Estimation of Ultrasound Echogenicity Map from B-Mode Images Using Convolutional Neural Network
In ultrasound B-mode imaging, speckle noises decrease the accuracy of estimation of tissue echogenicity of imaged 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 imaging system, the reso...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/17/4931 |
| _version_ | 1797555052794085376 |
|---|---|
| author | Che-Chou Shen Jui-En Yang |
| author_facet | Che-Chou Shen Jui-En Yang |
| author_sort | Che-Chou Shen |
| collection | DOAJ |
| description | In ultrasound B-mode imaging, speckle noises decrease the accuracy of estimation of tissue echogenicity of imaged 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 imaging 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. The CNN model is trained using in silico simulation dataset and tested with experimentally acquired images. 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 increased from 0.22/2.72 to 0.33/44.14, and the lateral and axial resolutions also improved 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 together with the capability for real-time implementation. |
| first_indexed | 2024-03-10T16:40:50Z |
| format | Article |
| id | doaj.art-70c74f6233a94adf9d1432e5b728d809 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T16:40:50Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-70c74f6233a94adf9d1432e5b728d8092023-11-20T12:01:08ZengMDPI AGSensors1424-82202020-08-012017493110.3390/s20174931Estimation of Ultrasound Echogenicity Map from B-Mode Images Using Convolutional Neural NetworkChe-Chou Shen0Jui-En Yang1Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei 10607, TaiwanDepartment of Electrical Engineering, National Taiwan University of Science and Technology, Taipei 10607, TaiwanIn ultrasound B-mode imaging, speckle noises decrease the accuracy of estimation of tissue echogenicity of imaged 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 imaging 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. The CNN model is trained using in silico simulation dataset and tested with experimentally acquired images. 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 increased from 0.22/2.72 to 0.33/44.14, and the lateral and axial resolutions also improved 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 together with the capability for real-time implementation.https://www.mdpi.com/1424-8220/20/17/4931tissue echogenicity mapspeckle reductionconvolutional neural networkimage resolutiondeconvolution |
| spellingShingle | Che-Chou Shen Jui-En Yang Estimation of Ultrasound Echogenicity Map from B-Mode Images Using Convolutional Neural Network Sensors tissue echogenicity map speckle reduction convolutional neural network image resolution deconvolution |
| title | Estimation of Ultrasound Echogenicity Map from B-Mode Images Using Convolutional Neural Network |
| title_full | Estimation of Ultrasound Echogenicity Map from B-Mode Images Using Convolutional Neural Network |
| title_fullStr | Estimation of Ultrasound Echogenicity Map from B-Mode Images Using Convolutional Neural Network |
| title_full_unstemmed | Estimation of Ultrasound Echogenicity Map from B-Mode Images Using Convolutional Neural Network |
| title_short | Estimation of Ultrasound Echogenicity Map from B-Mode Images Using Convolutional Neural Network |
| title_sort | estimation of ultrasound echogenicity map from b mode images using convolutional neural network |
| topic | tissue echogenicity map speckle reduction convolutional neural network image resolution deconvolution |
| url | https://www.mdpi.com/1424-8220/20/17/4931 |
| work_keys_str_mv | AT chechoushen estimationofultrasoundechogenicitymapfrombmodeimagesusingconvolutionalneuralnetwork AT juienyang estimationofultrasoundechogenicitymapfrombmodeimagesusingconvolutionalneuralnetwork |