Speckle Noise In Ultrasound Images Research Articles

Real-time volume rendering for three-dimensional fetal ultrasound using volumetric photon mapping

Three-dimensional (3D) fetal ultrasound has been widely used in prenatal examinations. Realistic and real-time volumetric ultrasound volume rendering can enhance the effectiveness of diagnoses and assist obstetricians and pregnant mothers in communicating. However, this remains a challenging task because (1) there is a large amount of speckle noise in ultrasound images and (2) ultrasound images usually have low contrasts, making it difficult to distinguish different tissues and organs. However, traditional local-illumination-based methods do not achieve satisfactory results. This real-time requirement makes the task increasingly challenging. This study presents a novel real-time volume-rendering method equipped with a global illumination model for 3D fetal ultrasound visualization. This method can render direct illumination and indirect illumination separately by calculating single scattering and multiple scattering radiances, respectively. The indirect illumination effect was simulated using volumetric photon mapping. Calculating each photon’s brightness is proposed using a novel screen-space destiny estimation to avoid complicated storage structures and accelerate computation. This study proposes a high dynamic range approach to address the issue of fetal skin with a dynamic range exceeding that of the display device. Experiments show that our technology, compared to conventional methodologies, can generate realistic rendering results with far more depth information.

Performance Evaluation of Ultrasound Images Using Non-Local Means Algorithm with Adaptive Isotropic Search Window for Improved Detection of Salivary Gland Diseases: A Pilot Study.

Speckle noise in ultrasound images (UIs) significantly reduces the accuracy of disease diagnosis. The aim of this study was to quantitatively evaluate its feasibility in salivary gland ultrasound imaging by modeling the adaptive non-local means (NLM) algorithm. UIs were obtained using an open-source device provided by SonoSkills and FUJIFILM Healthcare Europe. The adaptive NLM algorithm automates optimization by modeling the isotropic search window, eliminating the need for manual configuration in conventional NLM methods. The coefficient of variation (COV), contrast-to-noise ratio (CNR), and edge rise distance (ERD) were used as quantitative evaluation parameters. UIs of the salivary glands revealed evident visualization of the internal echo shape of the malignant tumor and calcification line using the adaptive NLM algorithm. Improved COV and CNR results (approximately 4.62 and 2.15 times, respectively) compared with noisy images were achieved. Additionally, when the adaptive NLM algorithm was applied to the UIs of patients with salivary gland sialolithiasis, the noisy images and ERD values were calculated almost similarly. In conclusion, this study demonstrated the applicability of the adaptive NLM algorithm in optimizing search window parameters for salivary gland UIs.

Coupling speckle noise suppression with image classification for deep-learning-aided ultrasound diagnosis

Objective. During deep-learning-aided (DL-aided) ultrasound (US) diagnosis, US image classification is a foundational task. Due to the existence of serious speckle noise in US images, the performance of DL models may be degraded. Pre-denoising US images before their use in DL models is usually a logical choice. However, our investigation suggests that pre-speckle-denoising is not consistently advantageous. Furthermore, due to the decoupling of speckle denoising from the subsequent DL classification, investing intensive time in parameter tuning is inevitable to attain the optimal denoising parameters for various datasets and DL models. Pre-denoising will also add extra complexity to the classification task and make it no longer end-to-end. Approach. In this work, we propose a multi-scale high-frequency-based feature augmentation (MSHFFA) module that couples feature augmentation and speckle noise suppression with specific DL models, preserving an end-to-end fashion. In MSHFFA, the input US image is first decomposed to multi-scale low-frequency and high-frequency components (LFC and HFC) with discrete wavelet transform. Then, multi-scale augmentation maps are obtained by computing the correlation between LFC and HFC. Last, the original DL model features are augmented with multi-scale augmentation maps. Main results. On two public US datasets, all six renowned DL models exhibited enhanced F1-scores compared with their original versions (by 1.31%–8.17% on the POCUS dataset and 0.46%–3.89% on the BLU dataset) after using the MSHFFA module, with only approximately 1% increase in model parameter count. Significance. The proposed MSHFFA has broad applicability and commendable efficiency and thus can be used to enhance the performance of DL-aided US diagnosis. The codes are available at https://github.com/ResonWang/MSHFFA.

Synthesizing Real-Time Ultrasound Images of Muscle Based on Biomechanical Simulation and Conditional Diffusion Network.

Quantitative muscle function analysis based on the ultrasound imaging, has been used for various applications, particularly with recent development of deep learning methods. The nature of speckle noises in ultrasound images poses challenges to accurate and reliable data annotation for supervised learning algorithms. To obtain a large and reliable dataset without manual scanning and labelling, we proposed a synthesizing pipeline to provide synthetic ultrasound datasets of muscle movement with an accurate ground truth, allowing augmenting, training, and evaluating models for different tasks. Our pipeline contained biomechanical simulation using finite element method, an algorithm for reconstructing sparse fascicles, and a diffusion network for ultrasound image generation. With the adjustment of a few parameters, the proposed pipeline can generate a large dataset of real-time ultrasound images with diversity in morphology and pattern. With 3,030 ultrasound images generated, we qualitatively and quantitatively verified that the synthetic images closely matched with the in-vivo images. In addition, we applied the synthetic dataset into different tasks of muscle analysis. Compared to trained on an unaugmented dataset, model trained on synthetic one had better cross-dataset performance, which demonstrates the feasibility of synthesizing pipeline to augment model training and avoid over-fitting. The results of the regression task show potentials under the conditions that the number of datasets or the accurate label are limited. The proposed synthesizing pipeline can not only be used for muscle-related study, but for other similar study and model development, where sequential images are needed for training.

A New Fractional-order Derivative-based Nonlinear Anisotropic Diffusion Model for Biomedical Imaging

Medical imaging, the process of visual representation of different organs and tissues of the human body, is employed for monitoring the normal as well as abnormal anatomy and physiology of the body. Imaging which can provide healthcare solutions ensuring a regular measurement of various complex diseases plays a critical role in the diagnosis and management of many complex diseases and medical conditions, and the quality of a medical image, which is not a single factor but a composite of contrast, artifacts, distortion, noise, blur, and so forth, depends on several factors such as the characteristics of the equipment, the imaging method in question as well as the imaging variables chosen by the operator. The medical images (ultrasound image, X-rays, CT scans, MRIs, etc.) may lose significant features and become degraded due to the emergence of noise as a result of which the process of improvement pertaining to medical images has become a thought-provoking area of inquiry with challenges related to detecting the speckle noise in the images and finding the applicable solution in a timely manner. The partial differential equations (PDEs), in this sense, can be used extensively in different aspects with regard to image processing ranging from filtering to restoration, segmentation to edge enhancement and detection, denoising in particular, among the other ones. In this research paper, we present a conformable fractional derivative-based anisotropic diffusion model for removing speckle noise in ultrasound images. The proposed model providing to be efficient in reducing noise by preserving the essential image features like edges, corners and other sharp structures for ultrasound images in comparison to the classical anisotropic diffusion model. Furthermore, we aim at proving the viscosity solution of the fractional diffusion model. The finite difference method is used to discretize the fractional diffusion model and classical diffusion models. The peak signal-to-noise ratio (PSNR) is used for the quality of the smooth images. The comparative experimental results corroborate that the proposed, developed and extended mathematical model is capable of denoising and preserving the significant features in ultrasound towards better accuracy, precision and examination within the framework of biomedical imaging and other related medical, clinical, and image-signal related applied as well as computational processes.

BSMNet: Boundary-salience multi-branch network for intima-media identification in carotid ultrasound images

Carotid artery intima-media thickness (CIMT) is an essential factor in signaling the risk of cardiovascular diseases, which is commonly evaluated using ultrasound imaging. However, automatic intima-media segmentation and thickness measurement are still challenging due to the boundary ambiguity of intima-media and inherent speckle noises in ultrasound images. In this work, we propose an end-to-end boundary-salience multi-branch network, BSMNet, to tackle the carotid intima-media identification from ultrasound images, where the prior shape knowledge and anatomical dependence are exploited using a parallel linear structure learning modules followed by a boundary refinement module. Moreover, we design a strip attention model to boost the thin strip region segmentation with shape priors, in which an anisotropic kernel shape captures long-range global relations and scrutinizes meaningful local salient contexts simultaneously. Extensive experimental results on an in-house carotid ultrasound (US) dataset demonstrate the promising performance of our method, which achieves about 0.02 improvement in Dice and HD95 than other state-of-the-art methods. Our method is promising in advancing the analysis of systemic arterial disease with ultrasound imaging.

Non-local adaptive hysteresis despeckling approach for medical ultrasound images

Speckle noise is a major problem in medical ultrasound imaging that reduces the image quality and leads to a negative impact on further diagnosis. In this paper, aiming to alleviate the effect of speckle, a new ultrasound image noise reduction approach called Non-local Adaptive Hysteresis Despeckling is proposed, which effectively exploits data redundancy not only for suppression of speckle noise but also for preserving meaningful structural details in ultrasound images. Since Hysteresis smoothing-based filters are initially introduced to eliminate additive white Gaussian noise, we attempt to adapt this category of filters to the signal-dependent and multiplicative nature of speckle noise in ultrasound images. Furthermore, the local functionality of Hysteresis smoothing-based filters, which is a limitation of their effectiveness, is addressed by proposing more efficient non-local weighting and averaging schemes to be more compatible with the speckle noise model. The qualitative and quantitative evaluations of the simulated and real clinical ultrasound images show that the proposed method can outperform other state-of-the-art methods.

RobustDespeckling: Robust speckle noise reduction method using multi-scale and kernel fisher discriminant analysis

In medical ultrasound imaging, speckle noise is an important property since it usually involves worsening the image resolution along with contrast, thus reducing the diagnostic significance of the imaging modality. The "RobustDespeckling" method, which has been proposed in this study to reduce speckle noise, involves extracting the noise-only signal from the image signal through applying the bidimesional empirical mode decomposition (BEMD) method and wavelet transform (WT) in the encapsulated way. Then, wavelet coefficients are thresholded to filter the noisy coefficients by an optimal threshold parameter that is estimated from kernel fisher discriminant analysis (KFDA). Finally, BEMD and WT processes are employed to obtain a de-noised image. The investigation is conducted by way of upsampling and downsampling operations of ultrasound images to analyze the efficiency of different de-noising techniques including the proposed “RobustDespeckling” method. The visual observation and statistical analysis signify that the “RobustDespeckling” method is robust in minimizing the speckle noise of ultrasound images over existing de-noising techniques. Consequently, the method is more competent to preserve the clarity of the edge without losing the significant image detail.

Speckle Reduction via Deep Content-Aware Image Prior for Precise Breast Tumor Segmentation in an Ultrasound Image.

The performance of computer-aided diagnosis (CAD) systems that are based on ultrasound imaging has been enhanced owing to the advancement in deep learning. However, because of the inherent speckle noise in ultrasound images, the ambiguous boundaries of lesions deteriorate and are difficult to distinguish, resulting in the performance degradation of CAD. Although several methods have been proposed to reduce speckle noise over decades, this task remains a challenge that must be improved to enhance the performance of CAD. In this article, we propose a deep content-aware image prior (DCAIP) with a content-aware attention module (CAAM) for superior despeckling of ultrasound images without clean images. For the image prior, we developed a CAAM to deal with the content information in an input image. In this module, super-pixel pooling (SPP) is used to give attention to salient regions in an ultrasound image. Therefore, it can provide more content information regarding the input image when compared to other attention modules. The DCAIP consists of deep learning networks based on this attention module. The DCAIP is validated by applying it as a preprocessing step for breast tumor segmentation in ultrasound images, which is one of the tasks in CAD. Our method improved the segmentation performance by 15.89% in terms of the area under the precision-recall (PR) curve (AUPRC). The results demonstrate that our method enhances the quality of ultrasound images by effectively reducing speckle noise while preserving important information in the image, promising for the design of superior CAD systems.

RED-MAM: A residual encoder-decoder network based on multi-attention fusion for ultrasound image denoising

The dependence of speckle noise in ultrasound images on image data makes the research of ultrasound image denoising tasks a great challenge. Several deep learning-based ultrasound image denoising methods have been proposed, but almost all of them suffer from the inability to focus on the importance of feature information on multiple domains at the same time. Therefore, this paper proposes a residual encoder-decoder based on multi-attention fusion attention module (RED-MAM) for ultrasound image denoising, which consists of five convolution layers, five deconvolution layers and two multi-attention fusion attention blocks. In order to make the denoising model better adapted to the properties of speckle noise, a multi-attention fusion attention block is constructed by several different attention modules. The multi-attention fusion attention block is introduced into the residual encoder-decoder denoising network to make the model focus on the ultrasound image texture structure information on multiple domains, thus enhancing the denoising effect of the model on ultrasound images. The performance of our proposed model is evaluated on three ultrasound image datasets. In terms of quantitative metrics, RED-MAM shows substantial improvement in Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM) and Root Mean Square Error (RMSE). The qualitative results show that RED-MAM has significantly improved denoising performance and has good results in noise suppression as well as structure retention. Our method achieves state-of-the-art performance on all three ultrasound datasets.

Automatic segmentation of ovarian follicles using deep neural network combined with edge information.

Medical ultrasound imaging plays an important role in computer-aided diagnosis systems. In many cases, it is the preferred method of doctors for diagnosing diseases. Combined with computer vision technology, segmentation of ovarian ultrasound images can help doctors accurately judge diseases, reduce doctors' workload, and improve doctors' work efficiency. However, accurate segmentation of an ovarian ultrasound image is a challenging task. On the one hand, there is a lot of speckle noise in ultrasound images; on the other hand, the edges of objects are blurred in ultrasound images. In order to segment the target accurately, we propose an ovarian follicles segmentation network combined with edge information. By adding an edge detection branch at the end of the network and taking the edge detection results as one of the losses of the network, we can accurately segment the ovarian follicles in an ultrasound image, making the segmentation results finer on the edge. Experiments show that the proposed network improves the segmentation accuracy of ovarian follicles, and that it has advantages over current algorithms.

An adaptive total generalized variational model for speckle reduction in ultrasound images

In this paper, we propose an adaptive total generalized variation model for removing the speckle noise in ultrasound image. The existence and uniqueness of the minimizers to the proposed model are established. Furthermore, we design an alternating minimization algorithm to solve numerically the model. By incorporating the generalized cross validation technique, the regularization parameter of the model can be updated during the iterations of the designed algorithm. Finally, experimental results are reported to demonstrate the effectiveness of the proposed method, and its performance is competitive with that of the other testing methods.

WUnet: A new network used for ultrasonic tongue contour extraction

Ultrasound imaging is becoming a practical tool in silent speech recognition. It is a challenge to accurately extract tongue contours due to the soft tissue characteristics of the tongue and the high level of speckle noise in ultrasound images. Based on the U-Net network, an improved network called wUnet is proposed to extract the contour of the ultrasonic tongue. First, upward interlevel jump connections are added to the coding network to extract sufficient tongue contour features at different levels to learn more coarse-grained information. Second, downward interlevel jump connections are added to the decoding network to have richer fine-grained semantics and more obvious image reconstruction effects in the information fusion stage. Finally, VGG16 convolutional blocks with a different number of layers are added between the two interlevel connections, and an end-to-end multilevel context encoder is jointly trained. The binary-cross entropy, IoU, and Dice coefficients are fused to form a composite function to calculate the network loss, which accelerates the process of determining the contour boundary. Extensive experiments on the NS, TJU, and TIMIT datasets show that the proposed approach yields a better extraction result on ultrasonic tongue contour than the baseline models.

A novel optimised method for speckle reduction in medical ultrasound images

The advancement of medical imaging techniques evolving from X-ray to PET images and the medical image analysis helped medical experts to detect, diagnose and offer treatments for complex disorders and deadly diseases in the human body. Among the various modalities used, Ultrasound imaging is the most widely accepted modality because of its affordability, non-invasive nature and various other features. But the presence of speckle noise in ultrasound image lowers the image quality and reduces diagnostic value. This article states an improved hybrid speckle noise reduction method, a combined application of Kuan and non-local means filters. In this method, Kuan filter is used to sharpen the edges and thereafter the speckle noise elimination is done by using the non-local means. In addition, the performance of the proposed hybrid filter and its design parameters are optimised by using a meta-heuristic called grey wolf optimiser. The performance of hybrid method is evaluated by analysing a chosen set of well-known post filtering methods used for speckle reduction with given ultrasound B-mode images. The comparison of test results using remarkable performance metrics and computation time demonstrate that the hybrid method can be used as the efficient speckle reduction method for image analysis.

Experimental evaluation of filters used for removing speckle noise and enhancing ultrasound image quality

In the modern-days diagnostics, ultrasound is considered a significant non-invasive imaging technique. However, ultrasound images are frequently contaminated by multiplicative speckle noise. Speckle noise is produced by constructive and destructive interference between ultrasound waves when the object being measured is smaller than the wavelength of the beam. The removal of speckle noise in ultrasound images is possible by using various filters. The current experimental study is aimed at finding the most suitable de-speckling filters for enhancing ultrasound images. The present study involves 102-abdomen ultrasound images degraded by speckle noise and the analysis of eight de-speckling filters (i.e., Mean, Median, Kuan, Lee, Frost, Adaptive Homomorphic, Wiener and Anisotropic Diffusion) is developed to find the optimum de-speckling filter. The results of the given filters are analyzed using the five quality metrics (i.e., PSNR, RMSE, SSI, STM, and SSIM). The metrics are further investigated by using the statistical tests (i.e., one-way ANOVA and Tukey’s post hoc test) to support the experimental evaluation. Simulation results showed that the Frost and adaptive Homomorphic filters work well for the ultrasound images degraded with higher value of speckle noise. From the proposed research, it is easy to select the optimal filter, which helps doctors to get fine details of the image.

Region-aware Global Context Modeling for Automatic Nerve Segmentation from Ultrasound Images

We present a novel deep learning model equipped with a new region-aware global context modeling technique for automatic nerve segmentation from ultrasound images, which is a challenging task due to (1) the large variation and blurred boundaries of targets, (2) the large amount of speckle noise in ultrasound images, and (3) the inherent real-time requirement of this task. It is essential to efficiently capture long-range dependencies by global context modeling for a segmentation network to overcome these challenges. Traditional global context modeling techniques usually explore pixel-aware correlations to establish long-range dependencies, which are usually computation-intensive and greatly degrade time performance. In addition, in this application, pixel-aware modeling may inevitably introduce much speckle noise in the computation and potentially degrade segmentation performance. In this paper, we propose a novel region-aware modeling technique to establish long-range dependencies based on different regions to improve segmentation accuracy while maintaining real-time performance; we call it region-aware pyramid aggregation (RPA) module. In order to adaptively divide the feature maps into a set of semantic-independent regions, we develop an attention mechanism and integrate it into the spatial pyramid network to evaluate the semantic similarity of different regions. We further develop an adaptive pyramid fusion (APF) module to dynamically fuse the multi-level features generated from the decoder to refining the segmentation results. We conducted extensive experiments on a famous public ultrasound nerve image segmentation dataset. Experimental results demonstrate that our method consistently outperforms our rivals in terms of segmentation accuracy. The code is available at https://github.com/jsonliu-szu/RAGCM.

Ultrasound liver tumor segmentation with nested U-Net and dynamic feature extraction

Locating tumor from ultrasound images is of high importance in medical analysis and diagnosis. There are mainly two challenges for segmenting tumors from ultrasound images. The first challenge is the low resolution and high speckle noise of ultrasound images. The second challenge is the various shapes and sizes of tumors. We propose a multi-level feature extraction neural network to automatically segment the data. Our purposed model is trained and tested with liver tumor ultrasound images from an open source dataset. Specifically, after pre-processing the dataset with median filter and data augmentation, we employ a collaborative model that utilizes nested U-net, U-Net + + as a backbone. The model is integrated with dense short skip connections within sub-networks to further improve the gradient flow and feature preservation. In addition, we modify the original atrous spacial pyramid to an adaptive pooling for better compatibility with nested U-Net. Adaptive atrous spacial pyramid pooling is designed to extract features from different levels and cover the increasing range of feature extraction with regard to the depth of the nested network. Segmentation results showed that the proposed model outperformed multiple network structures, and achieved a 0.915 3 dice coefficient, 0.843 8 intersection-over-union and 0.0019 mean square error.

Analysis of the Effect of Intraocular Lens Implantation on Retinal Nerve and Postoperative Nursing Outcome Based on Ultrasound Imaging

Traumatic cataract is a common complication of ocular contusion. Caused by various forms of trauma, the course and prognosis of traumatic cataract are also different. Intraocular lens (IOL) implantation is the most effective treatment at the present time and can provide good visual quality and near, medium, and far vision. In this study, an adaptive medical ultrasound image denoising algorithm was constructed based on the biological vision mechanism and was applied to observe IOL implantation and postoperative care of 30 patients with traumatic cataract. Results showed that eyesight could be restored to the original healthy state after IOL implantation, and eyesight was close to normal 3 months after surgery. The corresponding noise pixel block of the noise reduction algorithm was obviously the lowest. A total of 30 patients (9 patients with contusion, 13 patients with intraocular foreign body, and 8 patients with perforation) were treated with aspheric and multifocal IOL to achieve the expected outcome. The noise reduction algorithm constructed in this study effectively reduced the speckle noise of ultrasound images, improved the clarity of ultrasound images, and achieved the effective observation of medical nursing outcome after traumatic cataract IOL implantation. After IOL implantation, the retinal nerves of patients with traumatic cataract were affected to different degrees.

Speckle Noise Removal by Energy Models with New Regularization Setting

In this paper, we introduce two novel total variation models to deal with speckle noise in ultrasound image in order to retain the fine details more effectively and to improve the speed of energy diffusion during the process. Firstly, two new convex functions are introduced as regularization term in the adaptive total variation model, and then, the diffusion performances of Hypersurface Total Variation (HYPTV) model and Logarithmic Total Variation (LOGTV) model are analyzed mathematically through the physical characteristics of local coordinates. We have shown that the larger positive parameter in the model is set, the greater energy diffusion speed appears to be, but it will cause the image to be too smooth that required adequate attention. Numerical experimental results show that our proposed LOGTV model for speckle noise removal is superior to traditional models, not only in visual effect but also in quantitative measures.

Despeckling of clinical ultrasound images using deep residual learning

Background and objectiveUltrasound is the non-radioactive imaging modality used in the diagnosis of various diseases related to the internal organs of the body. The presence of speckle noise in ultrasound image (UI) is inevitable and may affect resolution and contrast of the image. Existence of the speckle noise degrades the visual evaluation of the image. The despeckling of UI is a desirable pre-processing step in computer-aided UI based diagnosis systems.MethodsThis paper proposes a novel method for despeckling UIs using pre-trained residual learning network (RLN). Initially, RLN is trained with pristine and its corresponding noisy images in order to achieve a better performance. The developed method chooses a pre-trained RLN for despeckling UIs with less computational resources. But the training procedure of RLN from scratch is computationally demanding. The pre-trained RLN is a blind despeckling approach and does not require any fine tuning and noise level estimation. The presented approach shows superiority in the removal of speckle noise as compared to the existing state-of-art methods.ResultsTo highlight the effectiveness of the proposed method the pristine images from the Waterloo dataset has been considered. The proposed pre-trained RLN based UI despeckling method resulted in a better peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM) at different speckle noise levels. The no-reference image quality approach is adopted to ensure robustness of the established method for real time UI. From results it is obvious that, the performance of the proposed method is superior than the existing methods in terms of naturalness image quality evaluator (NIQE).ConclusionsFrom the experimental results, it is clear that the proposed method outperforms the existing despeckling methods in terms of both artificially added and naturally occurring speckle images.