Quality evaluation of ultrasound imaging in the carotid artery based on normalization and speckle reduction filtering

Image quality is important when evaluating ultrasound images of the carotid for the assessment of the degree of atherosclerotic disease, or when transferring images through a telemedicine channel, and/or in other image processing tasks. The objective of this study was to investigate the usefulness of image quality evaluation based on image quality metrics and visual perception, in ultrasound imaging of the carotid artery after normalization and speckle reduction filtering. Image quality was evaluated based on statistical and texture features, image quality evaluation metrics, and visual perception evaluation made by two experts. These were computed on 80 longitudinal ultrasound images of the carotid bifurcation recorded from two different ultrasound scanners, the HDI ATL-3000 and the HDI ATL-5000 scanner, before (NF) and after (DS) speckle reduction filtering, after normalization (N), and after normalization and speckle reduction filtering (NDS). The results of this study showed that: (1) the normalized speckle reduction, NDS, images were rated visually better on both scanners; (2) the NDS images showed better statistical and texture analysis results on both scanners; (3) better image quality evaluation results were obtained between the original (NF) and normalized (N) images, i.e. NF–N, for both scanners, followed by the NF–DS images for the ATL HDI-5000 scanner and the NF–DS on the HDI ATL-3000 scanner; (4) the ATL HDI-5000 scanner images have considerable higher entropy than the ATL HDI-3000 scanner and thus more information content. However, based on the visual evaluation by the two experts, both scanners were rated similarly. The above findings are also in agreement with the visual perception evaluation, carried out by the two vascular experts. The results of this study showed that ultrasound image normalization and speckle reduction filtering are important preprocessing steps favoring image quality, and should be further investigated.     

Detection of the intima and media layer thickness of ultrasound common carotid artery image using efficient active contour segmentation technique

An active contour segmentation technique for extracting the intima–media layer of the common carotid artery (CCA) ultrasound images employing semiautomatic region of interest identification and speckle reduction techniques is presented in this paper. An attempt has been made to test the ultrasound images of the carotid artery of different subjects with this contour segmentation based on improved dynamic programming method. It is found that the preprocessing of ultrasound images of the CCA with region identification and despeckleing followed by active contour segmentation algorithm can be successfully used in evaluating the intima–media thickness (IMT) of the normal and abnormal subjects. It is also estimated that the segmentation used in this paper results an intermethod error of 0.09 mm and a coefficient of variation of 18.9%, for the despeckled images. The magnitudes of the IMT values have been used to explore the rate of prediction of blockage existing in the cerebrovascular and cardiovascular pathologies and also hypertension and atherosclerosis.     

Automatic detection of the intima-media thickness in ultrasound images of the common carotid artery using neural networks

Atherosclerosis is the leading underlying pathologic process that results in cardiovascular diseases, which represents the main cause of death and disability in the world. The atherosclerotic process is a complex degenerative condition mainly affecting the medium- and large-size arteries, which begins in childhood and may remain unnoticed during decades. The intima-media thickness (IMT) of the common carotid artery (CCA) has emerged as one of the most powerful tool for the evaluation of preclinical atherosclerosis. IMT is measured by means of B-mode ultrasound images, which is a non-invasive and relatively low-cost technique. This paper proposes an effective image segmentation method for the IMT measurement in an automatic way. With this purpose, segmentation is posed as a pattern recognition problem, and a combination of artificial neural networks has been trained to solve this task. In particular, multi-layer perceptrons trained under the scaled conjugate gradient algorithm have been used. The suggested approach is tested on a set of 60 longitudinal ultrasound images of the CCA by comparing the automatic segmentation with four manual tracings. Moreover, the intra- and inter-observer errors have also been assessed. Despite of the simplicity of our approach, several quantitative statistical evaluations have shown its accuracy and robustness.     

Enhancement of the ultrasound images by modified anisotropic diffusion method

Speckle is a primary factor which degrades the contrast resolution and masks the meaningful texture information present in an ultrasound image. Its presence severely hampers the interpretation and analysis of ultrasound images. When speckle reduction technique is applied for visual enhancement of ultrasound images, it is to be kept in mind that blurring associated with speckle reduction should be less and fine details are properly enhanced. With these points in consideration, the modified speckle reduction anisotropic diffusion (MSRAD) method is proposed in the present study to improve the visual quality of the ultrasound images. In the proposed MSRAD method, the four neighboring pixel template in speckle reduction anisotropic diffusion (SRAD) method of Yu and Acton (IEEE Trans Image Process 11:1260–1270, 2002) have been replaced by a new template of larger number of neighboring pixels to calculate the diffusion term. To enhance visual quality of ultrasound images, nonquadratic regularization (Yu and Yadegar, Proceedings of the IEEE international conference on image processing, 2006) is incorporated with MSRAD method and accordingly changes in parameter settings have been made. The performance of MSRAD method was evaluated using clinical ultrasound images, interpretation by the medical experts and results of MSRAD method by subjective and objective criteria.     

How can the variability in ultrasound measurement of intima-media thickness be reduced? Studies of interobserver variability in carotid and femoral arteries.

A critical component in scientific studies of most biological variables is the variation or error in measurements which leads to non-identical results of repeated measurements from the same subject. The aim of this study was to investigate whether the interobserver error (s) in measurement of intima-media thickness (IMT) in carotid and femoral arteries could be decreased if the mean value obtained using two ultrasound images from each of the right and left arteries was used in the analyses instead of the mean value obtained using images from only the right artery. In addition, we wished to evaluate two different reading procedures, one based on manual tracing of echo interfaces and the other on automated edge detection. In a methodological study, 50 subjects were examined with ultrasound twice in the same day by two independent laboratory technologists. The ultrasound images were analysed in two ways: using a computerized manual tracing analysing system and an automated analysing system. When both right and left carotid arteries were examined (manual reading), the interobserver error was smaller than that determined for the examination of only the right artery, for IMTmean in both the common carotid artery (P = 0.06) and the carotid artery bulb (P < 0.05). The interobserver error was also significantly smaller for double-sided vs. one-sided examination with automated reading of IMTmean in the common carotid artery (P < 0.01) and in the carotid artery bulb (P < 0.01). The coefficient of variation (CV) for measurement in the common carotid artery decreased from 8.6% (one-sided, manual reading) to 5.3% (double-sided, automated reading). The interobserver error in measurement of IMT in the common femoral artery did not improve by examination of both right and left arteries. The results from this study show that the interobserver errors in measurement of IMT can be decreased by using ultrasound images from both the right and the left carotid arteries, and that the use of an automated analysing system greatly simplifies the reading of ultrasound images with sustained low variability.     

基于Rician分布的颈动脉内中膜厚度的测定

目的 颈动脉内中膜厚度是定量评价心血管疾病的核心指标之一。本文提出一种半自动基于超声影像的测量颈动脉内中膜厚度的计算机辅助方法,并在分割算法中引入了符合超声影像的Rician分布。方法 原始Chan-Vese模型较为适用于颈动脉血管壁的边界线的提取,但是原始模型假设图像斑点噪声符合分段常值分布,这对于本文所使用的颈动脉超声图像是不准确的。本文在原始的Chan-Vese模型上进行了相应的改进,提出超声斑点噪声符合Rician分布的Chan-Vese分割模型,然后通过二次分割提取内中膜边界,最后进行内中膜厚度测量。结果 将该方法用于实际的超声颈动脉图像,结果较为理想。结论 本方法能快速准确地提取颈动脉内中膜,并无须对原始图像做预处理。     

基于模糊增强的医学超声图像分割

医学超声图像因对比度较低、形成过程产生的独有的斑点噪声等影响了手动与计算机辅助分析的效果,尤其是影响了计算机定量测量的效果.为了改进超声图像的分割效果,首先要增强超声图像的对比度,本文提出了一种模糊增强算法对超声图像进行显著增强,然后利用马尔可夫随机场与最大后验概率理论对增强后的图像进行分割,得到了比较满意的分割效果.     

Automatic Active Contour-Based Segmentation and Classification of Carotid Artery Ultrasound Images

In this paper, we present automatic image segmentation and classification technique for carotid artery ultrasound images based on active contour approach. For early detection of the plaque in carotid artery to avoid serious brain strokes, active contour-based techniques have been applied successfully to segment out the carotid artery ultrasound images. Further, ultrasound images might be affected due to rotation, scaling, or translational factors during acquisition process. Keeping in view these facts, image alignment is used as a preprocessing step to align the carotid artery ultrasound images. In our experimental study, we exploit intima–media thickness (IMT) measurement to detect the presence of plaque in the artery. Support vector machine (SVM) classification is employed using these segmented images to distinguish the normal and diseased artery images. IMT measurement is used to form the feature vector. Our proposed approach segments the carotid artery images in an automatic way and further classifies them using SVM. Experimental results show the learning capability of SVM classifier and validate the usefulness of our proposed approach. Further, the proposed approach needs minimum interaction from a user for an early detection of plaque in carotid artery. Regarding the usefulness of the proposed approach in healthcare, it can be effectively used in remote areas as a preliminary clinical step even in the absence of highly skilled radiologists.     

Quantification of carotid vessel wall and plaque thickness change using 3D ultrasound images

Quantitative measurements of carotid plaque burden progression or regression are important in monitoring patients and in evaluation of new treatment options. 3D ultrasound (US) has been used to monitor the progression or regression of carotid artery plaques. This paper reports on the development and application of a method used to analyze changes in carotid plaque morphology from 3D US. The technique used is evaluated using manual segmentations of the arterial wall and lumen from 3D US images acquired in two imaging sessions. To reduce the effect of segmentation variability, segmentation was performed five times each for the wall and lumen. The mean wall and lumen surfaces, computed from this set of five segmentations, were matched on a point-by-point basis, and the distance between each pair of corresponding points served as an estimate of the combined thickness of the plaque, intima, and media (vessel-wall-plus-plaque thickness or VWT). The VWT maps associated with the first and the second US images were compared and the differences of VWT were obtained at each vertex. The 3D VWT and VWT-Change maps may provide important information for evaluating the location of plaque progression in relation to the localized disturbances of flow pattern, such as oscillatory shear, and regression in response to medical treatments.     

Automated carotid artery intima layer regional segmentation

Evaluation of the carotid artery wall is essential for the assessment of a patient's cardiovascular risk or for the diagnosis of cardiovascular pathologies. This paper presents a new, completely user-independent algorithm called carotid artery intima layer regional segmentation (CAILRS, a class of AtheroEdge? systems), which automatically segments the intima layer of the far wall of the carotid ultrasound artery based on mean shift classification applied to the far wall. Further, the system extracts the lumen-intima and media-adventitia borders in the far wall of the carotid artery. Our new system is characterized and validated by comparing CAILRS borders with the manual tracings carried out by experts. The new technique is also benchmarked with a semi-automatic technique based on a first-order absolute moment edge operator (FOAM) and compared to our previous edge-based automated methods such as CALEX (Molinari et al 2010 J. Ultrasound Med. 29 399-418, 2010 IEEE Trans. Ultrason. Ferroelectr. Freq. Control 57 1112-24), CULEX (Delsanto et al 2007 IEEE Trans. Instrum. Meas. 56 1265-74, Molinari et al 2010 IEEE Trans. Ultrason. Ferroelectr. Freq. Control 57 1112-24), CALSFOAM (Molinari et al Int. Angiol. (at press)), and CAUDLES-EF (Molinari et al J. Digit. Imaging (at press)). Our multi-institutional database consisted of 300 longitudinal B-mode carotid images. In comparison to semi-automated FOAM, CAILRS showed the IMT bias of -0.035 ± 0.186 mm while FOAM showed -0.016 ± 0.258 mm. Our IMT was slightly underestimated with respect to the ground truth IMT, but showed uniform behavior over the entire database. CAILRS outperformed all the four previous automated methods. The system's figure of merit was 95.6%, which was lower than that of the semi-automated method (98%), but higher than that of the other automated techniques.     

Semi-automated carotid lumen segmentation in computed tomography angiography images

Carotid artery stenosis causes narrowing of carotid lumens and may lead to brain infarction. The purpose of this study was to develop a semi-automated method of segmenting vessel walls, surrounding tissues, and more importantly, the carotid artery lumen by contrast computed tomography angiography (CTA) images and to define the severity of stenosis and present a three-dimensional model of the carotid for visual inspection. In vivo contrast CTA images of 14 patients (7 normal subjects and 7 patients undergoing endarterectomy) were analyzed using a multi-step segmentation algorithm. This method uses graph cut followed by watershed and Hessian based shortest path method in order to extract lumen boundary correctly without being corrupted in the presence of surrounding tissues. Quantitative measurements of the proposed method were compared with those of manual delineation by independent board-certified radiologists. The results were quantitatively evaluated using spatial overlap surface distance indices. A slightly strong match was shown in terms of dice similarity coefficient (DSC) = 0.87_x005f
0.08; mean surface distance (Dmsd) = 0.32
0.32; root mean squared surface distance (Drmssd) = 0.49
0.54 and maximum surface distance (Dmax) = 2.14
2.08 between manual and automated segmentation of common, internal and external carotid arteries, carotid bifurcation and stenotic artery, respectively. Quantitative measurements showed that the proposed method has high potential to segment the carotid lumen and is robust to the changes of the lumen diameter and the shape of the stenosis area at the bifurcation site. The proposed method for CTA images provides a fast and reliable tool to quantify the severity of carotid artery stenosis.     

A review of ultrasound common carotid artery image and video segmentation techniques

The determination of the wall thickness [intima–media thickness (IMT)], the delineation of the atherosclerotic carotid plaque, the measurement of the diameter in the common carotid artery (CCA), as well as the grading of its stenosis are important for the evaluation of the atherosclerosis disease. All these measurements are also considered to be significant markers for the clinical evaluation of the risk of stroke. A number of CCA segmentation techniques have been proposed in the last few years either for the segmentation of the intima–media complex (IMC), the lumen of the CCA, or for the atherosclerotic carotid plaque from ultrasound images or videos of the CCA. The present review study proposes and discusses the methods and systems introduced so far in the literature for performing automated or semi-automated segmentation in ultrasound images or videos of the CCA. These are based on edge detection, active contours, level sets, dynamic programming, local statistics, Hough transform, statistical modeling, neural networks, and an integration of the above methods. Furthermore, the performance of these systems is evaluated and discussed based on various evaluation metrics. We finally propose the best performing method that can be used for the segmentation of the IMC and the atherosclerotic carotid plaque in ultrasound images and videos. We end the present review study with a discussion of the different image and video CCA segmentation techniques, future perspectives, and further extension of these techniques to ultrasound video segmentation and wall tracking of the CCA. Future work on the segmentation of the CCA will be focused on the development of integrated segmentation systems for the complete segmentation of the CCA as well as the segmentation and motion analysis of the plaque and or the IMC from ultrasound video sequences of the CCA. These systems will improve the evaluation, follow up, and treatment of patients affected by advanced atherosclerosis disease conditions.     

CAUDLES-EF: Carotid Automated Ultrasound Double Line Extraction System Using Edge Flow

The evaluation of the carotid artery wall is essential for the diagnosis of cardiovascular pathologies or for the assessment of a patient’s cardiovascular risk. This paper presents a completely user-independent algorithm, which automatically extracts the far double line (lumen–intima and media–adventitia) in the carotid artery using an Edge Flow technique based on directional probability maps using the attributes of intensity and texture. Specifically, the algorithm traces the boundaries between the lumen and intima layer (line one) and between the media and adventitia layer (line two). The Carotid Automated Ultrasound Double Line Extraction System based on Edge-Flow (CAUDLES-EF) is characterized and validated by comparing the output of the algorithm with the manual tracing boundaries carried out by three experts. We also benchmark our new technique with the two other completely automatic techniques (CALEXia and CULEXsa) we previously published. Our multi-institutional database consisted of 300 longitudinal B-mode carotid images with normal and pathologic arteries. We compared our current new method with previous methods, and showed the mean and standard deviation for the three methods: CALEXia, CULEXsa, and CAUDLES-EF as 0.134 ± 0.088, 0.074 ± 0.092, and 0.043 ± 0.097 mm, respectively. Our IMT was slightly underestimated with respect to the ground truth IMT, but showed a uniform behavior over the entire database. Regarding the Figure of Merit (FoM), CALEXia and CULEXsa showed the values of 84.7% and 91.5%, respectively, while our new approach, CAUDLES-EF, performed the best at 94.8%, showing a good improvement compared to previous methods.     

基于深度学习的颈动脉超声图像内中膜厚度测量

目的 颈动脉血管内中膜厚度(IMT)是衡量动脉粥样硬化程度的重要标准.一般采用人工标定进行测量,该过程耗时且繁琐,由此提出一种总体性能较好的全自动分割(AS)算法.方法 该算法首先利用卷积神经网络(CNN)识别出颈动脉血管远端,进而提取包含颈动脉内膜、中膜部分的感兴趣区域(ROI).采用基于堆栈式自编码器(SAE)构造的模式分类器将ROI中的像素进行分类.最后利用分类区域的面积信息和位置信息对分类结果进行甄别,运用曲线拟合提取边界完成测量任务.结果 针对本研究所用图像库中的84幅颈动脉超声图像进行实验,金标准(GT)由两名专家4次测量的平均值产生,其与AS之间的绝对误差和标准差为(13.3±20.5) μm,协方差系数为0.990 7.结论 实验结果表明,此算法总体性能较好,能够实现超声颈动脉血管内中膜全自动、快速、准确分割,从而满足临床需要.     

Completely automated robust edge snapper for carotid ultrasound IMT measurement on a multi-institutional database of 300 images

The carotid intima-media thickness (IMT) is the most used marker for the progression of atherosclerosis and onset of cardiovascular diseases. Computer-aided measurements improve accuracy and precision, but usually require user interaction. In this paper we characterized a new and completely automated technique for carotid segmentation and IMT measurement based on the merits of two previously developed techniques. We used an integrated approach of intelligent image feature extraction and line fitting for automatically locating the carotid artery in the image frame, followed by wall interfaces extraction based on a Gaussian edge operator. We called our system—CARES. We validated CARES on a multi-institutional database of 300 carotid ultrasound images. The IMT measurement bias was 0.032 ± 0.141 mm. Our novel approach of CARES processed 96% of the images in the database taken from two different institutions. In order to evaluate its performance, the figure-of-merit (FoM) was defined as the percent ratio between the average IMT computed by CARES and the one obtained from manual tracings by expert sonographers. The estimated FoM by CARES was 95.7%. Comparing the IMT bias of CARES with our previously published method CALEX that showed an IMT bias equal to 0.099 ± 0.137 mm, CARES improved the IMT accuracy by 67%, while increasing the standard deviation by 3%. CARES could be a useful research tool for processing large datasets in multi-center studies involving atherosclerosis.     

颈动脉MR图像分割和三维重建在斑块定位中的应用

背景：医学图像的三维重建在医疗诊断、实验分析中起着越来越重要的作用,它是一项复杂的任务,其中目标图像的分割是首要且重要的一步。 目的：探索对颈动脉MR图像的图像分割及三维重建方法,并探讨三维模型在颈动脉斑块定位中的应用。 方法：选择3D TOF序列图像对其进行基于最大熵原理的阈值分割,并与普通方法的结果做比较;进一步用数学形态学分割方法提取出颈动脉;进行三维重建,利用三维模型进行斑块的初步定位。 结果与结论：基于最大熵原理的阈值分割适于对颈动脉3D TOF序列图像的分割,用数学形态学分割方法进行后续分割可得到目标图像。三维重建后的模型对于斑块定位有辅助作用。     

Fetal ultrasound image segmentation system and its use in fetal weight estimation

A semi-automated fetal ultrasound image segmentation system is developed to improve the estimation of fetal weight (EFW). Four standardized fetal parameters are measured by the proposed segmentation system: biparietal diameter, head circumference, abdominal circumference and femur length. Computerized measurements of 215 fetuses are compared with manual measurements in term of fitness analysis and difference analysis. Among 215 cases, computerized measurements of 103 fetuses within 3 days of delivery are utilized in the fetal weight estimation. The EFW based on computerized measurements and manual measurements are compared by using regression analysis, artificial neural network and support vector regression. By using different estimation methods, the computerized measurements decrease the EFW errors about 40–70 g. The lowest mean absolute percentage error of EFW decrease from 6.71% for manual measurements to 4.66% for computerized measurements. The proposed fetal ultrasound image segmentation system can provide more accurate EFW in antepartum examination.     

A non-invasive study of alterations of the carotid artery with age using ultrasound images

A region-based method for measurement of arterial diameter to find out the elasticity of the vessel is proposed in this paper. Arterial segments are studied by using images obtained through ultrasound scanning in B-mode. Pulsatile changes of the common carotid artery during diastole and systole are computed. To achieve this, thinned segmentation is done by suitably adjusting the contrast of the image. The diameter changes of the artery wall from the centre of artery are calculated. Fifty-three normal subjects with age group 20–40 years are taken for measurement. Measured diameter is plotted as a graph and pulsatile changes of the artery are obtained. Since no atherosclerotic lesions are detected in the studied subjects, it is suggested that the common carotid artery is a highly compliant artery with a strong alteration of viscoelastic properties with age.     

基于改进图割的超声瞳孔图像分割与直径测量

传统的瞳孔直径测量是通过医生手工标定,对于眼外伤和丧失意识的患者测量不方便。针对瞳孔直径测量的人工交互量大且测量鲁棒性不强的问题,采用图割算法分割瞳孔超声图像并测量瞳孔直径。对传统图割算法进行两个方面的改进,采用自适应阈值的区域生长代替人为种子点选取,在保证分割效果的基础上减少了图割的交互量;在能量函数的数据项部分增加图像的梯度信息,减少了原始算法分割结果中出现的小区域,增强了对弱边缘的分割。最后,对采集到的超声瞳孔图像进行自动分割、自动测量瞳孔直径,可以得到患者瞳孔的直径动态变化,给临床诊断提供依据。为了验证算法的有效性,对10位患者的动态瞳孔超声图像进行基于改进图割的瞳孔直径测量,并与医生的手动测量结果对比。结果表明,本方法的结果与医生手动测量结果的绝对误差小于0.2 mm,相关系数不小于0.83。通过改进图割算法,改善了分割效果,实现了超声瞳孔动态图像的自动直径测量,并可有效代替瞳孔直径的人工测量,减少人工交互量。     

Segmentation of the prostate from suprapubic ultrasound images

We present a technique for semiautomated segmentation of human prostates using suprapubic ultrasound (US) images. In this approach, a speckle reducing anisotropic diffusion (SRAD) is applied to enhance the images and the instantaneous coefficient of variation (ICOV) is utilized for edge detection. Segmentation is accomplished via a parametric active contour model in a polar coordinate system that is tailored to the application. The algorithm initially approximates the prostate boundary in two stages. First a primary contour is detected using an elliptical model, followed by a primary contour optimization using an area-weighted mean-difference binary flow geometric snake model. The algorithm was assessed by comparing the computer-derived contours with contours produced manually by three sonographers. The proposed method has application in radiation therapy planning and delivery, as well as in automated volume measurements for ultrasonic diagnosis. The average root mean square discrepancy between computed and manual outlines is less than the inter-observer variability. Furthermore, 76% of the computer-outlined contour is less than 1 sigma manual outline variance away from "true" boundary of prostate. We conclude that the methods developed herein possess acceptable agreement with manually contoured prostate boundaries and that they are potentially valuable tools for radiotherapy treatment planning and verification.