Ultrasound breast tumor image computer-aided diagnosis with texture and morphological features

RATIONALE AND OBJECTIVES: Computer-aided diagnosis (CAD) systems based on shape analysis have been proved to be highly accurate in evaluating breast tumors. However, it takes considerable time to train the classifier and diagnose breast tumors, because extracting morphologic features require a lot of computation. Hence, to develop a highly accurate and quick CAD system, we combined the texture and morphologic features of ultrasound breast tumor imaging to evaluate breast tumors in this study. MATERIALS AND METHODS: This study evaluated 210 ultrasound breast tumor images, including 120 benign tumors and 90 malignant tumors. The breast tumors were segmented automatically by the level set method. The autocovariance texture features and solidity morphologic feature were extracted, and a support vector machine was used to identify the tumor as benign or malignant. RESULTS: The accuracy of the proposed diagnostic system for classifying breast tumors was 92.86%, the sensitivity was 94.44%, the specificity was 91.67%, the positive predictive value was 89.47%, and the negative predictive value was 95.65%. In addition, the proposed system reduced the training time compared to systems based only on the morphologic analysis. CONCLUSIONS: The CAD system based on texture and morphologic analysis can differentiate benign from malignant breast tumors with high accuracy and short training time. It is therefore clinically useful to reduce the number of biopsies of benign lesions and offer a second reading to assist inexperienced physicians in avoiding misdiagnosis.     

Computer-aided diagnosis with textural features for breast lesions in sonograms

Rationale and objectives

Computer-aided diagnosis (CAD) systems provided second beneficial support reference and enhance the diagnostic accuracy. This paper was aimed to develop and evaluate a CAD with texture analysis in the classification of breast tumors for ultrasound images.

Materials and methods

The ultrasound (US) dataset evaluated in this study composed of 1020 sonograms of region of interest (ROI) subimages from 255 patients. Two-view sonogram (longitudinal and transverse views) and four different rectangular regions were utilized to analyze each tumor. Six practical textural features from the US images were performed to classify breast tumors as benign or malignant. However, the textural features always perform as a high dimensional vector; high dimensional vector is unfavorable to differentiate breast tumors in practice. The principal component analysis (PCA) was used to reduce the dimension of textural feature vector and then the image retrieval technique was performed to differentiate between benign and malignant tumors. In the experiments, all the cases were sampled with k-fold cross-validation (k = 10) to evaluate the performance with receiver operating characteristic (ROC) curve.

Results

The area (A_Z) under the ROC curve for the proposed CAD system with the specific textural features was 0.925 ± 0.019. The classification ability for breast tumor with textural information is satisfactory.

Conclusions

This system differentiates benign from malignant breast tumors with a good result and is therefore clinically useful to provide a second opinion.     

Discrimination of MR images of breast masses with fractal-interpolation function models

RATIONALE AND OBJECTIVES: The authors evaluated the feasibility of using statistical fractal-dimension features to improve discrimination between benign and malignant breast masses at magnetic resonance (MR) imaging. MATERIALS AND METHODS: The study evaluated MR images of 32 malignant and 20 benign breast masses from archived data at the University of Pennsylvania Medical Center. The test set included four cases that were difficult to evaluate on the basis of border characteristics. All diagnoses had been confirmed at excisional biopsy. The fractal-dimension feature was computed as the mean of a sample space of fractal-dimension estimates derived from fractal interpolation function models. To evaluate the performance of the fractal-dimension feature, the classification effectiveness of five expert-observer architectural features was compared with that of the fractal dimension combined with four expert-observer features. Feature sets were evaluated with receiver operating characteristic analysis. Discrimination analysis used artificial neural networks and logistic regression. Robustness of the fractal-dimension feature was evaluated by determining changes in discrimination when the algorithm parameters were perturbed. RESULTS: The combination of fractal-dimension and expert-observer features provided a statistically significant improvement in discrimination over that achieved with expert-observer features alone. Perturbing selected parameters in the fractal-dimension algorithm had little effect on discrimination. CONCLUSION: A statistical fractal-dimension feature appears to be useful in distinguishing MR images of benign and malignant breast masses in cases where expert radiologists may have difficulty. The statistical approach to estimating the fractal dimension appears to be more robust than other fractal measurements on data-limited medical images.     

Combining support vector machine with genetic algorithm to classify ultrasound breast tumor images

To promote the classification accuracy and decrease the time of extracting features and finding (near) optimal classification model of an ultrasound breast tumor image computer-aided diagnosis system, we propose an approach which simultaneously combines feature selection and parameter setting in this study.In our approach ultrasound breast tumors were segmented automatically by a level set method. The auto-covariance texture features and morphologic features were first extracted following the use of a genetic algorithm to detect significant features and determine the near-optimal parameters for the support vector machine (SVM) to identify the tumor as benign or malignant.The proposed CAD system can differentiate benign from malignant breast tumors with high accuracy and short feature extraction time. According to the experimental results, the accuracy of the proposed CAD system for classifying breast tumors is 95.24% and the computing time of the proposed system for calculating features of all breast tumor images is only 8% of that of a system without feature selection. Furthermore, the time of finding (near) optimal classification model is significantly than that of grid search. It is therefore clinically useful in reducing the number of biopsies of benign lesions and offers a second reading to assist inexperienced physicians in avoiding misdiagnosis.     

Performance of breast ultrasound computer-aided diagnosis: dependence on image selection

RATIONALE AND OBJECTIVES: The automated classification of sonographic breast lesions is generally accomplished by extracting and quantifying various features from the lesions. The selection of images to be analyzed, however, is usually left to the radiologist. Here we present an analysis of the effect that image selection can have on the performance of a breast ultrasound computer-aided diagnosis system. MATERIALS AND METHODS: A database of 344 different sonographic lesions was analyzed for this study (219 cysts/benign processes, 125 malignant lesions). The database was collected in an institutional review board-approved, Health Insurance Portability and Accountability Act-compliant manner. Three different image selection protocols were used in the automated classification of each lesion: all images, first image only, and randomly selected images. After image selection, two different protocols were used to classify the lesions: (a) the average feature values were input to the classifier or (b) the classifier outputs were averaged together. Both protocols generated an estimated probability of malignancy. Round-robin analysis was performed using a Bayesian neural network-based classifier. Receiver-operating characteristic analysis was used to evaluate the performance of each protocol. Significance testing of the performance differences was performed via 95% confidence intervals and noninferiority tests. RESULTS: The differences in the area under the receiver-operating characteristic curves were never more than 0.02 for the primary protocols. Noninferiority was demonstrated between these protocols with respect to standard input techniques (all images selected and feature averaging). CONCLUSION: We have proved that our automated lesion classification scheme is robust and can perform well when subjected to variations in user input.     

基于灰度共生矩阵的乳腺钼靶图像分析

目的 应用灰度共生矩阵对乳腺钼靶图像进行纹理分析,自动分类识别乳腺肿块,实现乳腺肿瘤的辅助检测.资料与方法 纳入60例乳腺钼靶图像,其中正常乳腺组织20例,良恶性乳腺肿块各20例.对图像进行预处理后,计算各感兴趣区基于灰度共生矩阵的纹理特征值,采用支持向量机和概率神经网络分别对肿块进行分类.结果 三组各项纹理特征参数间差异有统计学意义(P＜0.05);d=2时支持向量机的三组分类准确率为91.67％、86.73％、95.00％,SPREAD值取0.1时概率神经网络的三组分类准确率为79.22％、81.77％、81.13％.结论 文中计算的纹理特征参数对乳腺肿块的良恶性判别有较显著的规律,支持向量机的分类准确率比概率神经网络的分类准确率高,该方法可成为乳腺肿瘤良恶性辅助诊断的有效方法之一.     

Computer-aided diagnosis applied to US of solid breast nodules by using neural networks.

PURPOSE: To increase the capabilities of ultrasonographic (US) technology for the differential diagnosis of solid breast tumors by using a neural network. MATERIALS AND METHODS: One hundred forty US images of solid breast nodules were evaluated. When a sonogram was obtained, an analog video signal from the VCR output of the scanner was transmitted to a notebook computer. A frame grabber connected to the printer port of the computer was then used to digitize the data. The suspicious tumor region on the digitized US image was manually selected. The texture information of the subimage was extracted, and a neural network classifier with autocorrelation features was used to classify the tumor as benign or malignant. In this experiment, 140 pathologically proved tumors (52 malignant and 88 benign tumors) were sampled with k-fold cross-validation (k = 10) to evaluate the performance with receiver operating characteristic curves. RESULTS: The accuracy of neural networks for classifying malignancies was 95.0% (133 of 140 tumors), the sensitivity was 98% (51 of 52), the specificity was 93% (82 of 88), the positive predictive value was 89% (51 of 57), and the negative predictive value was 99% (82 of 83). CONCLUSION: This system differentiated solid breast nodules with relatively high accuracy and helped inexperienced operators to avoid misdiagnoses. Because the neural network is trainable, it could be optimized if a larger set of tumor images is supplied.     

Support vector machines in sonography: application to decision making in the diagnosis of breast cancer

We evaluated a series of pathologically proven breast tumors using the support vector machine (SVM) in the differential diagnosis of solid breast tumors. This study evaluated two ultrasonic image databases, i.e., DB1 and DB2. The DB1 contained 140 ultrasonic images of solid breast nodules (52 malignant and 88 benign). The DB2 contained 250 ultrasonic images of solid breast nodules (35 malignant and 215 benign). The physician-located regions of interest (ROI) of sonography and textual features were utilized to classify breast tumors. An SVM classifier using interpixel textual features classified the tumor as benign or malignant. The receiver operating characteristic (ROC) area index for the proposed system on the DB1 and the DB2 are 0.9695+/-0.0150 and 0.9552+/-0.0161, respectively. The proposed system differentiates solid breast nodules with a relatively high accuracy and helps inexperienced operators avoid misdiagnosis. The main advantage in the proposed system is that the training procedure of SVM was very fast and stable. The training and diagnosis procedure of the proposed system is almost 700 times faster than that of multilayer perception neural networks (MLPs). With the growth of the database, new ultrasonic images can be collected and used as reference cases while performing diagnoses. This study reduces the training and diagnosis time dramatically.     

Volumetric texture analysis of breast lesions on contrast-enhanced magnetic resonance images.

Automated image analysis aims to extract relevant information from contrast-enhanced magnetic resonance images (CE-MRI) of the breast and improve the accuracy and consistency of image interpretation. In this work, we extend the traditional 2D gray-level co-occurrence matrix (GLCM) method to investigate a volumetric texture analysis approach and apply it for the characterization of breast MR lesions. Our database of breast MR images was obtained using a T1-weighted 3D spoiled gradient echo sequence and consists of 121 biopsy-proven lesions (77 malignant and 44 benign). A fuzzy c-means clustering (FCM) based method is employed to automatically segment 3D breast lesions on CE-MR images. For each 3D lesion, a nondirectional GLCM is then computed on the first postcontrast frame by summing 13 directional GLCMs. Texture features are extracted from the nondirectional GLCMs and the performance of each texture feature in the task of distinguishing between malignant and benign breast lesions is assessed by receiver operating characteristics (ROC) analysis. Our results show that the classification performance of volumetric texture features is significantly better than that based on 2D analysis. Our investigations of the effects of various of parameters on the diagnostic accuracy provided means for the optimal use of the approach.     

Solid breast masses: classification with computer-aided analysis of continuous US images obtained with probe compression

PURPOSE: To prospectively evaluate the accuracy of continuous ultrasonographic (US) images obtained during probe compression and computer-aided analysis for classification of biopsy-proved (reference standard) benign and malignant breast tumors. MATERIALS AND METHODS: This study was approved by the local ethics committee, and informed consent was obtained from all included patients. Serial US images of 100 solid breast masses (60 benign and 40 malignant tumors) were obtained with US probe compression in 86 patients (mean age, 45 years; range, 20-67 years). After segmentation of tumor contours with the level-set method, three features of strain on tissue from probe compression--contour difference, shift distance, area difference--and one feature of shape--solidity-were computed. A maximum margin classifier was used to classify the tumors by using these four features. The Student t test and receiver operating characteristic curve analysis were used for statistical analysis. RESULTS: The mean values of contour difference, shift distance, area difference, and solidity were 3.52% +/- 2.12 (standard deviation), 2.62 +/- 1.31, 1.08% +/- 0.85, and 1.70 +/- 1.85 in malignant tumors and 9.72% +/- 4.54, 5.04 +/- 2.79, 3.17% +/- 2.86, and 0.53 +/- 0.63 in benign tumors, respectively. Differences with P < .001 were statistically significant for all four features. Area under the receiver operating characteristic curve (A(Z)) values for contour difference, shift distance, area difference, and solidity were 0.88, 0.85, 0.86, and 0.79, respectively. The A(Z) value of three features of strain was significantly higher than that of the feature of shape (P < .01). The accuracy, sensitivity, specificity, and positive and negative predictive values of US classifications that were based on values for these four features were 87.0% (87 of 100), 85% (34 of 40), 88% (53 of 60), 83% (34 of 41), and 90% (53 of 59), respectively, with an A(Z) value of 0.91. CONCLUSION: Continuous US images obtained with probe compression and computer-aided analysis can aid in classification of benign and malignant breast tumors.     

Performance of computer-aided diagnosis in the interpretation of lesions on breast sonography

RATIONALE AND OBJECTIVES: To investigate the potential usefulness of computer-aided diagnosis as a tool for radiologists in the characterization and classification of mass lesions on ultrasound. MATERIALS AND METHODS: Previously, a computerized method for the automatic classification of breast lesions on ultrasound was developed. The computerized method includes automatic segmentation of the lesion from the ultrasound image background and automatic extraction of four features related to lesion shape, margin, texture, and posterior acoustic behavior. In this study, the effectiveness of the computer output as an aid to radiologists in their ability to distinguish between malignant and benign lesions, and in their patient management decisions in terms of biopsy recommendation are evaluated. Six expert mammographers and six radiologists in private practice at an institution accredited by the American Ultrasound Institute of Medicine participated in the study. Each observer first interpreted 25 training cases with feedback of biopsy results, and then interpreted 110 additional ultrasound cases without feedback. Simulating an actual clinical setting, the 110 cases were unknown to both the observers and the computer. During interpretation, observers gave their confidence that the lesion was malignant and also their patient management recommendation (biopsy or follow-up). The computer output was then displayed, and observers again gave their confidence that the lesion was malignant and theirpatient management recommendation. Statistical analyses included receiver operator characteristic analysis and Student t-test. RESULTS: For the expert mammographers and for the community radiologists, the Az (area under the receiver operator characteristic curve) increased from 0.83 to 0.87 (P = .02) and from 0.80 to 0.84 (P = .04), respectively, when the computer aid was used in the interpretation of the ultrasound images. Also, the Az values for the community radiologists with aid and for the expert mammographers without aid are similar to the Az value for the computer alone (Az = 0.83). CONCLUSION: Computer analysis of ultrasound images of breast lesions has been shown to improve the diagnostic accuracy of radiologists in the task of distinguishing between malignant and benign breast lesions and in recommending cases for biopsy.     

乳腺肿块的热断层成像分析

目的:探讨乳腺肿块在热断层成像系统(TTM)中热源的特点。方法:将乳腺肿块106例病人进行TTM检查,与病理结果对照,从乳腺异常热源的形态、结构、深度及热辐射值来分析良、恶性病变在TTM上的表现。结果:病理结果恶性病变49例,良性病变57例,TTM在乳腺良、恶性肿瘤诊断与病理诊断的符合率为89.5%和91.9%,良、恶性肿瘤热辐射值分别为1.822和2.599(P<0.001),深度在良、恶性肿瘤中也有明显差异。结论:恶性病变的形态多不规则,结构密实,热辐射值较高,良性病变则相反;TTM在乳腺良、恶性肿瘤的鉴别诊断中有重要的价值。     

The role of quantitative (18)F-FDG PET studies for the differentiation of malignant and benign bone lesions.

The role of quantitative (18)F-FDG PET studies for the differentiation of benign and malignant bone lesions is still an open question. METHODS: Our evaluation included 83 patients with 37 histologically proven malignancies and 46 benign lesions. Thirty-five of the 46 benign lesions were histologically confirmed. The (18)F-FDG studies were accomplished as a dynamic series for 60 min. Evaluation of the (18)F-FDG kinetics was performed using the following parameters: standardized uptake value (SUV), global influx (Ki), computation of the transport constants K1-k4 with consideration of the distribution volume (VB) according to a 2-tissue-compartment model, fractal dimension based on the box-counting procedure (parameter for the inhomogeneity of the tumors). RESULTS: The mean SUV, the vascular fraction VB, K1, and k3 were higher in malignant tumors compared with benign lesions (t test; P < 0.05). Although the (18)F-FDG SUV was helpful to differentiate benign and malignant tumors, there was some overlap, which limited the diagnostic accuracy. On the basis of the discriminant analysis, the SUV alone showed a sensitivity of only 54.05%, a specificity of 91.30%, and a diagnostic accuracy of 74.70%. The fractal dimension was superior and showed a sensitivity of 71.88%, a specificity of 81.58%, and an accuracy of 77.14%. The combination of SUV, fractal dimension, VB, K1-k4, and Ki revealed the best results with a sensitivity of 75.86%, a specificity of 97.22%, and an accuracy of 87.69%. Bayesian analysis showed true-positive results at the level of 0.8 for a low prevalence of disease (0.235) if the full kinetic data were used in the evaluation. CONCLUSION: (18)F-FDG PET has a high specificity for the exclusion of a malignant bone tumor. Evaluation of the full (18)F-FDG kinetics and the application of discriminant analysis are required and can be used prospectively to classify a bone lesion as malignant or benign.     

Computerized analysis of lesions in US images of the breast

RATIONALE AND OBJECTIVES: Breast sonography is not routinely used to distinguish benign from malignant solid masses because of considerable overlap in their sonographic appearances. The purpose of this study was to investigate the computerized analyses of breast lesions in ultrasonographic (US) images in order to ultimately aid in the task of discriminating between malignant and benign lesions. MATERIALS AND METHODS: Features related to lesion margin, shape, homogeneity (texture), and posterior acoustic attenuation pattern in US images of the breast were extracted and calculated. The study database contained 184 digitized US images from 58 patients with 78 lesions. Benign lesions were confirmed at biopsy or cyst aspiration or with image interpretation alone; malignant lesions were confirmed at biopsy. Performance of the various individual features and output from linear discriminant analysis in distinguishing benign from malignant lesions was studied by using receiver operating characteristic (ROC) analysis. RESULTS: At ROC analysis, the feature characterizing the margin yielded Az values (area under the ROC curve) of 0.85 and 0.75 in distinguishing between benign and malignant lesions for the entire database and for an "equivocal" database, respectively. The equivocal database contained lesions that had been proved to be benign or malignant at cyst aspiration or biopsy. Linear discriminant analysis round-robin runs yielded Az values of 0.94 and 0.87 in distinguishing benign from malignant lesions for the entire database and for the equivocal database, respectively. CONCLUSION: Computerized analysis of US images has the potential to increase the specificity of breast sonography.     

Solid breast masses: neural network analysis of vascular features at three-dimensional power Doppler US for benign or malignant classification

PURPOSE: To retrospectively evaluate the accuracy of neural network analysis of tumor vascular features at three-dimensional (3D) power Doppler ultrasonography (US) for classification of breast tumors as benign or malignant, with histologic findings as the reference standard. MATERIALS AND METHODS: This study was approved by the local ethics committee; informed consent was waived. Three-dimensional power Doppler US images of 221 solid breast masses (110 benign, 111 malignant) were obtained in 221 women (mean age, 46 years; range, 25-71 years). After narrowing down vessels to skeletons with a 3D thinning algorithm, six vascular feature values--vessel-to-volume ratio, number of vascular trees, total vessel length, longest path length, number of bifurcations, and vessel diameter-were computed. A neural network was used to classify tumors by using these features. Independent-samples t test and receiver operating characteristic (ROC) curve analysis were used. RESULTS: Mean values of vessel-to-volume ratio, number of vascular trees, total vessel length, longest path length, number of bifurcations, and vessel diameter were 0.0089 +/- 0.0073 (standard deviation), 26.41 +/- 14.73, 23.02 cm +/- 19.53, 8.44 cm +/- 10.38, 36.31 +/- 37.06, and 0.088 cm +/- 0.021 in malignant tumors, respectively, and 0.0028 +/- 0.0021, 9.69 +/- 6.75, 5.17 cm +/- 4.78, 1.68 cm +/- 1.79, 6.05 +/- 7.55, and 0.064 cm +/- 0.028 in benign tumors, respectively (P < .001 for all six features). Area under ROC curve (A(z)) values of the six features were 0.84, 0.87, 0.87, 0.82, 0.84, and 0.75, respectively. Accuracy, sensitivity, specificity, and positive and negative predictive values were 85% (187 of 221), 83% (96 of 115), 86% (91 of 106), 86% (96 of 111), and 83% (91 of 110), respectively, with A(z) of 0.92 based on all six feature values. CONCLUSION: Three-dimensional power Doppler US images and neural network analysis of features can aid in classification of breast tumors as benign or malignant.     

CT纹理分析对卵巢上皮肿瘤的鉴别诊断

目的探讨基于CT平扫图像的纹理分析对鉴别卵巢上皮肿瘤良性、交界性及恶性的诊断价值。方法选取经病理证实的55例卵巢上皮肿瘤的术前CT图像和临床资料,其中良性、交界性及恶性肿瘤分别为21例、14例及20例。采用纹理分析软件于轴位CT平扫图像上提取病灶的纹理参数,各组间纹理参数比较采用独立样本t检验或Mann-Whitney U检验,对差异有统计学意义的纹理参数进行ROC曲线分析,评价其鉴别卵巢上皮肿瘤良性、交界性及恶性的诊断效能。结果恶性组的紧密度(Compactness)、熵(GlcmEntropy)高于交界性组,恶性组的熵(GlcmEntropy)、相对偏差(RelativeDeviation)高于良性组,均匀性(Uniformity)、表面积(SurfaceArea)、紧密度(Compactness)、立体像素值总和(VoxelValueSum)低于良性组,交界性组的均匀性低于良性组,差异均有统计学意义(P均<0.05)。ROC曲线显示部分纹理参数对卵巢上皮肿瘤各组间的诊断效能良好。结论基于CT平扫的部分纹理参数对鉴别卵巢上皮肿瘤的良性、交界性及恶性具有一定的临床价值,有利于临床对卵巢上皮肿瘤的早期诊断和干预。     

人体肝脏组织CT图像的分维特征研究

目的 用分形维数来表征肝脏软组织图像的纹理特征,比较肝脏病变组织与正常组织CT图像的分维特征差别。方法 采用差分盒计算方法,计算肝脏软组织CT图像中ROI(range of interesting)的分维数值。结果 从所提供的肝脏CT图像的样本中研究发现：1)肝脏正常软组织的分维数值大约在2．35左右,而癌变软组织的分维数均在2．40以上;2)同一脏器软组织的分维数值与它们所处的位置无关,只与组织所表现出来的性质有关,即：是正常组织还是癌变组织;3)分维数值从某种意义上表征了人体脏器组织的一些纹理特征;4)噪声对肝脏组织所呈现出来的固有纹理特征没有太大的影响。结论 肝脏正常软组织CT图像的分维数值小于癌变组织CT图像的分维数值。     

基于二维超声图像的纹理分析在桥本甲状腺炎背景下甲状腺结节良、恶性鉴别中的价值

目的:探讨基于二维超声图像的纹理分析对桥本甲状腺炎背景下甲状腺结节良、恶性的鉴别诊断价值.方法:回顾性分析2018年2月-8月在本院经病理证实的合并桥本甲状腺炎的甲状腺结节的二维超声图像.根据病理结果将甲状腺结节分为良性组和恶性组.采用ITK-SNAPE软件在甲状腺结节的二维超声图像上手工勾画兴趣区,通过python的...