Abstract

In ultrasound B-mode imaging, speckle noises decreases the accuracy of estimation of tissue echogenicity of imaging targets from the amplitude of the echo signals. In addition, since the granular size of the speckle pattern is affected by the point spread function (PSF) of the image system, the resolution of B-mode image remains limited, and the boundaries of tissue structures often become blurred. This study proposed a convolutional neural network (CNN) to remove speckle noises together with improvement of image spatial resolution to reconstruct ultrasound tissue echogenicity map. Results indicate that the proposed CNN method can effectively eliminate the speckle noises in the background of the B-mode images while retaining the contours and edges of the tissue structures. The contrast and the contrast-to-noise ratio of the reconstructed echogenicity map increase from 0.22/2.72 to 0.33/44.14 and the lateral and axial resolutions also improve from 5.9/2.4 to 2.9/2.0, respectively. Compared with other post-processing filtering methods, the proposed CNN method provides better approximation to the original tissue echogenicity by completely removing speckle noises and improving the image resolution.

Highlights

  • Medical ultrasound imaging relies on the coherent summation of echoes from randomly distributed scatterers whose sizes are smaller than the acoustic wavelength

  • We found that the reconstruction task can be optimized only if the point spread function (PSF) size of training dataset is set according to that of test image

  • The model trained by the mixed loss function can reconstruct clearer echogenicity maps than using mean square error (MSE) loss

Read more

Summary

Introduction

Medical ultrasound imaging relies on the coherent summation of echoes from randomly distributed scatterers whose sizes are smaller than the acoustic wavelength. When the number of random scatterers within a sample volume is high enough, both the real and imaginary part of the stochastically interfered echoes will comply with normal distribution. The amplitude of echoes becomes Rayleigh distributed and the resultant B-mode image suffers from granular patterns, which are called speckle noises. Due to the nature of Rayleigh distribution, speckle noise is inherently multiplicative. The presence of speckle noise decreases the accuracy of estimation of tissue echogenicity from amplitude of echo signal. B-mode imaging can be modeled as the convolution of the point spread function (PSF) of imaging system and the tissue echogenicity map with Rayleigh randomization [1]

Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.