IVUS Images Research Articles

Automated diagnosis of atherosclerosis using multi-layer ensemble models and bio-inspired optimization in intravascular ultrasound imaging.

Atherosclerosis causes heart disease by forming plaques in arterial walls. IVUS imaging provides a high-resolution cross-sectional view of coronary arteries and plaque morphology. Healthcare professionals diagnose and quantify atherosclerosis physically or using VH-IVUS software. Since manual or VH-IVUS software-based diagnosis is time-consuming, automated plaque characterization tools are essential for accurate atherosclerosis detection and classification. Recently, deep learning (DL) and computer vision (CV) approaches are promising tools for automatically classifying plaques on IVUS images. With this motivation, this manuscript proposes an automated atherosclerotic plaque classification method using a hybrid Ant Lion Optimizer with Deep Learning (AAPC-HALODL) technique on IVUS images. The AAPC-HALODL technique uses the faster regional convolutional neural network (Faster RCNN)-based segmentation approach to identify diseased regions in the IVUS images. Next, the ShuffleNet-v2 model generates a useful set of feature vectors from the segmented IVUS images, and its hyperparameters can be optimally selected by using the HALO technique. Finally, an average ensemble classification process comprising a stacked autoencoder (SAE) and deep extreme learning machine (DELM) model can be utilized. The MICCAI Challenge 2011 dataset was used for AAPC-HALODL simulation analysis. A detailed comparative study showed that the AAPC-HALODL approach outperformed other DL models with a maximum accuracy of 98.33%, precision of 97.87%, sensitivity of 98.33%, and F score of 98.10%.

Improved IVUS and VH-IVUS image segmentation using a hybrid approach based on active counter model and clustering algorithms

Improved IVUS and VH-IVUS image segmentation using a hybrid approach based on active counter model and clustering algorithms

Scale Mutualized Perception for Vessel Border Detection in Intravascular Ultrasound Images.

Vessel border detection in IVUS images is essential for coronary disease diagnosis. It helps to obtain the clinical indices on the inner vessel morphology to indicate the stenosis. However, the existing methods suffer the challenge of scale-dependent interference. Early methods usually rely on the hand-crafted features, thus not robust to this interference. The existing deep learning methods are also ineffective to solve this challenge, because these methods aggregate multi-scale features in the top-down way. This aggregation may bring in interference from the non-adjacent scale. Besides, they only combine the features in all scales, and thus may weaken their complementary information. We propose the scale mutualized perception to solve this challenge by considering the adjacent scales mutually to preserve their complementary information. First, the adjacent small scales contain certain semantics to locate different vessel tissues. Then, they can also perceive the global context to assist the representation of the local context in the adjacent large scale, and vice versa. It helps to distinguish the objects with similar local features. Second, the adjacent large scales provide detailed information to refine the vessel boundaries. The experiments show the effectiveness of our method in 153 IVUS sequences, and its superiority to ten state-of-the-art methods.

Plaque Territory Detection in IVUS Images based on Concentration of Entropy and Gradient Magnitude via Spiral Random Walk-based Approach

This paper presents a simple and optimal approach for automatically identifying the location and size of plaque territories in IVUS images, thus improving plaque territory classification. Unlike existing circular-based algorithms, we leverage the anatomical structure of IVUS images to enhance accuracy. The adventitia, which constitutes the largest part of the image, serves as a landmark; however, its low contrast makes edge detection challenging. To address this issue, we enhance the brightness of the adventitia, identify and remove intima blobs, and accurately determine the media boundary. This aids in simplifying the calculation of plaque territory. To locate the plaque territory, we employ a spiral random walk-based approach that utilizes the concentration of entropy and gradient magnitude in the target area. Our approach outperforms existing methods, contributing to automated plaque analysis for cardiovascular disease diagnosis and treatment. The results show that the proposed approach achieves an accuracy of 0.89, precision of 0.81, recall of 0.77, and F1-Score of 0.83, respectively.

Diagnostic performance of IVUS-FFR analysis based on generative adversarial network and bifurcation fractal law for assessing myocardial ischemia.

IVUS-based virtual FFR (IVUS-FFR) can provide additional functional assessment information to IVUS imaging for the diagnosis of coronary stenosis. IVUS image segmentation and side branch blood flow can affect the accuracy of virtual FFR. The purpose of this study was to evaluate the diagnostic performance of an IVUS-FFR analysis based on generative adversarial networks and bifurcation fractal law, using invasive FFR as a reference. In this study, a total of 108 vessels were retrospectively collected from 87 patients who underwent IVUS and invasive FFR. IVUS-FFR was performed by analysts who were blinded to invasive FFR. We evaluated the diagnostic performance and computation time of IVUS-FFR, and compared it with that of the FFR-branch (considering side branch blood flow by manually extending the side branch from the bifurcation ostia). We also compared the effects of three bifurcation fractal laws on the accuracy of IVUS-FFR. The diagnostic accuracy, sensitivity, and specificity for IVUS-FFR to identify invasive were 90.7% (95% CI, 83.6-95.5), 89.7% (95% CI, 78.8-96.1), 92.0% (95% CI, 80.8-97.8), respectively. A good correlation and agreement between IVUS-FFR and invasive FFR were observed. And the average computation time of IVUS-FFR was shorter than that of FFR-branch. In addition to this, we also observe that the HK model is the most accurate among the three bifurcation fractal laws. Our proposed IVUS-FFR analysis correlates and agrees well with invasive FFR and shows good diagnostic performance. Compared with FFR-branch, IVUS-FFR has the same level of diagnostic performance with significantly lower computation time.

Deep learning segmentation, classification, and risk prediction of complex vascular lesions on intravascular ultrasound images

BackgroundThis study aimed to access the performance of our deep learning-based model in the segmentation and classification of vascular lesions on IVUS images. MethodsA total of 5,089 IVUS frames derived from 100 patients with stable or unstable angina pectoris were retrospectively collected. Our deep learning diagnostic framework composed of two stages, image segmentation and lesion classification. Segmentation was performed using the dilated attention U-Net model. The standard classifier, ResNet18, was subsequently used to classify the lesions into six groups, plaques (fibrous, lipid, and calcified), dissections, hematomas, and thrombi. Segmentation performance was evaluated in terms of Dice similarity coefficient (DSC) and 95% Hausdorff distance (HD95), while classification was assessed based on sensitivity, specificity, area under the receiver operating characteristic curve, and F1 score. The predictive value of our proposed model for high-risk lesions based on geometric measurements was further assessed. ResultsThe segmentation performance of our model was deemed satisfactory, with average DSC values of 80.75%, 86.68%, and 79.21% demonstrated for dissections, hematomas, and thrombi, respectively. Good lesion classification performance was observed as well, with F1 scores of 94.89%, 95.91% and 96.42%, respectively. Our model further demonstrated the ability to stratify lesions at risk for dissection. ConclusionOur deep-learning diagnostic framework demonstrated accuracy in the identification, classification, and risk stratification of vascular lesions based on IVUS images. It is clinically conducive, easily adoptable, and enables the early diagnosis of complex lesions at risk of major adverse cardiovascular events.

INTRAVASCULAR ULTRASOUND DERIVED MINIMAL LUMINAL AREA AND PLAQUE BURDEN OF CORONARY VESSELS IN OUR LOCAL POPULATION

Objectives: To report the average IVUS derived MLAs and plaque burden of coronary arteries of our local population.
 Methodology: It was a retrospective observational study. A total of 64 patients having IVUS done from January 2022 to September 2022 was enrolled in this study. IVUS images were acquired using 40 MHz, 3.1 French Opticross IVUS catheter (OptiCross™, Boston Scientific, USA).
 Results: Out of 54 patients, 39 (72%) were males with a mean age of 53.7 ± 14.1 years. The left main (LM) disease was found in n = 43 (79.6%) on coronary angiogram. The LM mean minimal luminal area was 6.68 ± 1.9 mm2 and mean minimal luminal diameter was 3.83 mm ± 1.02. Mean LM plaque burden was 57% (range 0-57). In proximal LAD mean MLA was 5.04 ± 2.7mm2, mean proximal reference diameter was 3.97 ± 0.64 mm and plaque burden was 53.88 ± 16.5%. The pattern of the plaque was diffuse with more calcified in the LAD than in the left main stem. The mean minimal stent area achieved in patients who had received stenting was 13.05 ± 2.88mm2 in LM (n = 15), and 9.71 ± 2.88 mm2 in proximal LAD (n = 30).
 
 Figure 1: (a). IVUS image of left main artery with minimum plaque. (b) well apposed stent in LAD of a patient, (c). heavy plaque burden with calcification causing drop out.
 Conclusion: Our local population has Coronary sizes comparable to those reported in the international literature. The stent size in major vessels like LM and proximal LAD should be guided by the use of IVUS to achieve maximum MSA to reduce adverse outcomes.

Capsule networks for segmentation of small intravascular ultrasound image datasets

PurposeIntravascular ultrasound (IVUS) imaging is crucial for planning and performing percutaneous coronary interventions. Automatic segmentation of lumen and vessel wall in IVUS images can thus help streamlining the clinical workflow. State-of-the-art results in image segmentation are achieved with data-driven methods like convolutional neural networks (CNNs). These need large amounts of training data to perform sufficiently well but medical image datasets are often rather small. A possibility to overcome this problem is exploiting alternative network architectures like capsule networks.MethodsWe systematically investigated different capsule network architecture variants and optimized the performance on IVUS image segmentation. We then compared our capsule network with corresponding CNNs under varying amounts of training images and network parameters.ResultsContrary to previous works, our capsule network performs best when doubling the number of capsule types after each downsampling stage, analogous to typical increase rates of feature maps in CNNs. Maximum improvements compared to the baseline CNNs are 20.6% in terms of the Dice coefficient and 87.2% in terms of the average Hausdorff distance.ConclusionCapsule networks are promising candidates when it comes to segmentation of small IVUS image datasets. We therefore assume that this also holds for ultrasound images in general. A reasonable next step would be the investigation of capsule networks for few- or even single-shot learning tasks.

Calcification detection for intravascular ultrasound image using direct acyclic graph architecture: pre-trained model for 1-channel image

Coronary artery calcification is a calcium buildup within the walls of the arteries. It is considered a predominant marker for coronary artery disease. Thus many approaches have been developed for the automatic detection of calcification. The previous calcification detection was on segmentation of other structures as pre-processing steps or using the fact that the calcification often appears as a bright region. In this paper, an automated system proposed using a deep learning approach to detect the calcification absence and calcification presence in coronary artery IVUS image. A useful advantage of deep learning, compared to other methods is, it uses representations and features directly from the raw data, bypassing the need to manually extract features, a common that required in the traditional machine learning framework. The type of deep learning architecture used is 27 layers of convolutional neural networks (CNNs) using Direct Acyclic Graph. The proposed system used 2175 images and achieved an accuracy of 98.16% for Cartesian coordinate images and 99.08% for Polar Reconstructed Coordinate images.

Comparison of quantitative measurements between two different intravascular ultrasound catheters and consoles: in vitro and in vivo studies

Previous studies suggested possible discordant quantitative measurements between different IVUS catheters and/or systems. The purpose of this study was to assess compatibility of two different IVUS catheters and consoles for quantitative measurements of coronary arteries. (1). In vitro study: IVUS imaging was performed in a concentric cylindrical phantom with 6 sections of known, cross-sectional diameter ranging from 3.0 to 8.0 mm. The lumen diameter (LD) and lumen cross-sectional area (LA) were measured and compared. To compare between 2 different IVUS consoles, IVUS images were obtained using a single IVUS catheter (catheter 1) connected to 2 different IVUS consoles (console 1 and 2). To compare between 2 different IVUS catheters, IVUS imaging was obtained using 2 different IVUS catheters (catheter 1 and 2) connected to a single IVUS console (console 2). (2). In vivo study: IVUS imaging was performed in 40 stented coronary arterial segments from 40 patients. The maximal stent diameter (Max SD), minimal stent diameter (minSD), and stent area (SA) were measured at both distal and proximal stent edges and compared between the two IVUS consoles (console 1 and 2) connected to a single IVUS catheter (catheter 1) (n = 20). IVUS imaging was also performed to compare between catheter 1 and 2 connected to IVUS console 2 (n = 20). Both in vitro and in vivo studies showed good correlation between the two IVUS consoles as well as two IVUS catheters. In conclusion, two IVUS catheters and consoles provide comparable IVUS measures both in vitro and in vivo.

In-stent protruding bump with abnormal IVUS images causing acute coronary syndrome in a hemodialysis patient.

In-stent protruding bump with abnormal IVUS images causing acute coronary syndrome in a hemodialysis patient.

Classification of Coronary Heart Artery Disease Using IVUS Images by SVM Classifier with Modified Radial Basis Function Kernel (MRBFK)

Classification of Coronary Heart Artery Disease Using IVUS Images by SVM Classifier with Modified Radial Basis Function Kernel (MRBFK)

Intravascular ultrasound-based machine learning for predicting fractional flow reserve in intermediate coronary artery lesions

Background and aimsIntravascular ultrasound (IVUS)-derived morphological criteria are poor predictors of the functional significance of intermediate coronary stenosis. IVUS-based supervised machine learning (ML) algorithms were developed to identify lesions with a fractional flow reserve (FFR) ≤0.80 (vs. >0.80). MethodsA total of 1328 patients with 1328 non-left main coronary lesions were randomized into training and test sets in a 4:1 ratio. Masked IVUS images were generated by an automatic segmentation model, and 99 computed IVUS features and six clinical variables (age, gender, body surface area, vessel type, involved segment, and involvement of the proximal left anterior descending artery) were used for ML training with 5-fold cross-validation. Diagnostic performances of the binary classifiers (L2 penalized logistic regression, artificial neural network, random forest, AdaBoost, CatBoost, and support vector machine) for detecting ischemia-producing lesions were evaluated using the non-overlapping test samples. ResultsIn the classification of test set lesions into those with an FFR ≤0.80 vs. >0.80, the overall diagnostic accuracies for predicting an FFR ≤0.80 were 82% with L2 penalized logistic regression, 80% with artificial neural network, 83% with random forest, 83% with AdaBoost, 81% with CatBoost, and 81% with support vector machine (AUCs: 0.84–0.87). With exclusion of the 28 lesions with borderline FFR of 0.75–0.80, the overall accuracies for the test set were 86% with L2 penalized logistic regression, 85% with an artificial neural network, 87% with random forest, 87% with AdaBoost, 85% with CatBoost, and 85% with support vector machine. ConclusionsThe IVUS-based ML algorithms showed good diagnostic performance for identifying ischemia-producing lesions, and may reduce the need for pressure wires.

Lumen-intima and media-adventitia segmentation in IVUS images using supervised classifications of arterial layers and morphological structures

BackgroundIntravascular ultrasound (IVUS) provides axial grey-scale images of blood vessels. The large number of images require automatic analysis, specifically to identify the lumen and outer vessel wall. However, the high amount of noise, the presence of artifacts and anatomical structures, such as bifurcations, calcifications and fibrotic plaques, usually hinder the proper automatic segmentation of the vessel wall. MethodsLumen, media, adventitia and surrounding tissues are automatically detected using Support Vector Machines (SVMs). The classification performance of the SVMs vary according to the kind of structure present within each region of the image. Random Forest (RF) is used to detect different morphological structures and to modify the initial layer classification depending on the detected structure. The resulting classification maps are fed into a segmentation method based on deformable contours to detect lumen-intima (LI) and media-adventitia (MA) interfaces. ResultsThe modifications in the layer classifications according to the presence of structures proved to be effective improving LI and MA segmentations. The proposed method reaches a Jaccard Measure (JM) of 0.88 ± 0.08 for LI segmentation, compared with 0.88 ± 0.05 of a semiautomatic method. When looking at MA, our method reaches a JM of 0.84 ± 0.09, and outperforms previous automatic methods in terms of HD, with 0.51mm ± 0.30. ConclusionsA simple modification to the arterial layer classification produces results that match and improve state-of-the-art fully-automatic segmentation methods for LI and MA in 20MHz IVUS images. For LI segmentation, the proposed automatic method performs accurately as semi-automatic methods. For MA segmentation, our method matched the quality of state-of-the-art automatic methods described in the literature. Furthermore, our implementation is modular and open-source, allowing for future extensions and improvements.

A 40-MHz Ultrasound Transducer with an Angled Aperture for Guiding Percutaneous Revascularization of Chronic Total Occlusion: A Feasibility Study.

Complete blockage of a coronary artery, called chronic total occlusion (CTO), frequently occurs due to atherosclerosis. To reopen the obstructed blood vessels with a stent, guidewire crossing is performed with the help of angiography that can provide the location of CTO lesions and the image of guidewire tip. Since angiography is incapable of imaging inside a CTO lesion, the surgeons are blind during guidewire crossing. For this reason, the success rate of guidewire crossing relies upon the proficiency of the surgeon, which is considerably reduced from 69.0% to 32.5% if extensive calcification, not penetrated by a guidewire, exists in CTO lesions. In this paper, a recently developed 40-MHz forward-looking intravascular ultrasound (FL–IVUS) transducer to visualize calcification within CTO lesions is reported. This transducer consists of a single element angled aperture and a guidewire passage. The aperture is spherically deformed to have a focal length of 3 mm in order to improve spatial resolution of FL–IVUS images. The angle between the beam direction and the axis of rotation is designed to be 30° to effectively visualize calcification within a CTO lesion as well as the blood vessel wall. The experimental results demonstrated that the developed FL–IVUS transducer facilitates visualization of calcification within CTO lesions and makes it possible to help the surgeon make decisions about whether to push the guidewire in order to cross the lesion or to change the surgical procedure.

Automated detection of vulnerable plaque in intravascular ultrasound images.

Acute coronary syndrome (ACS) is a syndrome caused by a decrease in blood flow in the coronary arteries. The ACS is usually related to coronary thrombosis and is primarily caused by plaque rupture followed by plaque erosion and calcified nodule. Thin-cap fibroatheroma (TCFA) is known to be the most similar lesion morphologically to a plaque rupture. In this paper, we propose methods to classify TCFA using various machine learning classifiers including feed-forward neural network (FNN), K-nearest neighbor (KNN), random forest (RF), and convolutional neural network (CNN) to figure out a classifier that shows optimal TCFA classification accuracy. In addition, we suggest pixel range-based feature extraction method to extract the ratio of pixels in the different region of interests to reflect the physician's TCFA discrimination criteria. Our feature extraction method examines the pixel distribution of the intravascular ultrasound (IVUS) image at a given ROI, which allows us to extract general characteristics of the IVUS image while simultaneously reflecting the different properties of the vessel's substances such as necrotic core and calcified nodule depending on the brightness of the pixel. A total of 12,325 IVUS images were labeled with corresponding optical coherence tomography (OCT) images to train and evaluate the classifiers. We achieved 0.859, 0.848, 0.844, and 0.911 area under the ROC curve (AUC) in the order of using FNN, KNN, RF, and CNN classifiers. As a result, the CNN classifier performed best and the top 10 features of the feature-based classifiers (FNN, KNN, RF) were found to be similar to the physician's TCFA diagnostic criteria. Graphical Abstract AUC result of proposed classifiers.

Six-month evaluation of novel bioabsorbable scaffolds composed of poly-L-lactic acid and amorphous calcium phosphate nanoparticles in porcine coronary arteries.

Objective Using coronary angiography and intravascular ultrasound methods to evaluate the performance of the novel fully bioabsorbable scaffold (NFBS) composed of poly-L-lactic acid/amorphous calcium phosphate (PLLA/ACP) at six-month follow-up by comparing with PLLA scaffolds Methods Twelve PLLA/ACP scaffolds and 12 PLLA scaffolds were implanted into the coronary arteries of 12 miniature pigs. Quantitative coronary angiography (QCA) was used to measure the reference vessel diameter (RVD), mean lumen diameter (MLD) and late lumen loss (LLL). According to IVUS images, we calculated the strut malapposition rate (SMR) at post implantation, strut overlap rate (SOR), reference vessel area (RVA), mean stent area (MSA), mean lumen area (MLA) and luminal patency rate (LPR) at six-month follow-up. The radial strength of the scaffold was evaluated using a catheter tensile testing machine. Results QCA results indicated that, at six month, MLD of PLLA/ACP scaffolds was greater than those of PLLA scaffolds (2.47 ± 0.22 mm vs. 2.08 ± 0.25 mm, P < 0.05); LLL of PLLA/ACP scaffolds was less than those of PLLA scaffolds (0.42 ± 0.20 mm vs. 0.75 ± 0.22 mm, P < 0.05). IVUS results showed the SMR and SOR were all significantly less with the PLLA/ACP scaffolds than the PLLA scaffolds (5.84% ± 3.56% vs. 17.72% ± 4.86%, P < 0.05) (6.17% ± 4.63% vs. 17.65% ± 4.29%, P < 0.05). MSA, MLA and LPR of the PLLA/ACP scaffolds were all greater than those of PLLA scaffolds (6.35 ± 0.45 mm2 vs. 5.35 ± 0.51 mm2, P < 0.05) (4.76 ± 0.46 mm2 vs. 3.77 ± 0.46 mm2, P < 0.05) (78.01% ± 12.29% vs. 61.69% ± 9.76%, P < 0.05). Radial strength of PLLA/ACP scaffold at six month was greater than that of PLLA scaffold (76.33 ± 3.14 N vs. 67.67 ± 3.63 N). Conclusion The NFBS had less stent recoil, better lumen patency rate and greater radial strength than PLLA scaffolds. The results suggest the NFBS scaffolds can maintain the structural strength and functional performance, which are effective for up to six months when implanted in porcine coronary arteries.

Combining IVUS and Optical Coherence Tomography for More Accurate Coronary Cap Thickness Quantification and Stress/Strain Calculations: A Patient-Specific Three-Dimensional Fluid-Structure Interaction Modeling Approach.

Accurate cap thickness and stress/strain quantifications are of fundamental importance for vulnerable plaque research. Virtual histology intravascular ultrasound (VH-IVUS) sets cap thickness to zero when cap is under resolution limit and IVUS does not see it. An innovative modeling approach combining IVUS and optical coherence tomography (OCT) is introduced for cap thickness quantification and more accurate cap stress/strain calculations. In vivo IVUS and OCT coronary plaque data were acquired with informed consent obtained. IVUS and OCT images were merged to form the IVUS + OCT data set, with biplane angiography providing three-dimensional (3D) vessel curvature. For components where VH-IVUS set zero cap thickness (i.e., no cap), a cap was added with minimum cap thickness set as 50 and 180 μm to generate IVUS50 and IVUS180 data sets for model construction, respectively. 3D fluid-structure interaction (FSI) models based on IVUS + OCT, IVUS50, and IVUS180 data sets were constructed to investigate cap thickness impact on stress/strain calculations. Compared to IVUS + OCT, IVUS50 underestimated mean cap thickness (27 slices) by 34.5%, overestimated mean cap stress by 45.8%, (96.4 versus 66.1 kPa). IVUS50 maximum cap stress was 59.2% higher than that from IVUS + OCT model (564.2 versus 354.5 kPa). Differences between IVUS and IVUS + OCT models for cap strain and flow shear stress (FSS) were modest (cap strain <12%; FSS <6%). IVUS + OCT data and models could provide more accurate cap thickness and stress/strain calculations which will serve as basis for further plaque investigations.

Computational imaging of aortic vasa vasorum and neovascularization in rabbits using contrast-enhanced intravascular ultrasound: Association with histological analysis.

Objective:Neoangiogenesis is pathophysiologically related to atherosclerotic plaque growth and vulnerability. We examined the in vivo performance of a computational method using contrast-enhanced intravascular ultrasound (CE-IVUS) to detect and quantify aortic wall neovascularization in rabbits. We also compared these findings with histological data.Methods:Nine rabbits were fed with a hyperlipidemic diet. IVUS image sequences were continuously recorded before and after the injection of a contrast agent. Mean enhancement of intensity of a region of interest (MEIR) was calculated using differential imaging algorithm. The percent difference of MEIR before and after the injection of microbubbles (d_MEIR) was used as an index of the density of plaque or/and adventitial neovascularization. Aortic segments were excised for histological analysis.Results:CE-IVUS and histological analysis were performed in 11 arterial segments. MEIR was significantly increased (~20%) after microbubble injection (from 8.1±0.9 to 9.7±1.8, p=0.016). Segments with increased VV/neovessels in the tunica adventitia (histological scores 2 and 3) had significantly higher d_MEIR compared with segments with low presence of VV/neovessels (score 1); 40.5±22.9 vs. 8±14.6, p=0.024, respectively.Conclusion:It is possible to detect VV or neovessels in vivo using computational analysis of CE-IVUS images, which is in agreement with histological data. These findings may have critical implications on vulnerable plaque assessment and risk stratification.

Nonlocal total variation based on symmetric Kullback-Leibler divergence for the ultrasound image despeckling

BackgroundUltrasound imaging is safer than other imaging modalities, because it is noninvasive and nonradiative. Speckle noise degrades the quality of ultrasound images and has negative effects on visual perception and diagnostic operations.MethodsIn this paper, a nonlocal total variation (NLTV) method for ultrasonic speckle reduction is proposed. A spatiogram similarity measurement is introduced for the similarity calculation between image patches. It is based on symmetric Kullback-Leibler (KL) divergence and signal-dependent speckle model for log-compressed ultrasound images. Each patch is regarded as a spatiogram, and the spatial distribution of each bin of the spatiogram is regarded as a weighted Gamma distribution. The similarity between the corresponding bins of the two spatiograms is computed by the symmetric KL divergence. The Split-Bregman fast algorithm is then used to solve the adapted NLTV object function. Kolmogorov-Smirnov (KS) test is performed on synthetic noisy images and real ultrasound images.ResultsWe validate our method on synthetic noisy images and clinical ultrasound images. Three measures are adopted for the quantitative evaluation of the despeckling performance: the signal-to-noise ratio (SNR), structural similarity index (SSIM), and natural image quality evaluator (NIQE). For synthetic noisy images, when the noise level increases, the proposed algorithm achieves slightly higher SNRS than that of the other two algorithms, and the SSIMS yielded by the proposed algorithm is obviously higher than that of the other two algorithms. For liver, IVUS and 3DUS images, the NIQE values are 8.25, 6.42 and 9.01, all of which are higher than that of the other two algorithms.ConclusionsThe results of the experiments over synthetic and real ultrasound images demonstrate that the proposed method outperforms current state-of-the-art despeckling methods with respect to speckle reduction and tissue texture preservation.