A novel approach to speckle reduction in ultrasound imaging

AdaRes: A deep learning-based model for ultrasound image denoising: Results of image quality metrics, radiomics, artificial intelligence, and clinical studies

PURPOSE

The quality of ultrasound images is degraded by speckle and Gaussian noises. This study aims to develop a deep-learning (DL)-based filter for ultrasound image denoising.

METHODS

A novel DL-based filter using adaptive residual (AdaRes) learning was proposed. Five image quality metrics (IQMs) and 27 radiomics features were used to evaluate denoising results. The effect of our proposed filter, AdaRes, on four pre-trained convolutional neural network (CNN) classification models and three radiologists was assessed.

RESULTS

AdaRes filter was tested on both natural and ultrasound image databases. IQMs results indicate that AdaRes could remove noises in three different noise levels with the highest performances. In addition, a radiomics study proved that AdaRes did not distort tissue textures and it could preserve most radiomics features. AdaRes could also improve the performance classification using CNNs in different settings. Finally, AdaRes also improved the mean overall performance (AUC) of three radiologists from 0.494 to 0.702 in the classification of benign and malignant lesions.

CONCLUSIONS

AdaRes filtered out noises on ultrasound images more effectively and can be used as an auxiliary preprocessing step in computer-aided diagnosis systems. Radiologists may use it to remove unwanted noises and improve the ultrasound image quality before the interpretation.

Histotripsy Bubble Cloud Contrast With Chirp-Coded Excitation in Preclinical Models

Histotripsy is a focused ultrasound therapy for tissue ablation via the generation of bubble clouds. These effects can be achieved noninvasively, making sensitive and specific bubble imaging essential for histotripsy guidance. Plane-wave ultrasound imaging can track bubble clouds with an excellent temporal resolution, but there is a significant reduction in echoes when deep-seated organs are targeted. Chirp-coded excitation uses wideband, long-duration imaging pulses to increase signals at depth and promote nonlinear bubble oscillations. In this study, we evaluated histotripsy bubble contrast with chirp-coded excitation in scattering gel phantoms and a subcutaneous mouse tumor model. A range of imaging pulse durations were tested, and compared to a standard plane-wave pulse sequence. Received chirped signals were processed with matched filters to highlight components associated with either fundamental or subharmonic (bubble-specific) frequency bands. The contrast-to-tissue ratio (CTR) was improved in scattering media for subharmonic contrast relative to fundamental contrast (both chirped and standard imaging pulses) with the longest-duration chirped-pulse tested (7.4 [Formula: see text] pulse duration). The CTR was improved for subharmonic contrast relative to fundamental contrast (both chirped and standard imaging pulses) by 4.25 dB ± 1.36 dB in phantoms and 3.84 dB ± 6.42 dB in vivo. No systematic changes were observed in the bubble cloud size or dissolution rate between sequences, indicating image resolution was maintained with the long-duration imaging pulses. Overall, this study demonstrates the feasibility of specific histotripsy bubble cloud visualization with chirp-coded excitation.

Speckle statistics of biological tissues in optical coherence tomography

The speckle statistics of optical coherence tomography images of biological tissue have been studied using several historical probability density functions. Here, we propose a new theoretical framework based on power-law functions, where we hypothesize that an underlying power-law distribution governs scattering from tissues. Thus, multi-scale scattering sites including the fractal branching vasculature will contribute to power-law probability distributions of speckle statistics. Specifically, these are the Burr type XII distribution for speckle amplitude, the Lomax distribution for intensity, and the generalized logistic distribution for log amplitude. Experimentally, these three distributions are fitted to histogram data from nine optical coherence tomography scans of various samples and biological tissues, in vivo and ex vivo. The distributions are also compared with classical models such as the Rayleigh, K, and gamma distributions. The results indicate that across OCT datasets of various tissue types, the proposed power-law distributions are more appropriate models yielding novel parameters for characterizing the physics of scattering from biological tissue. Thus, the overall framework brings to the field new biomarkers from OCT measures of speckle in tissues, grounded in basic biophysics and with wide applications to diagnostic imaging in clinical use.

A Novel Neutrosophic Method for Automatic Seed Point Selection in Thyroid Nodule Images

The thyroid nodule is one of the endocrine issues caused by an irregular cell development. This rate of survival can be improved by earlier nodule detection. Accordingly, the accurate recognition of the nodule is of the utmost importance in providing powerful results in building the survival rate. The reduction in the accuracy of manual or semiautomatic segmentation methods for thyroid nodule detection is due to many factors, basically, the lack of experience of the sonographer and latency of operation. Most lesion regions in ultrasound images are homogeneous. Therefore, the value of entropy in these regions is high compared to its neighbours. Based on this criterion, a novel procedure for automatically selecting the seed point in thyroid nodule images is proposed. The proposed system consists of three components: neutrosophic image enhancement and speckle reduction to reduce speckle noise and automatic seed selection algorithm extracted from the centre of candidate block in ultrasound thyroid images based on the principle that most of its Higher Order Spectra Entropies (HOSE) from Radon Transform (RT) at different angles are within the range between average and maximum entropies, and the region growing image segmentation is applied with the constant threshold. The performance of proposed automatic segmentation method is compared with other methods in terms of calculating, True Positive (TP) value (96.44 ± 3.01%), False Positive (FP) value (3.55 ± 1.45%), Dice Coefficient (DC) value (92.24 ± 6.47%), Similarity Index (SI) (80.57 ± 1.06%), and Hausdroff Distance (HD) (0.42 ± 0.24 pixels). The proposed system can be considered as an added value to the malignancy diagnosis in thyroid nodule by an endocrinologist.

Using neutrosophic graph cut segmentation algorithm for qualified rendering image selection in thyroid elastography video

Recently, elastography has become very popular in clinical investigation for thyroid cancer detection and diagnosis. In elastogram, the stress results of the thyroid are displayed using pseudo colors. Due to variation of the rendering results in different frames, it is difficult for radiologists to manually select the qualified frame image quickly and efficiently. The purpose of this study is to find the qualified rendering result in the thyroid elastogram. This paper employs an efficient thyroid ultrasound image segmentation algorithm based on neutrosophic graph cut to find the qualified rendering images. Firstly, a thyroid ultrasound image is mapped into neutrosophic set, and an indeterminacy filter is constructed to reduce the indeterminacy of the spatial and intensity information in the image. A graph is defined on the image and the weight for each pixel is represented using the value after indeterminacy filtering. The segmentation results are obtained using a maximum-flow algorithm on the graph. Then the anatomic structure is identified in thyroid ultrasound image. Finally the rendering colors on these anatomic regions are extracted and validated to find the frames which satisfy the selection criteria. To test the performance of the proposed method, a thyroid elastogram dataset is built and totally 33 cases were collected. An experienced radiologist manually evaluates the selection results of the proposed method. Experimental results demonstrate that the proposed method finds the qualified rendering frame with 100% accuracy. The proposed scheme assists the radiologists to diagnose the thyroid diseases using the qualified rendering images.

Speckle-reduction algorithm for ultrasound images in complex wavelet domain using genetic algorithm-based mixture model

Compared with other medical-imaging modalities, ultrasound (US) imaging is a valuable way to examine the body's internal organs, and two-dimensional (2D) imaging is currently the most common technique used in clinical diagnoses. Conventional 2D US imaging systems are highly flexible cost-effective imaging tools that permit operators to observe and record images of a large variety of thin anatomical sections in real time. Recently, 3D US imaging has also been gaining popularity due to its considerable advantages over 2D US imaging. It reduces dependency on the operator and provides better qualitative and quantitative information for an effective diagnosis. Furthermore, it provides a 3D view, which allows the observation of volume information. The major shortcoming of any type of US imaging is the presence of speckle noise. Hence, speckle reduction is vital in providing a better clinical diagnosis. The key objective of any speckle-reduction algorithm is to attain a speckle-free image while preserving the important anatomical features. In this paper we introduce a nonlinear multi-scale complex wavelet-diffusion based algorithm for speckle reduction and sharp-edge preservation of 2D and 3D US images. In the proposed method we use a Rayleigh and Maxwell-mixture model for 2D and 3D US images, respectively, where a genetic algorithm is used in combination with an expectation maximization method to estimate mixture parameters. Experimental results using both 2D and 3D synthetic, physical phantom, and clinical data demonstrate that our proposed algorithm significantly reduces speckle noise while preserving sharp edges without discernible distortions. The proposed approach performs better than the state-of-the-art approaches in both qualitative and quantitative measures.

Measurement of myocardial perfusion and infarction size using computer-aided diagnosis system for myocardial contrast echocardiography

Proper evaluation of myocardial microvascular perfusion and assessment of infarct size is critical for clinicians. We have developed a novel computer-aided diagnosis (CAD) approach for myocardial contrast echocardiography (MCE) to measure myocardial perfusion and infarct size. Rabbits underwent 15 min of coronary occlusion followed by reperfusion (group I, n = 15) or 60 min of coronary occlusion followed by reperfusion (group II, n = 15). Myocardial contrast echocardiography was performed before and 7 d after ischemia/reperfusion, and images were analyzed with the CAD system on the basis of eliminating particle swarm optimization clustering analysis. The myocardium was quickly and accurately detected using contrast-enhanced images, myocardial perfusion was quantitatively calibrated and a color-coded map calibrated by contrast intensity and automatically produced by the CAD system was used to outline the infarction region. Calibrated contrast intensity was significantly lower in infarct regions than in non-infarct regions, allowing differentiation of abnormal and normal myocardial perfusion. Receiver operating characteristic curve analysis documented that -54-pixel contrast intensity was an optimal cutoff point for the identification of infarcted myocardium with a sensitivity of 95.45% and specificity of 87.50%. Infarct sizes obtained using myocardial perfusion defect analysis of original contrast images and the contrast intensity-based color-coded map in computerized images were compared with infarct sizes measured using triphenyltetrazolium chloride staining. Use of the proposed CAD approach provided observers with more information. The infarct sizes obtained with myocardial perfusion defect analysis, the contrast intensity-based color-coded map and triphenyltetrazolium chloride staining were 23.72 ± 8.41%, 21.77 ± 7.8% and 18.21 ± 4.40% (% left ventricle) respectively (p > 0.05), indicating that computerized myocardial contrast echocardiography can accurately measure infarct size. On the basis of the results, we believe the CAD method can quickly and automatically measure myocardial perfusion and infarct size and will, it is hoped, be very helpful in clinical therapeutics.

Ultrasound artifacts: classification, applied physics with illustrations, and imaging appearances

Ultrasound has become a widely used diagnostic imaging modality in medicine because of its safety and portability. Because of rapid advances in technology, in recent years, sonographic imaging quality has significantly increased. Despite these advances, the potential to encounter artifacts while imaging remains.This article classifies both common and uncommon gray-scale and Doppler ultrasound artifacts into those resulting from physiology and those caused by hardware. A brief applied-physics explanation for each artifact is listed along with an illustrated diagram. The imaging appearance of artifacts is presented in case examples, along with strategies to minimize the artifacts in real time or use them for clinical advantage where applicable.

Multiresolution edge detection using enhanced fuzzy c-means clustering for ultrasound image speckle reduction

PURPOSE

Speckle suppression in ultrasound (US) images of various anatomic structures via a novel speckle noise reduction algorithm.

METHODS

The proposed algorithm employs an enhanced fuzzy c-means (EFCM) clustering and multiresolution wavelet analysis to distinguish edges from speckle noise in US images. The edge detection procedure involves a coarse-to-fine strategy with spatial and interscale constraints so as to classify wavelet local maxima distribution at different frequency bands. As an outcome, an edge map across scales is derived whereas the wavelet coefficients that correspond to speckle are suppressed in the inverse wavelet transform acquiring the denoised US image.

RESULTS

A total of 34 thyroid, liver, and breast US examinations were performed on a Logiq 9 US system. Each of these images was subjected to the proposed EFCM algorithm and, for comparison, to commercial speckle reduction imaging (SRI) software and another well-known denoising approach, Pizurica's method. The quantification of the speckle suppression performance in the selected set of US images was carried out via Speckle Suppression Index (SSI) with results of 0.61, 0.71, and 0.73 for EFCM, SRI, and Pizurica's methods, respectively. Peak signal-to-noise ratios of 35.12, 33.95, and 29.78 and edge preservation indices of 0.94, 0.93, and 0.86 were found for the EFCM, SIR, and Pizurica's method, respectively, demonstrating that the proposed method achieves superior speckle reduction performance and edge preservation properties. Based on two independent radiologists' qualitative evaluation the proposed method significantly improved image characteristics over standard baseline B mode images, and those processed with the Pizurica's method. Furthermore, it yielded results similar to those for SRI for breast and thyroid images significantly better results than SRI for liver imaging, thus improving diagnostic accuracy in both superficial and in-depth structures.

CONCLUSIONS

A new wavelet-based EFCM clustering model was introduced toward noise reduction and detail preservation. The proposed method improves the overall US image quality, which in turn could affect the decision-making on whether additional imaging and/or intervention is needed.

Evaluation of various speckle reduction filters on medical ultrasound images

At present, ultrasound is one of the essential tools for noninvasive medical diagnosis. However, speckle noise is inherent in medical ultrasound images and it is the cause for decreased resolution and contrast-to-noise ratio. Low image quality is an obstacle for effective feature extraction, recognition, analysis, and edge detection; it also affects image interpretation by doctor and the accuracy of computer-assisted diagnostic techniques. Thus, speckle reduction is significant and critical step in pre-processing of ultrasound images. Many speckle reduction techniques have been studied by researchers, but to date there is no comprehensive method that takes all the constraints into consideration. In this paper we discuss seven filters, namely Lee, Frost, Median, Speckle Reduction Anisotropic Diffusion (SRAD), Perona-Malik's Anisotropic Diffusion (PMAD) filter, Speckle Reduction Bilateral Filter (SRBF) and Speckle Reduction filter based on soft thresholding in the Wavelet transform. A comparative study of these filters has been made in terms of preserving the features and edges as well as effectiveness of de-noising.We computed five established evaluation metrics in order to determine which despeckling algorithm is most effective and optimal for real-time implementation. In addition, the experimental results have been demonstrated by filtered images and statistical data table.

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

In ultrasound (US), optical coherence tomography, synthetic aperture radar, and other coherent imaging systems, images are corrupted by multiplicative speckle noise that obscures image interpretation. An anisotropic diffusion (AD) method based on the Gabor transform, named Gabor-based anisotropic diffusion (GAD), is presented to suppress speckle in medical ultrasonography. First, an edge detector using the Gabor transform is proposed to capture directionality of tissue edges and discriminate edges from noise. Then the edge detector is embedded into the partial differential equation of AD to guide the diffusion process and iteratively denoise images. To enhance GAD's adaptability, parameters controlling diffusion are determined from a fully formed speckle region that is automatically detected. We evaluate the GAD on synthetic US images simulated with three models and clinical images acquired in vivo. Compared with seven existing speckle reduction methods, the GAD is superior to other methods in terms of noise reduction and detail preservation.

Effect of a novel segmentation algorithm on radiologists' diagnosis of breast masses using ultrasound imaging

We investigated the effect of using a novel segmentation algorithm on radiologists' sensitivity and specificity for discriminating malignant masses from benign masses using ultrasound. Five-hundred ten conventional ultrasound images were processed by a novel segmentation algorithm. Five radiologists were invited to analyze the original and computerized images independently. Performances of radiologists with or without computer aid were evaluated by receiver operating characteristic (ROC) curve analysis. The masses became more obvious after being processed by the segmentation algorithm. Without using the algorithm, the areas under the ROC curve (Az) of the five radiologists ranged from 0.70∼0.84. Using the algorithm, the Az increased significantly (range, 0.79∼0.88; p < 0.001). The proposed segmentation algorithm could improve the radiologists' diagnosis performance by reducing the image speckles and extracting the mass margin characteristics.

BREAST ULTRASOUND IMAGE SEGMENTATION BASED ON PARTICLE SWARM OPTIMIZATION AND THE CHARACTERISTICS OF BREAST TISSUE

Breast cancer occurs in over 8% of women during their lifetime, and is the leading cause of death among women. Sonography is superior to mammography because it has the ability to detect focal abnormalities in the dense breasts and has no side-effect. In this paper, we propose a novel automatic segmentation algorithm based on the characteristics of breast tissue and eliminating particle swarm optimization (EPSO) clustering analysis. The characteristics of mammary gland in breast ultrasound (BUS) images are analyzed and utilized, and a method based on step-down threshold technique is employed to locate the mammary gland area. The EPSO clustering algorithm utilizes the idea of "survival of the superior and weeding out the inferior". The experimental results demonstrate that the proposed approach can segment BUS image with high accuracy and low computational time. The EPSO clustering method reduces the computational time by 32.75% compared with the standard PSO clustering algorithm. The proposed approach would find wide applications in automatic lesion classification and computer aided diagnosis (CAD) systems of breast cancer.

Texture feature analysis for breast ultrasound image enhancement

Texture analysis of breast ultrasound B-scans has been widely applied to the segmentation and classification of breast tumors. We present a parametric imaging method based on the texture features to preserve tumor edges and retain the texture information simultaneously. Four texture-feature parameters--homogeneity, contrast, energy and variance--were evaluated using the gray-level co-occurrence matrix. The local texture-feature parameter was assigned as the new pixel located at the center of the sliding window at each position. This process yielded the texture-feature parametric image as the map of texture-feature values. The signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were estimated to show the quality improvement of the images. The contours outlined from 11 experienced physicians and the gradient vector flow (GVF) snake algorithm segmentations were adopted to verify the edge enhancement of texture-feature parametric images. In addition, the Fisher's linear discriminant analysis (FLDA) and receiver-operating-characteristic (ROC) curve were used to test the performance of breast tumor classifications between texture-feature parametric images and B-scan images. The results show that the variance images have higher CNR and SNR estimates than those in the B-scan images. There was a high agreement between the physician's manual contours and the GVF snake automatic segmentations in the variance images, and the mean area overlap was over 93%. The area under the ROC curve from the B-scan images had 0.81 and 95% confidence interval of 0.72-0.88, and the texture-feature parametric images had 0.90 and 95% confidence interval of 0.84-0.96. These findings indicate that the texture-feature parametric imaging method can be not only useful for determining the location of the lesion boundary but also as a tool to improve the accuracy of breast tumor classifications.

Speckle reduction in ultrasound images using nonisotropic adaptive filtering

In this article, a speckle reduction approach for ultrasound imaging that preserves important features such as edges, corners and point targets is presented. Speckle reduction is an important problem in coherent imaging, such as ultrasound imaging or synthetic aperture radar, and many speckle reduction algorithms have been developed. Speckle is a non-additive and non-white process and the reduction of speckle without blurring sharp features is known to be difficult. The new speckle reduction algorithm presented in this article utilizes a nonhomogeneous filter that adapts to the proximity and direction of the nearest important features. To remove speckle without blurring important features, the location and direction of edges in the image are estimated. Then for each pixel in the image, the distance and angle to the nearest edge are efficiently computed by a two-pass algorithm and stored in distance and angle maps. Finally for each pixel, an adaptive directional filter aligned to the nearest edge is applied. The shape and orientation of the adaptive filter are determined from the distance and angle maps. The new speckle reduction algorithm is tested with both synthesized and real ultrasound images. The performance of the new algorithm is also compared with those of other speckle reduction approaches and it is shown that the new algorithm performs favorably in reducing speckle without blurring important features.

SRBF: Speckle reducing bilateral filtering

Speckle noise negatively affects medical ultrasound image shape interpretation and boundary detection. Speckle removal filters are widely used to selectively remove speckle noise without destroying important image features to enhance object boundaries. In this article, a fully automatic bilateral filter tailored to ultrasound images is proposed. The edge preservation property is obtained by embedding noise statistics in the filter framework. Consequently, the filter is able to tackle the multiplicative behavior modulating the smoothing strength with respect to local statistics. The in silico experiments clearly showed that the speckle reducing bilateral filter (SRBF) has superior performances to most of the state of the art filtering methods. The filter is tested on 50 in vivo US images and its influence on a segmentation task is quantified. The results using SRBF filtered data sets show a superior performance to using oriented anisotropic diffusion filtered images. This improvement is due to the adaptive support of SRBF and the embedded noise statistics, yielding a more homogeneous smoothing. SRBF results in a fully automatic, fast and flexible algorithm potentially suitable in wide ranges of speckle noise sizes, for different medical applications (IVUS, B-mode, 3-D matrix array US).

Improvement of speckle noise reduction using multi-resolutional coherence measurement in ultrasound image

Ultrasound (US) images are degraded by speckle noise that reduces the contrast and details of images. But the effective method for speckle noise reduction with keeping edge has been still a challenging point. Coherence measurement has been used to distinguish homogeneous region and coherence regions, e.g. edges, and the edge map obtained from coherence measurement has limitation such as noisy or discontinued edge detection. In this paper, to overcome these problems, the enhanced edge map generation using multi-resolutional coherence measurement is proposed and adaptive wavelet based-speckle noise reduction is performed using the enhanced edge map. The experimental results showed that the enhanced edge map by proposed method contains the robust and linked edge information. Moreover, the results show that the proposed method outperforms the conventional method in preserving edge details.

Novel computer-aided diagnosis algorithms on ultrasound image: effects on solid breast masses discrimination

The objective of this study is to retrospectively investigate whether using the newly developed algorithms would improve radiologists' accuracy for discriminating malignant masses from benign ones on ultrasonographic (US) images. Five radiologists blinded to the histological results and clinical history independently interpreted 226 cases according to the sonographic lexicon of the fourth edition of the Breast Imaging Reporting and Data System and assigned a final assessment category to indicate the probability of malignancy. For each case, each radiologist provided three diagnoses: first with the original images, subsequently with the assistant of the resulting images processed by the proposed CAD algorithms which are called as processed images, and another using the processed images only. Observers' malignancy rating data were analyzed with the receiver operating characteristic (ROC) curve. For reading only with the processed images, areas under the ROC curve (A(z)) of each reader (0.863, 0.867, 0.859, 0.868, 0.878) were better than that with the original images (0.772, 0.807, 0.796, 0.828, 0.846), difference of the average A(z) between the twice reading was significant (p < 0.001). Compared with the results single used processed images, A(z) of utilizing the combined images were increased (0.866, 0.885, 0.872, 0.894, 0.903), but the difference is not statistically significant (p = 0.081). The proposed CAD method has potential to be a good aid to radiologists in distinguishing malignant breast solid masses from benign ones.

Automated segmentation of ultrasonic breast lesions using statistical texture classification and active contour based on probability distance

Because of its complicated structure, low signal/noise ratio, low contrast and blurry boundaries, fully automated segmentation of a breast ultrasound (BUS) image is a difficult task. In this paper, a novel segmentation method for BUS images without human intervention is proposed. Unlike most published approaches, the proposed method handles the segmentation problem by using a two-step strategy: ROI generation and ROI segmentation. First, a well-trained texture classifier categorizes the tissues into different classes, and the background knowledge rules are used for selecting the regions of interest (ROIs) from them. Second, a novel probability distance-based active contour model is applied for segmenting the ROIs and finding the accurate positions of the breast tumors. The active contour model combines both global statistical information and local edge information, using a level set approach. The proposed segmentation method was performed on 103 BUS images (48 benign and 55 malignant). To validate the performance, the results were compared with the corresponding tumor regions marked by an experienced radiologist. Three error metrics, true-positive ratio (TP), false-negative ratio (FN) and false-positive ratio (FP) were used for measuring the performance of the proposed method. The final results (TP = 91.31%, FN = 8.69% and FP = 7.26%) demonstrate that the proposed method can segment BUS images efficiently, quickly and automatically.