Phase asymmetry ultrasound despeckling with fractional anisotropic diffusion and total variation

Low illumination fog noise image denoising method based on ACE-GPM

The Perona-Malik (P-M) model exhibits deficiencies such as noise amplification, new noise introduction, and significant gradient effects when processing noisy images. To address these issues, this paper proposes an image-denoising algorithm, ACE-GPM, which integrates an Automatic Color Equalization (ACE) algorithm with a gradient-adjusted P-M model. Initially, the ACE algorithm is employed to enhance the contrast of low-light images obscured by fog and noise. Subsequently, the Otsu method, a technique to find the optimal threshold based on between-class variance, is applied for precise segmentation, enabling more accurate identification of different regions within the image. After that, distinct gradients enhance the image's foreground and background via an enhancement function that accentuates edge and detailed information. The denoising process is finalized by applying the gradient P-M model, employing a gradient descent approach to further emphasize image edges and details. Experimental evidence indicates that the proposed ACE-GPM algorithm not only elevates image contrast and eliminates noise more effectively than other denoising methods but also preserves image details and texture information, evidenced by an average increase of 0.42 in the information entropy value. Moreover, the proposed solution achieves these outcomes with reduced computational resource expenditures while maintaining high image quality.

US-Net: A lightweight network for simultaneous speckle suppression and texture enhancement in ultrasound images

BACKGROUND

Numerous traditional filtering approaches and deep learning-based methods have been proposed to improve the quality of ultrasound (US) image data. However, their results tend to suffer from over-smoothing and loss of texture and fine details. Moreover, they perform poorly on images with different degradation levels and mainly focus on speckle reduction, even though texture and fine detail enhancement are of crucial importance in clinical diagnosis.

METHODS

We propose an end-to-end framework termed US-Net for simultaneous speckle suppression and texture enhancement in US images. The architecture of US-Net is inspired by U-Net, whereby a feature refinement attention block (FRAB) is introduced to enable an effective learning of multi-level and multi-contextual representative features. Specifically, FRAB aims to emphasize high-frequency image information, which helps boost the restoration and preservation of fine-grained and textural details. Furthermore, our proposed US-Net is trained essentially with real US image data, whereby real US images embedded with simulated multi-level speckle noise are used as an auxiliary training set.

RESULTS

Extensive quantitative and qualitative experiments indicate that although trained with only one US image data type, our proposed US-Net is capable of restoring images acquired from different body parts and scanning settings with different degradation levels, while exhibiting favorable performance against state-of-the-art image enhancement approaches. Furthermore, utilizing our proposed US-Net as a pre-processing stage for COVID-19 diagnosis results in a gain of 3.6% in diagnostic accuracy.

CONCLUSIONS

The proposed framework can help improve the accuracy of ultrasound diagnosis.

Comparative analysis of wavelet transform filtering systems for noise reduction in ultrasound images

Wavelet transform (WT) is a commonly used method for noise suppression and feature extraction from biomedical images. The selection of WT system settings significantly affects the efficiency of denoising procedure. This comparative study analyzed the efficacy of the proposed WT system on real 292 ultrasound images from several areas of interest. The study investigates the performance of the system for different scaling functions of two basic wavelet bases, Daubechies and Symlets, and their efficiency on images artificially corrupted by three kinds of noise. To evaluate our extensive analysis, we used objective metrics, namely structural similarity index (SSIM), correlation coefficient, mean squared error (MSE), peak signal-to-noise ratio (PSNR) and universal image quality index (Q-index). Moreover, this study includes clinical insights on selected filtration outcomes provided by clinical experts. The results show that the efficiency of the filtration strongly depends on the specific wavelet system setting, type of ultrasound data, and the noise present. The findings presented may provide a useful guideline for researchers, software developers, and clinical professionals to obtain high quality images.

Speckle Reduction in Ultrasound Images of the Common Carotid Artery Based on Integer and Fractional-Order Total Variation

Designing a technique with higher speckle noise suppressing capability, better edge preserving performance, and lower time complexity is a research objective for the common carotid artery (CCA) ultrasound despeckling. Total variation based techniques have been widely used in the image denoising and have good performance in preserving the edges in the images. However, the total variation based filters can produce the staircase artifacts. To address this issue, second-order total variation based techniques have been proposed for the image denoising. However, the previous study has been proved that the fractional differential model has better performance in reducing the speckles in ultrasound despeckling compared with the second-order model. Thus, to improve the performance of ultrasound despeckling and edge preserving, a novel despeckling model based on integer and fractional-order total variation (IFOTV) is proposed for CCA ultrasound images. Moreover, the minimization problems in our despeckling model are solved by the alternating direction method of multiplier (ADMM). In results with synthetic images, the edge preservation index (EPI) values of proposed method are 0.9524, 0.8797, and 0.7351 as well as 0.9137, 0.8253, and 0.6847 under three different levels of noise, which are the highest among four advanced methods. In results with simulated CCA ultrasound images, the speckle suppression and mean preservation indices of proposed method are 0.5596, 0.6571, and 0.8106 under three different levels of noise, which are the best among four advanced methods. In results with clinical images, the average absolute error of intima-media thickness measurements of proposed method is 0.0660 ± 0.0679 (mean ± std in mm), which is the lowest among four advanced methods. In conclusion, the IFOTV method has improved performance in suppressing the speckle noise and preserving the edge, and is thus a potential alternative to the current filters for the CCA ultrasound despeckling.

A Novel Speckle Suppression Method with Quantitative Combination of Total Variation and Anisotropic Diffusion PDE Model

Speckle noise seriously affects synthetic aperture radar (SAR) image application. Speckle suppression aims to smooth the homogenous region while preserving edge and texture in the image. A novel speckle suppression method based on the combination of total variation and partial differential equation denoising models is proposed in this paper. Taking full account of the local statistics in the image, a quantization technique—which is different from the normal edge detection method—is supported by the variation coefficient of the image. Accordingly, a quantizer is designed to respond to both noise level and edge strength. This quantizer automatically determines the threshold of diffusion coefficient and controls the weight between total variation filter and anisotropic diffusion partial differential equation filter. A series of experiments are conducted to test the performance of the quantizer and proposed filter. Extensive experimental results have demonstrated the superiority of the proposed method with both synthetic images and natural SAR images.

Despeckling and enhancement of ultrasound images using non-local variational framework

Speckles are introduced in the ultrasound data due to constructive and destructive interference of the probing signals that are used for capturing the characteristics of the tissue being imaged. There are a plethora of models discussed in the literature to improve the contrast and resolution of the ultrasound images by despeckling them. There is a class of models that assumes that the noise is multiplicative in its original form, and transforming the model to a log domain makes it an additive one. Nevertheless, such a transformation duly oversimplifies the scenario and does not capture the inherent properties of the data-correlated nature of speckles. Therefore, it results in poor reconstruction. This problem is addressed to a considerable extent in the subsequent works by adopting various models to address the data-correlated nature of the noise and its distributions. This work introduces a weberized non-local total bounded variational model based on the noise distribution built on the Retinex theory. This perceptually inspired model apparently restores and improves the contrast of the images without compromising much on the details inherently present in the data. The numerical implementation of the model is carried out using the Bregman formulation to improve the convergence rate and reduce the parameter sensitivity. The experimental results are highlighted and compared to demonstrate the efficiency of the model.

Sequential vessel segmentation via deep channel attention network

Accurately segmenting contrast-filled vessels from X-ray coronary angiography (XCA) image sequence is an essential step for the diagnosis and therapy of coronary artery disease. However, developing automatic vessel segmentation is particularly challenging due to the overlapping structures, low contrast and the presence of complex and dynamic background artifacts in XCA images. This paper develops a novel encoder-decoder deep network architecture which exploits the several contextual frames of 2D+t sequential images in a sliding window centered at current frame to segment 2D vessel masks from the current frame. The architecture is equipped with temporal-spatial feature extraction in encoder stage, feature fusion in skip connection layers and channel attention mechanism in decoder stage. In the encoder stage, a series of 3D convolutional layers are employed to hierarchically extract temporal-spatial features. Skip connection layers subsequently fuse the temporal-spatial feature maps and deliver them to the corresponding decoder stages. To efficiently discriminate vessel features from the complex and noisy backgrounds in the XCA images, the decoder stage effectively utilizes channel attention blocks to refine the intermediate feature maps from skip connection layers for subsequently decoding the refined features in 2D ways to produce the segmented vessel masks. Furthermore, Dice loss function is implemented to train the proposed deep network in order to tackle the class imbalance problem in the XCA data due to the wide distribution of complex background artifacts. Extensive experiments by comparing our method with other state-of-the-art algorithms demonstrate the proposed method's superior performance over other methods in terms of the quantitative metrics and visual validation. To facilitate the reproductive research in XCA community, we publicly release our dataset and source codes at https://github.com/Binjie-Qin/SVS-net.