Breast tissue characterization using FARMA modeling of ultrasonic RF echo

A number of empirical and analytical studies demonstrated that the ultrasound RF echo reflected from tissue exhibits 1/f characteristics. In this paper, we propose to model 1/f characteristics of the ultrasonic RF echo by a novel parsimonious model, namely the fractional differencing auto regressive moving average (FARMA) process, and evaluated diagnostic value of model parameters for breast cancer malignancy differentiation. FARMA model captures the fractal and long term correlated nature of the backscattered speckle texture and facilitates robust efficient estimation of fractal parameters. In our study, in addition to the computer generated FARMA model parameters, we included patient age and radiologist's prebiopsy level of suspicion (LOS) as potential indicators of malignant and benign masses. We evaluated the performance of the proposed set of features using various classifiers and training methods using 120 in vivo breast images. Our study shows that the area under the receiver operating characteristics (ROC) curve of FARMA model parameters alone is superior to the area under the ROC curve of the radiologist's prebiopsy LOS. The area under the ROC curve of the three sets of features yields a value of 0.87, with a confidence interval of [0.85, 0.89], at a significance level of 0.05. Our results suggest that the proposed method of ultrasound RF echo model leads to parameters that can differentiate breast tumors with a relatively high precision. This set of RF echo features can be incorporated into a comprehensive computer-aided diagnostic system to aid physicians in breast cancer diagnosis.     

Performance evaluation of ultrasonic Nakagami image in tissue characterization

Conventional ultrasonic B-mode images qualitatively describe tissue structures but are unsuitable for quantitative analyses of scatterer properties. We have recently developed an ultrasonic parametric imaging technique based on the Nakagami statistical distribution that is able to quantify scatterer concentrations. The aim of the present study is to further explore both the behavior of a Nakagami image in characterizing different scatterer structures at different signal-to-noise ratios (SNRs) and the feasibility of Nakagami imaging using a general commercial ultrasound scanner for tissue examinations. Simulations, experiments on a tissue-mimicking phantom and in vitro measurements on a muscle tissue before and after microwave treatment were carried out. The SNR and contrast-to-noise ratio (CNR) were estimated to quantify image performance. The results demonstrate that a Nakagami image can differentiate different scatterer concentrations for single, hypoechoic and hyperechoic targets. Also, a Nakagami image, when combined with an ultrasound scanner, can complement the B-scan to characterize tissue and to identify the region of interest with a larger CNR. However, the noise effect can degrade the performance of a Nakagami image. When the signal SNR decreased to 15 dB in simulations and to 8 dB in experiments, the CNR of the hyperechoic Nakagami image decreased by 4% and 27%, respectively, and that of the hypoechoic one decreased by 42% and 80%, respectively. These results indicate that a Nakagami image behaves well in identifying regions with high scatterer concentrations but does not perform well when both the scatterer concentration and SNR are low.     

Added Value of Quantitative Ultrasound and Machine Learning in BI-RADS 4–5 Assessment of Solid Breast Lesions

The purpose of this study was to evaluate various combinations of 13 features based on shear wave elasticity (SWE), statistical and spectral backscatter properties of tissues, along with the Breast Imaging Reporting and Data System (BI-RADS), for classification of solid breast lesions at ultrasonography by means of random forests. One hundred and three women with 103 suspicious solid breast lesions (BI-RADS categories 4-5) were enrolled. Before biopsy, additional SWE images and a cine sequence of ultrasound images were obtained. The contours of lesions were delineated, and parametric maps of the homodyned-K distribution were computed on three regions: intra-tumoral, supra-tumoral and infra-tumoral zones. Maximum elasticity and total attenuation coefficient were also extracted. Random forests yielded receiver operating characteristic (ROC) curves for various combinations of features. Adding BI-RADS category improved the classification performance of other features. The best result was an area under the ROC curve of 0.97, with 75.9% specificity at 98% sensitivity.     

Computer-aided diagnosis for the classification of breast masses in automated whole breast ultrasound images

New automated whole breast ultrasound (ABUS) machines have recently been developed and the ultrasound (US) volume dataset of the whole breast can be acquired in a standard manner. The purpose of this study was to develop a novel computer-aided diagnosis system for classification of breast masses in ABUS images. One hundred forty-seven cases (76 benign and 71 malignant breast masses) were obtained by a commercially available ABUS system. Because the distance of neighboring slices in ABUS images is fixed and small, these continuous slices were used for reconstruction as three-dimensional (3-D) US images. The 3-D tumor contour was segmented using the level-set segmentation method. Then, the 3-D features, including the texture, shape and ellipsoid fitting were extracted based on the segmented 3-D tumor contour to classify benign and malignant tumors based on the logistic regression model. The Student’s t test, Mann-Whitney U test and receiver operating characteristic (ROC) curve analysis were used for statistical analysis. From the Az values of ROC curves, the shape features (0.9138) are better than the texture features (0.8603) and the ellipsoid fitting features (0.8496) for classification. The difference was significant between shape and ellipsoid fitting features (p = 0.0382). However, combination of ellipsoid fitting features and shape features can achieve a best performance with accuracy of 85.0% (125/147), sensitivity of 84.5% (60/71), specificity of 85.5% (65/76) and the area under the ROC curve Az of 0.9466. The results showed that ABUS images could be used for computer-aided feature extraction and classification of breast tumors. (E-mail: rfchang@csie.ntu.edu.tw)     

基于分形特征序列的乳腺X线图像分类方法

目的表征乳腺图像中肿块部分纹理特征,通过纹理分析实现乳腺图像中肿块部分与正常腺体部分的分类。方法应用分形特征值表征乳腺图像纹理特征,利用多级分形特征提取法将乳腺图像分解成一系列细节图像,提取出多个分形特征值;利用分类精度、ROC曲线及曲线下面积(AUC)进行特征选择构建分形特征序列,最后应用支持向量机(SVM)方法进行分类。结果对60幅图像的可疑病变区域进行分形特征序列提取分析,SVM交叉验证分类精度达84.50%。结论基于分形维数的乳腺图像分类方法不仅能对肿块与正常腺体进行图像分类,还可有效表征乳腺图像的纹理信息,有助于提高乳腺肿块诊断的准确率。     

Watershed segmentation for breast tumor in 2-D sonography

Automatic contouring for breast tumors using medical ultrasound (US) imaging may assist physicians without relevant experience, in making correct diagnoses. This study integrates the advantages of neural network (NN) classification and morphological watershed segmentation to extract precise contours of breast tumors from US images. Textural analysis is employed to yield inputs to the NN to classify ultrasonic images. Autocovariance coefficients specify texture features to classify breasts imaged by US using a self-organizing map (SOM). After the texture features in sonography have been classified, an adaptive preprocessing procedure is selected by SOM output. Finally, watershed transformation automatically determines the contours of the tumor. In this study, the proposed method was trained and tested using images from 60 patients. The results of computer simulations reveal that the proposed method always identified similar contours and regions-of-interest (ROIs) to those obtained by manual contouring (by an experienced physician) of the breast tumor in ultrasonic images. As US imaging becomes more widespread, a functional automatic contouring method is essential and its clinical application is becoming urgent. Such a method provides robust and fast automatic contouring of US images. This study is not to emphasize that the automatic contouring technique is superior to the one undertaken manually. Both automatic and manual contours did not, after all, necessarily result in the same factual pathologic border. In computer-aided diagnosis (CAD) applications, automatic segmentation can save much of the time required to sketch a precise contour, with very high stability.     

Ultrasonic Nakagami Imaging: A Strategy to Visualize the Scatterer Properties of Benign and Malignant Breast Tumors

Previous studies have demonstrated the usefulness of the Nakagami parameter in characterizing breast tumors by ultrasound. However, physicians or radiologists may need imaging tools in a clinical setting to visually identify the properties of breast tumors. This study proposed the ultrasonic Nakagami image to visualize the scatterer properties of breast tumors and then explored its clinical performance in classifying benign and malignant tumors. Raw data of ultrasonic backscattered signals were collected from 100 patients (50 benign and 50 malignant cases) using a commercial ultrasound scanner with a 7.5 MHz linear array transducer. The backscattered signals were used to form the B-scan and the Nakagami images of breast tumors. For each tumor, the average Nakagami parameter was calculated from the pixel values in the region-of-interest in the Nakagami image. The receiver operating characteristic (ROC) curve was used to evaluate the clinical performance of the Nakagami image. The results showed that the Nakagami image shadings in benign tumors were different from those in malignant cases. The average Nakagami parameters for benign and malignant tumors were 0.69 ± 0.12 and 0.55 ± 0.12, respectively. This means that the backscattered signals received from malignant tumors tend to be more pre-Rayleigh distributed than those from benign tumors, corresponding to a more complex scatterer arrangement or composition. The ROC analysis showed that the area under the ROC curve was 0.81 ± 0.04 and the diagnostic accuracy was 82%, sensitivity was 92% and specificity was 72%. The results showed that the Nakagami image is useful to distinguishing between benign and malignant breast tumors.     

Quantitative evaluation of diagnostic information around the contours in ultrasound images

Purpose To develop a new contour extraction method for identifying abnormal tissue. Methods We combined two techniques: logarithmic K distribution of a scattering model (method 1) and regional discrimination using the characteristics of local ultrasound images (method 2) into an integrated method (method 3) that provides accurate contours, which are essential for quantitizing border information. Results The diagnostic tissue information around the border of an image can be characterized by its shape and texture statistics. The degrees of circularity and irregularity and the depth–width ratio were calculated for the extracted contours of breast tumors. In addition, gradients, separability, and variance between the two regions along the contour and the area and variance of the internal echoes, were calculated as indices of diagnostic criteria of breast tumors. The quantitized indices were able to discriminate among cysts, fibroadenomas, and cancer. Conclusion In many ultrasound images of breast tumors, the combined techniques, the variance ratio of the logarithmic K distribution to the logarithmic Rayleigh distribution and the multilevel technique with local image information can effectively extract abnormal tissue contours.     

影像学诊断评价中的参数法ROC曲线分析

目的 探讨采用ROC曲线参数分析法对影像学分类诊断结果进行评价的价值,并介绍ROC曲线参数分析软件ROCKIT。 方法 2名医师分别对60幅肺部CT图像进行肺结节良恶性5级分类诊断。分别用ROCKIT软件和SPSS软件对他们的诊断结果进行参数法和非参数法ROC曲线分析。 结果 对2名医师的诊断结果利用ROCKIT进行参数法ROC分析时,ROC曲线下面积分别为0.940±0.039和0.785±0.075(Z=2.056, P=0.040),利用SPSS进行非参数估计时结果分别为0.913±0.042和0.771±0.075。通过ROCKIT软件可绘制光滑的拟合ROC曲线,SPSS软件可绘制不光滑的经验ROC曲线。 结论 当有序分类资料样本量适中时,参数估计一般均无偏倚,非参数估计的结果可能小于真实值;ROCKIT软件是双正态参数法ROC曲线分析的有力工具。     

基于肿瘤全域表观扩散系数纹理分析预测上皮性卵巢癌复发的研究

目的:探讨基于肿瘤全域的表观扩散系数(Apparent diffusion coefficient,ADC)纹理分析对上皮性卵巢癌(Epithelial ovarian carcinoma,EOC)复发的预测价值。方法 :回顾性分析49例经病理证实为EOC患者的术前DWI成像(b=0、800 s/mm^2),利用后处理软件在ADC图上绘制全瘤的感兴趣区,分析提取出纹理参数,包括偏度、峰度、熵值、惰性、相关性、对比度、变异等共77个参数。采用多因素Logistic回归分析确定可作为复发的最佳预测因素,绘制ROC曲线评价其预测效能。结果:两组患者肿瘤大小及腹水复发组均高于非复发组,差异有统计学意义(P<0.05),FIGO分期两组间差异有统计学意义(P<0.05)。复发组惰性、对比度、变异、熵值显著高于非复发组,峰度、第10百分位数、第25百分位数、相关性显著低于非复发组,差异均有统计学意义(P<0.05)。ROC曲线分析显示峰度、惰性、相关性、肿瘤大小、FIGO分期联合预测复发的曲线下面积最大,为0.929。结论:基于全肿瘤容积的ADC纹理分析有助于预测EOC患者复发。     

一种使用膨胀气球模型的Snakes多目标分割方法

目的为实现一种有效的基于Snakes的多目标医学图像分割算法。方法通过模拟气球在含多个物体的封闭空间内的膨胀,来实现Snake曲线的拓扑形变。算法使用一个燃烧区域滞后跟踪Snake曲线运动来给出其演化停止条件,然后忽略停止条件并继续演化Snake曲线,就能完成燃烧而得到一个连通区域。提取出已燃烧区域的轮廓可给出与各分割目标对应的子Snake。结果所提出的算法能够正确分割出医学图像中多目标对象的轮廓。结论此基于模型的分割算法原理明确且易于实现,具有较好的实用性。     

基于梯度向量流snake模型的可视人体图像骨组织分割

为克服传统snake模型不能适应结构复杂的解剖图像、初始轮廓必须充分接近物体边缘的缺点,本研究将基于梯度向量流(GVF)的snake模型用于可视人计划(VHP)图像中骨组织的分割,并修改梯度向量流(GVF)模型,使之适用于彩色图像;针对VHP彩色解剖图像数据量巨大的特点,将多尺度思想应用到snake模型中,以提高处理速度.这种方法提高了计算效率,节省了70%分割时间,得到了理想的精确度,对研究解剖结构、组织定量化测定等具有较高的实用意义.     

小鼠原位移植性肝癌模型磁共振扩散加权成像实验研究

目的探讨1.5T磁共振扫描仪对小鼠原位移植性肝癌模型扩散加权成像(DWI)显示能力及较佳b值选择。方法对22只小鼠原位移植性肝癌模型进行多b值DWI成像及T2WI成像。计算不同图像中肿瘤信噪比(SNR)、肿瘤与肝脏对比噪声比(CNR)及信号强度比(SIR)等数据,并进行统计学分析。结果DWI成像能显示T2WI所显示的所有肿瘤。DWI显示病灶范围与T2WI无统计学差异(F=0.048,P>0.05)。DWI图像中肿瘤SNR、肿瘤与肝脏CNR及SIR随b值升高而降低,均高于T2WI图像,与T2WI间有统计学差异(FSNR=58.012,FCNR=47.743,FSIR=12.353,各组P<0.05)。b值600s/mm2与900s/mm2间肿瘤SNR、肿瘤与肝脏CNR无统计学差异,其他各b值间肿瘤SNR、肿瘤与肝脏CNR均有统计学差异。b值300、600、900s/mm2间及300与2000s/mm2间肿瘤与肝脏SIR无统计学差异,其他各b值间肿瘤与肝脏SIR均有统计学差异。结论1.5T磁共振可以对小鼠原位移植性肝癌模型进行DWI成像,b=900s/mm2是DWI成像较佳b值。     

Quantitative analysis of ultrasonic B-mode images

Various sources of variability, such as speckle noise, depth dependence and inhomogeneous intervening tissue, are involved in B-mode images, even when using the same ultrasonic equipment with fixed settings. The behavior of these sources of variability was investigated by texture analysis of images obtained from simulations and from a tissue-mimicking phantom, a normal adult liver and a pediatric renal (Wilms') tumor. First-order statistics (MEAN and SNR) and second-order statistics from the co-occurrence matrix (ENT and COR) were calculated. In a phantom, the SNR and ENT show a clear depth dependence. In biological tissue, the variability is mainly caused by the speckle noise and inhomogeneous intervening tissue. In addition, almost the entire range of the COR feature is present in images of liver and tumor. Furthermore, all the features calculated in windows of 1 cm2 exhibit an overlap among the different media. With the second-order features, it is possible to discriminate 85% reliable (average) between the normal, adult, liver and the pediatric renal tumor above a window size of 9 cm2. The SNR can not discriminate between these tissues. The maximum resolution of 9 cm2 reveals a serious limitation of parametric imaging. Finally, the features reproduce well in the case of follow-up of an abdominal tumor during chemotherapy.     

常规超声与S-Detect技术在乳腺病灶良恶性鉴别诊断中的效能比较

目的探讨常规超声与S-Detect技术在乳腺病灶良恶性鉴别诊断中的效能比较。 方法选取2018年6月至7月在中国医科大学附属第一医院经手术病理证实的367例乳腺病灶患者，共468个病灶。所有病灶分别由3名不同年资（1、4、7年）乳腺超声医师进行二维超声成像（静态图像及动态图像）的两次乳腺超声影像报告与数据系统（BI-RADS）分类以及计算机S-Detect分类，通过绘制不同BI-RADS分类诊断组的ROC曲线，确定最佳诊断界值，以进行各组BI-RADS分类的良恶性统计，以病理结果为"金标准"，应用诊断试验四格表分别计算不同BI-RADS分类诊断组及S-Detect分类组对乳腺病灶良恶性诊断的敏感度、特异度、准确性、阳性预测值及阴性预测值，采用χ²检验分别将各BI-RADS分类组诊断效能与S-Detect分类组进行比较。绘制各组的ROC曲线，应用Z检验分别将各BI-RADS分类组ROC曲线下面积与S-Detect分类组进行比较。 结果468个乳腺病灶术后病理诊断良性313个，恶性155个。通过绘制不同BI-RADS分类诊断组的ROC曲线，确定最佳诊断界值为BI-RADS 4a类。S-Detect分类诊断敏感度93.5%明显高于低年资医师静态图像BI-RADS分类诊断69.0%及低年资医师动态录像BI-RADS分类诊断72.3%，差异有统计学意义（χ²=30.627、24.785，P均<0.001），S-Detect分类诊断特异度83.7%，明显低于中年资医师动态图像BI-RADS分类诊断92.0%，差异有统计学意义（χ²=10.124，P=0.001），其余各诊断效能差异均无统计学意义（P均>0.05）。S-Detect分类诊断曲线下面积0.917高于低年资医师两次（静态图像及动态图像）BI-RADS分类0.790、0.803，差异均有统计学意义（Z=5.271、4.693，P均<0.0001）；S-Detect分类诊断曲线下面积与中年资医师静态BI-RADS分类0.917比较，差异无统计学意义（P>0.05），低于中年资医师动态BI-RADS分类0.941，差异有统计学意义（Z=4.327，P<0.0001）；S-Detect分类诊断曲线下面积均低于高年资医师两次BI-RADS分类0.946、0.959，差异均有统计学意义（Z=4.225、5.477，P均<0.0001）。 结论S-Detect分类技术可以达到中年资医师静态图像BI-RADS分类的诊断水平，但低于其动态图像的诊断水平。     

Quantitative Ultrasound Monitoring of Breast Tumour Response to Neoadjuvant Chemotherapy: Comparison of Results Among Clinical Scanners

Quantitative ultrasound (QUS) techniques have been demonstrated to detect cell death in vitro and in vivo. Recently, multi-feature classification models have been incorporated into QUS texture-feature analysis methods to increase further the sensitivity and specificity of detecting treatment response in locally advanced breast cancer patients. To effectively incorporate these analytic methods into clinical applications, QUS and texture-feature estimations should be independent of data acquisition systems. The study here investigated the consistencies of QUS and texture-feature estimation techniques relative to several factors. These included the ultrasound system properties, the effects of tissue heterogeneity and the effects of these factors on the monitoring of response to neoadjuvant chemotherapy. Specifically, tumour-response–detection performance based on QUS and texture parameters using two clinical ultrasound systems was compared. Observed variations in data between the systems were small and the results exhibited good agreement in tumour response predictions obtained from both ultrasound systems. The results obtained in this study suggest that tissue heterogeneity was a dominant feature in the parameters measured with the two different ultrasound systems; whereas differences in ultrasound system beam properties only exhibited a minor impact on texture features. The McNemar statistical test performed on tumour response prediction results from the two systems did not reveal significant differences. Overall, the results in this study demonstrate the potential to achieve reliable and consistent QUS and texture-based analyses across different ultrasound imaging platforms.     

超声影像组学标签对乳腺癌腋窝淋巴结转移的预测价值

目的探讨基于常规超声的影像组学特征预测乳腺癌腋窝淋巴结转移的应用价值。 方法回顾性收集2020年1月至2020年10月于中山大学肿瘤防治中心就诊经手术病理确诊的265例乳腺癌患者的临床资料和术前超声图像,按超声检查时间顺序,将患者分为训练集（159例）和验证集（106例）。应用ImageJ软件手动勾画病灶区域,使用Pyradiomics从每个病灶区域中提取影像组学特征,采用多种方法逐步筛选特征,应用Logistic回归构建预测乳腺癌腋窝淋巴结转移的超声影像组学标签。在训练集和验证集上采用ROC曲线、校准曲线和决策曲线评估超声影像组学标签预测乳腺癌腋窝淋巴结转移的效能。 结果最终筛选出8个关键超声影像组学特征用于构建超声影像组学标签。该标签在训练集和验证集中预测乳腺癌腋窝淋巴结转移的ROC曲线下面积分别为0.805（95%CI：0.734~0.876）、0.793（95%CI：0.706~0.880）。在校准曲线中,该标签在训练集和验证集均表现出较好的校准度（P=0.592、0.593）,决策曲线分析进一步表明了该标签具有一定的临床实用性。 结论基于超声的影像组学标签在预测乳腺癌腋窝淋巴结转移方面具有一定价值,可为治疗前乳腺癌的准确分期以及治疗方案的合理选择提供参考依据。     

The Acceptability of Iterative Reconstruction Algorithms in Head CT: An Assessment of Sinogram Affirmed Iterative Reconstruction (SAFIRE) vs. Filtered Back Projection (FBP) Using Phantoms

BackgroundComputed tomography (CT) is the primary imaging investigation for many neurologic conditions with a proportion of patients incurring cumulative doses. Iterative reconstruction (IR) allows dose optimization, but head CT presents unique image quality complexities and may lead to strong reader preferences.ObjectivesThis study evaluates the relationships between image quality metrics, image texture, and applied radiation dose within the context of IR head CT protocol optimization in the simulated patient setting. A secondary objective was to determine the influence of optimized protocols on diagnostic confidence using a custom phantom.Methods and SettingA three-phase phantom study was performed to characterize reconstruction methods at the local reference standard and a range of exposures. CT numbers and pixel noise were quantified supplemented by noise uniformity, noise power spectrum, contrast-to-noise ratio (CNR), high- and low-contrast resolution. Reviewers scored optimized protocol images based on established reporting criteria.ResultsIncreasing strengths of IR resulted in lower pixel noise, lower noise variance, and increased CNR. At the reference standard, the image noise was reduced by 1.5 standard deviation and CNR increased by 2.0. Image quality was maintained at ≤24% relative dose reduction. With the exception of image sharpness, there were no significant differences between grading for IR and filtered back projection reconstructions.ConclusionsIR has the potential to influence pixel noise, CNR, and noise variance (image texture); however, systematically optimized IR protocols can maintain the image quality of filtered back projection. This work has guided local application and acceptance of lower dose head CT protocols.     

Texture analysis of breast tumors on sonograms.

We performed a feasibility study to determine if the texture features extracted from sonograms can be used to predict malignant or benign breast pathology by the proposed artificial neural network and to compare the diagnostic results with the radiologists' results. A total of 1,020 images (4 different rectangular regions from the 2 orthogonal imaging planes of each tumor) from 255 patients were used as samples. When a sonogram was performed, 1 physician identified the region of interest in the sonogram; then, a neural network model, using 24 autocorrelation texture features, classified the tumor as benign or malignant. Three radiologists who were unfamiliar with the samples also classified these images. The receiver operating characteristic (ROC) area index for the proposed neural network system is 0.9840 +/- 0.0072. The neural network identified 35 of 36 malignancies and 211 of 219 benign tumors using all 4 regions of interest. The radiologists, on average, identified 19 of 36 malignancies, with 12 tumors called indeterminate and 4 tumors called benign. We conclude that benign and malignant breast tumors can be distinguished using interpixel correlation in digital ultrasonic images.