Ultrasonic Image Denoising Using Adaptive Bilateral Filtering Based on Back Propagation Neural Network

Xiaofang Zhu; Liang Jing; Dangguo Shao

doi:10.3788/LOP57.241014

Laser & Optoelectronics Progress, Volume. 57, Issue 24, 241014(2020)

Ultrasonic Image Denoising Using Adaptive Bilateral Filtering Based on Back Propagation Neural Network

Xiaofang Zhu, Liang Jing, and Dangguo Shao^*

Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, Yunnan 650500, China

show less

Abstract Get PDF(in Chinese)

Figures & Tables(10)

Fig. 1. Structural diagram of BP neural network

Download full size

Fig. 2. BP neural network based adaptive bilateral filtering model

Download full size

Fig. 3. Denoising results of physical phantom ultrasonic image. (a) Original image; (b) P-M model; (c) DPAD method; (d) DnCNN model ; (e) our method

Download full size

Fig. 4. Denoising results of liver ultrasonic image 1. (a) Original image; (b) P-M model; (c) DPAD method; (d) DnCNN model; (e) our method

Download full size

Fig. 5. Denoising results of liver ultrasonic image 2. (a) Original image; (b) P-M model; (c) DPAD method; (d) DnCNN model; (e) our method

Download full size

Fig. 6. Denoising results of kidney ultrasonic image. (a) Original image; (b) P-M model; (c) DPAD method; (d) DnCNN model; (e) our method

Download full size

Table 1. Objective analysis of denoising results of physical phantom ultrasonic image

View table

Table 1. Objective analysis of denoising results of physical phantom ultrasonic image

Image in figure 3	Image size /(pixel×pixel)	Window size	Iterations	SNR /dB	CNR /dB	upSNR	upCNR
(a)	507×243	--	--	3.842	3.951	--	--
(b)	507×243	3×3	100	21.128	20.367	449.920	415.490
(c)	507×243	3×3	100	27.429	27.080	613.930	585.400
(d)	507×243	--	--	37.737	36.843	795.487	778.818
(e)	507×243	9×9	10	33.261	32.870	765.720	731.940

Table 2. Objective analysis of denoising results of liver ultrasonic image 1

View table

Table 2. Objective analysis of denoising results of liver ultrasonic image 1

Image in figure 4	Image size /(pixel×pixel)	Window size	Iterations	SNR /dB	CNR /dB	upSNR	upCNR
(a)	512×741	--	--	4.905	4.492	--	--
(b)	512×741	3×3	100	20.802	19.383	324.10	331.50
(c)	512×741	3×3	100	19.025	18.176	287.87	304.63
(d)	512×741	--	--	28.540	27.089	481.86	503.05
(e)	512×741	9×9	10	25.713	25.067	424.22	458.04

Table 3. Objective analysis of denoising results of liver ultrasonic image 2

View table

Table 3. Objective analysis of denoising results of liver ultrasonic image 2

Image in figure 5	Image size /(pixel×pixel)	Window size	Iterations	SNR /dB	CNR /dB	upSNR	upCNR
(a)	715×901	--	--	5.418	3.302	--	--
(b)	715×901	3×3	100	18.476	15.573	241.00	371.62
(c)	715×901	3×3	100	20.157	17.652	272.04	434.59
(d)	715×901	--	--	24.230	20.865	347.21	531.89
(e)	715×901	9×9	10	23.458	19.069	332.96	477.50

Table 4. Objective analysis of denoising results of kidney ultrasonic image

View table

Table 4. Objective analysis of denoising results of kidney ultrasonic image

Image in figure 6	Image size /(pixel×pixel)	Window size	Iterations	SNR(dB)	CNR(dB)	upSNR	upCNR
(a)	446×519	--	--	7.013	6.676	--	--
(b)	446×519	3×3	100	21.713	20.148	209.61	201.80
(c)	446×519	3×3	100	22.073	21.251	214.74	218.32
(d)	446×519	--	--	30.154	28.563	329.97	327.85
(e)	446×519	9×9	10	28.734	27.528	309.72	312.34

Tools

Get Citation

Copy Citation Text

Xiaofang Zhu, Liang Jing, Dangguo Shao. Ultrasonic Image Denoising Using Adaptive Bilateral Filtering Based on Back Propagation Neural Network[J]. Laser & Optoelectronics Progress, 2020, 57(24): 241014

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Image Processing

Received: May. 6, 2020

Accepted: Jun. 17, 2020

Published Online: Nov. 23, 2020

The Author Email: Shao Dangguo (23014260@qq.com)

DOI:10.3788/LOP57.241014

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology