Gabor-based anisotropic diffusion for speckle noise reduction in medical ultrasonography

3-D Gabor-based anisotropic diffusion for speckle noise suppression in dynamic ultrasound images

Speckle noise contaminates medical ultrasound images, and the suppression of speckle noise is helpful for image interpretation. Traditional ultrasound denoising (i.e., despeckling) methods are developed on two-dimensional static images. However, one of the advantages of ultrasonography is its nature of dynamic imaging. A method for dynamic ultrasound despeckling is expected to incorporate both the spatial and temporal information in successive images of dynamic ultrasound and thus yield better denoising performance. Here we regard a dynamic ultrasound video as three-dimensional (3-D) images with two dimensions in the spatial domain and one in the temporal domain, and we propose a despeckling algorithm for dynamic ultrasound named the 3-D Gabor-based anisotropic diffusion (GAD-3D). The GAD-3D expands the classic two-dimensional Gabor-based anisotropic diffusion (GAD) into 3-D domain. First, we proposed a robust 3-D Gabor-based edge detector by capturing the edge with 3-D Gabor transformation. Then we embed this novel detector into the partial differential equation of GAD to guide the 3-D diffusion process. In the simulation experiment, when the noise variance is as high as 0.14, the GAD-3D improves the Pratt's figure of merit, mean structural similarity index and peak signal-to-noise ratio by 24.32%, 10.98%, and 6.51%, respectively, compared with the best values of seven other methods. Experimental results on clinical dynamic ultrasonography suggest that the GAD-3D outperforms the other seven methods in noise reduction and detail preservation. The GAD-3D is effective for dynamic ultrasound despeckling and may be potentially valuable for disease assessment in dynamic medical ultrasonography.

Dual-mode artificially-intelligent diagnosis of breast tumours in shear-wave elastography and B-mode ultrasound using deep polynomial networks

The main goal of this study is to build an artificial intelligence (AI) architecture for automated extraction of dual-modal image features from both shear-wave elastography (SWE) and B-mode ultrasound, and to evaluate the AI architecture for classification between benign and malignant breast tumors. In this AI architecture, ultrasound images were segmented by the reaction diffusion level set model combined with the Gabor-based anisotropic diffusion algorithm. Then morphological features and texture features were extracted from SWE and B-mode ultrasound images at the contourlet domain. Finally, we employed a framework for feature learning and classification with the deep polynomial network (DPN) on dual-modal features to distinguish between malignant and benign breast tumors. With the leave-one-out cross validation, the DPN method on dual-modal features achieved a sensitivity of 97.8%, a specificity of 94.1%, an accuracy of 95.6%, a Youden's index of 91.9% and an area under the receiver operating characteristic curve of 0.961, which was superior to the classic single-modal methods, and the dual-modal methods using the principal component analysis and multiple kernel learning. These results have demonstrated that the dual-modal AI-based technique with DPN has the potential for breast tumor classification in future clinical practice.

Speckle reduction in laser projection displays through angle and wavelength diversity

Speckle is the main obstacle for the use of laser light sources in projection technology. This paper focuses on speckle suppression by the reduction of temporal coherence which is provided by the broadband laser light. The investigation of the effect of laser spectrum width and multiple lasers on speckle contrast is discussed. A broader spectrum width of the laser light is attained by the use of multiple semiconductor laser diodes of the broad area type. Measurements of speckle contrast with and without angle diversity are performed for two and four laser diodes. The measurement of speckle contrast for a single laser diode is also presented for comparison. The experimental results show that multiple laser diodes provide lower speckle contrast as compared to a single laser diode. In addition, it is also shown in this paper that the wavelength distribution of independent laser diodes has an effect on speckle contrast. Two different types of blue laser diodes, Nichia NUB802T and Nichia NUB801E, which have slightly different central wavelengths, were used for the measurements. Four laser diodes with a combination of two types of laser diodes offer better speckle contrast reduction than four laser diodes of the same type due to an effective broader spectrum. Additional speckle contrast reduction is achieved through the angle diversity by using a dynamic deformable mirror.

Intelligent speckle reducing anisotropic diffusion algorithm for automated 3-D ultrasound images

A novel 3-D filtering method is presented for speckle reduction and detail preservation in automated 3-D ultrasound images. First, texture features of an image are analyzed by using the improved quadtree (QT) decomposition. Then, the optimal homogeneous and the obvious heterogeneous regions are selected from QT decomposition results. Finally, diffusion parameters and diffusion process are automatically decided based on the properties of these two selected regions. The computing time needed for 2-D speckle reduction is very short. However, the computing time required for 3-D speckle reduction is often hundreds of times longer than 2-D speckle reduction. This may limit its potential application in practice. Because this new filter can adaptively adjust the time step of iteration, the computation time is reduced effectively. Both synthetic and real 3-D ultrasound images are used to evaluate the proposed filter. It is shown that this filter is superior to other methods in both practicality and efficiency.