Abstract
Ultrasound imaging has been widely used for clinical diagnosis. However, the inherent speckle noise will degrade the quality of ultrasound images. Existing despeckling methods cannot deliver sufficient speckle reduction and preserve image details well at high noise corruption and they cannot realize real-time ultrasound image denoising. With the popularity of deep learning, supervised learning for image denoising has recently attracted considerable attention. In this paper, we have proposed a novel residual UNet using mixed-attention mechanism (MARU) for real-time ultrasound image despeckling. In view of the signal-dependent characteristics of speckle noise, we have designed an encoder-decoder network to reconstruct the despeckled image by extracting features from the noisy image. Furthermore, a lightweight mixed-attention block is proposed to effectively enhance the image features and suppress some speckle noise during the encoding phase by using separation and re-fusion strategy for channel and spatial attention. Besides, we have graded the speckle noise levels with a certain interval and designed an algorithm to estimate the noise levels for despeckling real ultrasound images. Experiments have been done on the natural images, the synthetic image, the image simulated using Field II and the real ultrasound images. Compared with existing despeckling methods, the proposed network has achieved the state-of-the-art despeckling performance in terms of subjective human vision and such quantitative indexes as peak signal to noise ratio (PSNR), structural similarity (SSIM), equivalent number of looks (ENL) and contrast-to-noise ratio (CNR).
Highlights
Ultrasound imaging has become one popular medical imaging technology due to its non-invasive, inexpensive and realtime advantages
EXPERIMENTAL RESULTS To demonstrate the superiority of the proposed network in terms of despeckling performance, it will be compared with such traditional well-known despeckling algorithms as squeeze box filter (SBF), speckle reducing anisotropic diffusion filter (SRAD), optimized Bayesian non-local means (OBNLM) and PCA-non-local means (NLM) methods and such deep learning based methods as ID-convolutional neural network (CNN), deep CNN denoiser (DCNND) and denoising convolutional neural network (DnCNN)
In this paper, a novel convolutional neural network is proposed for real-time ultrasound image despeckling
Summary
Ultrasound imaging has become one popular medical imaging technology due to its non-invasive, inexpensive and realtime advantages. The presence of speckle noise reduces the resolution and contrast of the image, and adversely affects subsequent image processing and analysis tasks such as image segmentation, image registration, image feature extraction and recognition [2]. Speckle noise reduction from medical ultrasound images is highly important for improving image quality. The distribution of ultrasound speckle noise is signal dependent and is governed by Fisher-Tippett distribution [3] or. Where (x, y) is the pixel location, v(x, y) is the noise-free image, u(x, y) is the noisy image, η(x, y) is Gaussian noise distributed with zero-mean and variance σ2, and the factor γ is related to ultrasound devices and additional processing. Extensive studies indicate that γ = 0.5 can be used to model speckle noise in the ultrasound image [2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: 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.
