic noise that interferes with diagnostic precision. The aim of this study was to classify hepatic steatosis through applying attenuation correction with a phantom to reduce speckle noise in liver ultrasound tomography in patients. This retrospective study applied three randomized groups signifying different liver statuses. A total of 114 patients’ effective liver ultrasound images—30 normal, 44 fatty, and 40 cancerous—were included. The proposed depth attenuation correction method was first applied to images. Three regions of interest were manually drawn on the images. Next, five feature values for the regions of interest were calculated. Finally, the hybrid method of logistic regression and support vector machine was employed to classify the ultrasound images with 10-fold cross-validation. The accuracy, kappa statistic, and mean absolute error of the proposed hybrid method were 87.5%, 0.812, and 0.119, respectively, which were higher than those of the logistic regression method—75.0%, 0.548, and 0.280—or those of the support vector machine method—75.7%, 0.637, and 0.293—respectively. Therefore, the hybrid method has been proven to be more accurate and have better performance and less error than either single method. The hybrid method provided acceptable accuracy of classification in three liver ultrasound image groups after depth attenuation correction. In the future, the deep learning approaches may be considered for the application in classifying liver ultrasound images.

Keywords

Ultrasound tomography attenuation correction logistic regression support vector machine

Get full access to this article

View all access options for this article.

References

Hyun

Brickson

Looby

et al. Beamforming and speckle reduction using neural networks. IEEE Trans Ultrason Ferroelectr Freq Control 2019; 66: 898–910.

Acton

. Speckle reducing anisotropic diffusion. IEEE Trans Imag Process 2002; 11(11): 1260–1270.

Aja-Fernandez

Alberola-Lopez

. On the estimation of the coefficient of variation for anisotropic diffusion speckle filtering. IEEE Trans Imag Process 2006; 15(9): 2694–2701.

Yue

Croitoru

Bidani

et al. Nonlinear multiscale wavelet diffusion for speckle suppression and edge enhancement in ultrasound images. IEEE Trans Med Imag 2006; 25(3): 297–311.

Khare

Jeong

et al. Despeckling of medical ultrasound images using Daubechies complex wavelet transform. Sig Process 2010; 90(2): 428–439.

Tay

Garson

Acton

et al. Ultrasound despeckling for contrast enhancement. IEEE Trans Imag Process 2010; 19(7): 1847–1860.

Kervrann

Boulanger

Coupe

. Bayesian non-local means filter, image redundancy and adaptive dictionaries for noise removal. In: SSVM ’07 Proceedings of the 1st international conference on Scale space and variational methods in computer vision, Ischia, Italy, 30 May–2 June 2007, pp.520–532. New York: ACM.

Coupe

Hellier

Kervrann

et al. Nonlocal means-based speckle filtering for ultrasound images. IEEE Trans Imag Process 2009; 18(10): 2221–2229.

Breivik

Snare

Steen

et al. Real-time nonlocal means-based despeckling. IEEE Trans Ultrason Ferroelect Freq Control 2017; 64(6): 959–977.

10.

Owjimehr

Danyali

Helfroush

. An improved method for liver diseases detection by ultrasound image analysis. J Med Signals Sens 2015; 5(1): 21–29.

11.

Acharya

Raghavendra

Fujita

et al. Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images. Comput Biol Med 2016; 79: 250–258.

12.

Acharya

Faust

Molinari

et al. Ultrasound-based tissue characterization and classification of fatty liver disease: a screening and diagnostic paradigm. Knowled based Syst 2015; 75: 66–77.

13.

Acharya

Fujita

Bhat

et al. Decision support system for fatty liver disease using GIST descriptors extracted from ultrasound images. Inform Fus 2016; 29: 32–39.

14.

Minhas

Sabih

Hussain

. Automated classification of liver disorders using ultrasound images. J Med Syst 2012; 36(5): 3163–3172.

15.

Andrade

Silva

Santos

et al. Classifier approaches for liver steatosis using ultrasound images Andreia. Proc Technol 2012; 5: 763–770.

16.

Singh

Gupta

. An information fusion based method for liver classification using texture analysis of ultrasound images. Inform Fus 2014; 19: 91–96.

17.

Owjimehr

Danyali

Helfroush

. An improved method for liver diseases detection by ultrasound image analysis. J Med Signals Sens 2015; 5(1): 21–29.

18.

Acharya

Raghavendra

Koh

JEW

et al. Automated detection and classification of liver fibrosis stages using contourlet transform and nonlinear features. Comput Methods Program Biomed 2018; 166: 91–98.

19.

Byra

Styczynski

Szmigielski

et al. Transfer learning with deep convolutional neural network for liver steatosis assessment in ultrasound images. Int J Comput Assist Radiol Surg 2018; 13(12): 1895–1903.

20.

Biswas

Kuppili

Edla

et al. Symtosis: a liver ultrasound tissue characterization and risk stratification in optimized deep learning paradigm. Comput Methods Program Biomed 2018; 155: 165–177.