Prospective sonographic study of 3093 breast tumors.

To evaluate the predictive ability of sonographic tumor characteristics to differentiate benign from malignant tumors, we examined 3093 breast tumors (2360 benign and 733 malignant tumors) with ultrasonography. The ratio of the longest dimension to the anteroposterior diameter of benign tumors was significantly larger than that of malignant tumors (1.88+/-0.1 versus 1.69+/-0.02, P < 0.0001). Shape, margins, echogenicity, internal echo pattern, retrotumor acoustic shadowing, compressibility, and microcalcification were significant factors in the logistic regression model. The sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of breast sonography for malignancy were 86.1, 66.1, 44.1, 93.9, and 70.8%, respectively. Biopsy of the tumor for pathologic diagnosis is recommended if sonographic features are suggestive of malignancy.     

Stepwise logistic regression analysis of tumor contour features for breast ultrasound diagnosis.

To assist the ultrasound (US) differential diagnosis of solid breast tumors by using stepwise logistic regression (SLR) analysis of tumor contour features, we retrospectively reviewed 111 medical records of digitized US images of breast pathologies. They were pathologically proved benign breast tumors from 40 patients (i.e., 40 fibroadenomas) and malignant breast tumors from 71 patients (i.e., 71 infiltrative ductal carcinomas). Radiologists, before analysis by the computer-aided diagnosis (CAD) system, segmented the tumors manually. The contour features were calculated by measuring the radial length of tumor boundaries. The features selection process was accomplished using a stepwise analysis procedure. Then, an SLR model with contour features was used to classify tumors as benign or malignant. In this experiment, cases were sampled with "leave-one-out" test methods to evaluate the SLR performance using a receiver operating characteristic (ROC) curve. The accuracy of our SLR model with contour features for classifying malignancies was 91.0% (101 of 111 tumors), the sensitivity was 97.2% (69 of 71), the specificity was 80.0% (32 of 40), the positive predictive value was 89.6% (69 of 77), and the negative predictive value was 94.1% (32 of 34). The CAD system using SLR can differentiate solid breast nodules with relatively high accuracy and its high negative predictive value could potentially help inexperienced operators to avoid misdiagnoses. Because the SLR model is trainable, it could be optimized if a larger set of tumor images were supplied.     

三维超声冠状面成像鉴别乳腺实性病灶良恶性的应用价值

目的：探讨三维超声冠状面成像鉴别乳腺肿块良恶性的应用价值。方法观察分析97例患者106个乳腺实性病灶的二维和三维超声冠状面成像,对二维超声图像进行乳腺超声影像报告与数据系统（BI-RADS-US）分类,并与病理结果对照,计算二维超声对乳腺病灶良恶性病灶的鉴别诊断价值;根据良恶性病灶在三维超声冠状面上的声像图特征,建立Logistic回归模型,绘制受试者操作特性（ROC）曲线及计算曲线下面积来分析其对乳腺癌的诊断价值。结果106个乳腺病灶中,恶性病灶71个,良性病灶35个。二维超声诊断准确性85.8%,敏感度84.5%,特异度88.6%。多因素回归分析显示最后进入Logistic模型的特征分别为病灶边缘的成角或毛刺和“太阳征”。ROC曲线下面积为0.899,标准误为0.033,95%可信区间（0.834,0.965）。以成角或毛刺、“太阳征”为自变量的Logistic回归模型诊断乳腺肿块的准确性为88.7%（94/106）,敏感度为90.1%（64/71）,特异度为85.7%（30/35）,阳性预测值为92.8%（64/69）,阴性预测值为81.1%（30/37）。结论乳腺三维超声冠状面,特别是成角或毛刺征及“太阳征”在乳腺肿块的良恶性鉴别中具有重要价值。对于疑难病灶,三维超声冠状面上的信息有助于提高医生的诊断自信心。     

Computer-Aided Diagnosis for Breast Tumors by Using Vascularization of 3-D Power Doppler Ultrasound

This study assessed the accuracy of three-dimensional (3-D) power Doppler ultrasound in differentiating between benign and malignant breast tumors by using a support vector machine (SVM). A 3-D power Doppler ultrasonography was performed on 164 patients with 86 benign and 78 malignant breast tumors. The volume-of-interest (VOI) in 3-D ultrasound images was automatically generated from three rectangular regions-of-interest (ROI). The vascularization index (VI), flow index (FI) and vascularization-flow index (VFI) on 3-D power-Doppler ultrasound images were evaluated for the entire volume area, computer extracted VOI area and the area outside the VOI. Furthermore, patient's age and VOI volume were also applied for breast tumor classifications. Each ultrasonography in this study was classified as benign or malignant based on the features using the SVM model. All the tumors were sampled using k-fold cross-validation (k = 10) to evaluate the diagnostic performance with receiver operating characteristic (ROC) curves. The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) and accuracy of SVM for classifying malignancies were 94%, 69%, 73%, 92% and 81%, respectively. The classification performance in terms of Az value for the ROC curve of the features derived from 3-D power Doppler is 0.91. This study indicates that combining 3-D power Doppler vascularity with patient's age and tumor size offers a good method for differentiating benign andmalignant breast tumors. (E-mail: ylhuang@thu.edu.tw (Y.-L.H.); darren_chen@cch.org.tw (D.-R.C.))     

乳腺超声弹性成像8分评分标准价值的探讨

目的探讨超声弹性成像8分评分标准诊断乳腺病变良、恶性的最佳诊断界点及其诊断价值。方法以弹性成像评分8分法作为诊断标准,对经手术病理结果证实的583个乳腺病灶的超声弹性成像图依据8分评分标准进行评分,并进行诊断试验的ROC曲线分析。结果8分法弹性成像评分标准对乳腺病灶良、恶性诊断的最佳诊断界点为5分,其ROC曲线下面积为0.9523,其敏感性、特异性、阳性预测值、阴性预测值及准确性分别为：82.07%、98.63%、95.20%、94.32%和94.51%。结论超声弹性成像8分评分标准使用更为简便、准确,有助于乳腺肿块的良恶性鉴别。     

乳腺小肿物超声特征的Logistic回归分析

目的探讨乳腺小肿物的超声征象,应用Logistic回归分析评价其应用价值。方法回顾性分析经手术病理证实的497个乳腺小肿物的超声征象,根据病理结果分为良性组466个和恶性组31个,比较两组超声特征的差异。应用多因素二元Logistic回归分析筛选出鉴别诊断乳腺小肿物良恶性的独立影响因素,建立回归方程,绘制受试者工作特征(ROC)曲线分析Logistic回归模型的预测价值。结果两组超声特征中形态、纵横比、边缘、回声类型、肿物内钙化、周围组织相关征象及肿物内血流信号比较差异均有统计学意义(均P<0.05),两组肿物后方回声特征比较差异无统计学意义(P=0.26)。多因素二元Logistic回归分析显示纵横比≥1、内部血流信号、边缘血流信号均是鉴别乳腺小肿物良恶性的独立影响因素(OR=9.56、9.68、4.29,P=0.02、0.00、0.04);Logistic回归方程为:Logistic(P)=-3.86+2.23×纵横比≥1+2.29×内部血流信号+1.46×边缘血流信号。Logistic回归模型以预测概率P=0.50作为阈值,鉴别小肿物良恶性的准确率95.2%,敏感性83.9%,特异性89.1%,ROC曲线下面积0.89。结论以纵横比和血流信号建立的Logistic回归模型有助于乳腺小肿物良恶性的鉴别诊断。     

乳腺超声造影预测模型的建立及其对乳腺良恶性病变诊断效能的分析

目的分析乳腺超声造影（CEUS）的增强特征，构建乳腺病变CEUS预测模型，探讨该模型对乳腺良恶性病变的诊断价值。 方法选取2016年6月至2018年8月于丽水市人民医院及浙江大学医学院附属第二医院就诊的乳腺病变患者192例共195个病灶，所有病灶均为常规超声检查BI-RADS分类4类及以上，均经穿刺活检或手术取得病理结果。将病例分为CEUS组120例共123个病灶，均经CEUS检查；CEUS＋动态增强磁共振（DCE-MRI）组72例共72个病灶，均接受CEUS及DCE-MRI检查。对CEUS组120例患者的CEUS模式特征进行单因素及多因素Logistic回归分析，筛选预测乳腺恶性病变的CEUS危险因素，并建立预测模型，绘制ROC曲线。以CEUS＋DCE-MRI组72例患者的病理结果为"金标准"，分别计算CEUS预测模型与DCE-MRI对乳腺良恶性病变的诊断效能。 结果Logistic回归分析结果显示诊断乳腺恶性病灶的CEUS特征性表现为增强后病灶范围增大（OR=12.941，P=0.003），"蟹足"征或血管扭曲缠绕（OR=7.553，P=0.009），灌注缺损（OR=5.670，P=0.024）。建立的风险预测模型即Logistic回归方程为：Y=-4.108＋2.560X₆＋2.022X₇＋1.735X₈。该模型预测乳腺良恶性病灶的ROC曲线下面积为0.953。以穿刺或术后病理结果为"金标准"，CEUS风险预测模型诊断乳腺良恶性病变的敏感度、特异度、阳性预测值、阴性预测值以及准确性分别为93.0%、73.3%、93.0%、73.3%、88.9%；DCE-MRI诊断乳腺良恶性病变的敏感度、特异度、阳性预测值、阴性预测值以及准确性分别为94.7%、73.3%、93.1%、78.6%、90.3%。CEUS风险预测模型与DCE-MRI诊断乳腺良恶性病变的一致性较高（Kappa值=0.70）。 结论乳腺CEUS预测模型对鉴别良恶性病灶具有较高的诊断效能，且操作相对简单、检查时间短、可重复性好、价格相对低廉，不失为诊断乳腺良恶性病变的一种有效和可靠方法。     

Sonographic differentiation of benign and malignant papillary lesions of the breast.

OBJECTIVE: The purpose of this study was to evaluate sonographic findings of breast papillary lesions and the effectiveness of the American College Radiology Breast Imaging Reporting and Data System sonographic assessment system for differentiation of benign and malignant papillary lesions. METHODS: We retrospectively reviewed breast sonographic findings of 46 surgically proven benign papillomas and 22 papillary carcinomas. All sonographic images of patients were interpreted by 2 radiologists. Sonographic findings were analyzed according to the Breast Imaging Reporting and Data System classification. RESULTS: The shape of the lesion was round or oval in 33 benign lesions (71.7%) and 13 papillary carcinomas (61.9%). As for the margin, a circumscribed margin was found in 31 benign papillomas (67.4%) and 12 malignant lesions (57.1%). Differences in the predominant shape and margin between the 2 groups were not statistically significant (P > .05). Fourteen benign papillomas (30.5%) and 12 papillary carcinomas (57.1%) showed a complex echo pattern. It was more frequently observed in malignant lesions; however, it was not statistically significant (P = .09). A nonparallel orientation, an echogenic halo, posterior acoustic enhancement, and associated microcalcification were more frequently found in malignant than in benign lesions (P < .05). When the presence of any suspicious sonographic feature (nonparallel orientation, echogenic halo, posterior enhancement, or calcification) was considered to indicate malignancy, interpretation of the sonographic features gave sensitivity of 85.7%, specificity of 64.9%, a positive predictive value of 47.4%, and a negative predictive value of 92.5% for detection of malignant papillary lesions. The only differential finding between noninvasive and invasive papillary cancers was a circumscribed margin (P < .05). CONCLUSIONS: Sonographic features more specific to malignancy include a nonparallel orientation, an echogenic halo, posterior acoustic enhancement, and associated microcalcification.     

乳腺超声造影预测模型构建及对BI-RADS 4类病变的风险评估

目的 分析乳腺良恶性病变的超声造影特征,构建预测模型,探讨其对乳腺影像报告与数据系统(BI-RADS)4类病变风险的评估价值.方法 选取我院均经手术病理结果 证实的乳腺病变患者174例,共180个病灶(BI-RADS 4类).将其分为模型构建样本(91例,共94个病灶)和模型验证样本(83例,共86个病灶).对模型构建...     

声触诊组织成像定量剪切波弹性成像技术鉴别诊断乳腺肿块良恶性的价值

目的评价声辐射力脉冲弹性成像（ARFI）声触诊组织成像定量（VTIQ）剪切波弹性成像技术鉴别诊断乳腺肿块良恶性的应用价值。 方法回顾性分析2014年6至7月同济大学附属第十人民医院行超声检查的乳腺肿块患者60例共60个乳腺肿块。所有肿块均经手术病理证实。首先对所有患者行乳腺常规超声检查,观察并记录肿块大小、边界、部位、回声、内部血供等,并进行乳腺影像报告和数据系统（BI-RADS）分类。然后应用VTIQ技术测量病灶内部横向剪切波速度（SWV）。以BI-RADS分类≥4类为乳腺恶性肿块诊断标准,BI-RADS<4为乳腺良性肿块诊断标准。以病理结果作为金标准,计算BI-RADS分类鉴别诊断乳腺肿块良恶性的敏感度、特异度、准确性、阳性预测值、阴性预测值及Youden指数。采用t检验比较乳腺良恶性肿块的SWV值差异。绘制VTIQ技术鉴别诊断乳腺肿块良恶性的操作者工作特性（ROC）曲线。 结果60个乳腺肿块包括乳腺恶性病灶18个,均为浸润性导管癌;乳腺良性病灶42个,包括纤维腺瘤21个,腺病16个,腺病伴导管扩张2个,导管内乳头状瘤1个,良性分叶状肿瘤1个,乳头状瘤1个。BI-RADS分类鉴别诊断乳腺肿块良恶性的敏感度、特异度、准确性、阳性预测值、阴性预测值、Youden指数分别为88.8%、59.5%、68.3%、48.5%、92.6%、0.48。乳腺恶性肿块平均SWV值高于乳腺良性肿块平均SWV值,且差异有统计学意义[（6.35±1.59）m/s vs （2.28±0.64） m/s,t=9.14,P<0.001）。ROC曲线显示,VTIQ技术测得的SWV值鉴别诊断乳腺肿块良恶性的阈值为4.20 m/s,VTIQ技术鉴别诊断乳腺肿块良恶性的敏感度、特异度、准确性、阳性预测值、阴性预测值、Youden指数分别为94.4%、66.6%、75.0%、54.8%、96.5%、0.61。 结论与BI-RADS分类比较,VTIQ技术能明显提高乳腺肿块良恶性的鉴别诊断能力。     

Retrieval technique for the diagnosis of solid breast tumors on sonogram

We evaluated a series of pathologically proven breast tumors using an image-retrieval technique for classifying benign and malignant lesions. A total of 263 breast tumors (129 malignant and 134 benign) were retrospectively evaluated. The physician located regions-of-interest (ROI) of ultrasonic images and texture parameters (contrast, covariance and dissimilarity) were used in the process of the content-based image-retrieval technique. The accuracy of using the retrieval technique for classifying malignancies was 92.55% (236 of 255), the sensitivity was 94.44% (119 of 126), the specificity was 90.70% (117 of 129), the positive predictive value was 90.84% (119 of 131), and negative predictive value was 94.35% (117 of 124) for the proposed computer-aided diagnostic system. This computer-aided diagnosis system can provide a useful tool and its high negative predictive value could potentially help avert benign biopsies. It is unnecessary to perform any training procedures. This computer-aided diagnosis system can provide a second opinion for a sonographic interpreter; the main advantage in this proposed system is that we do not need any training. Historical cases can be directly added into the database and training of the diagnosis system again is not needed. With the growth of the database, more and more information can be collected and used as reference cases while performing diagnoses. This increases the flexibility of our diagnostic system.     

乳腺MRI特征及ADC值预测乳腺影像报告和数据系统4类良恶性病变

目的 探讨乳腺MRI特征及ADC值对乳腺影像报告和数据系统（BI-RADS）4类良恶性病变的预测能力，并尝试建立Logistic回归预测模型。方法 收集MRI诊断为BI-RADS 4类病变、并取得病理结果的79例乳腺病变患者（82个病变）。采用单因素二元Logistic回归及两独立样本t检验分析各MRI特征和ADC值鉴别良恶性乳腺病变的统计学意义，并建立多因素Logistic回归预测模型，绘制ROC曲线评价回归模型预测BI-RADS 4类病变良恶性的效能。结果 肿块型病变中，将边缘、内部强化及ADC值纳入Logistic回归预测模型中（P均<0.05，伪R²=0.62），其诊断良恶性乳腺病变的ROC曲线AUC为0.981，敏感度为87.80%，特异度为100%。非肿块型病变中，无预测变量纳入建立Logistic回归预测模型（P均>0.1）。结论 乳腺MRI特征（边缘、内部强化）及ADC值对预测肿块型BI-RADS 4类病变的良恶性具有一定意义；Logistic回归预测模型可有效鉴别BI-RADS 4类肿块型病变性质。     

Characterization of solid breast masses: use of the sonographic breast imaging reporting and data system lexicon.

OBJECTIVE: The purpose of this study was to determine the reliability of sonographic American College of Radiology Breast Imaging Reporting And Data System (BI-RADS) classification in differentiating benign from malignant breast masses. METHODS: One hundred seventy-eight breast masses studied by sonography with a known diagnosis were reviewed. All lesions were classified according to the sonographic BI-RADS lexicon. Pathologic results were compared with sonographic features. Sensitivity, specificity, accuracy, and positive predictive value (PPV) and negative predictive value (NPV) for the sonographic BI-RADS lexicon were calculated. RESULTS: Twenty-six cases were assigned to class 3, 73 to class 4, and 79 to class 5. Pathologic results revealed 105 malignant and 73 benign lesions. The sonographic BI-RADS lexicon showed 71.3% accuracy, 98.1% sensitivity, 32.9% specificity, 67.8% PPV, and 92.3% NPV. The NPV for class 3 was 92.3%. The PPVs for classes 4 and 5 were 46.6% and 87.3%. Typical signs of malignancy were irregular shape, antiparallel orientation, noncircumscribed margin, echogenic halo, and decreased sound transmission. Typical signs of benignity were oval shape and circumscribed margin. CONCLUSIONS: The sonographic BI-RADS lexicon is an important system for describing and classifying breast lesions.     

剪切波弹性成像定性技术鉴别诊断乳腺良恶性病变

目的 探讨SWE定性技术在乳腺病灶良恶性鉴别诊断中的应用价值。方法 对236例患者共261个病灶行常规超声及SWE检查。以常规超声图像进行乳腺影像报告和数据系统（BI-RADS）分类,将SWE图像分为6种类型。以病理结果为金标准,绘制ROC曲线,评价SWE分型、BI-RADS分类及二者联合的诊断效能。结果 良性病灶100个,恶性病灶161个。以SWE分型3型为诊断界点,敏感度、特异度、准确率、阳性预测值、阴性预测值分别为85.71%（138/161）、93.00%（93/100）、88.51%（231/261）、95.17%（138/145）、80.17%（93/116）;以BI-RADS 4a类为诊断界点,敏感度、特异度、准确率、阳性预测值、阴性预测值分别为98.76%（159/161）、73.00%（73/100）、88.89%（232/261）、85.48%（159/186）、97.33%（73/75）;二者联合诊断的敏感度、特异度、准确率、阳性预测值、阴性预测值分别为99.38%（160/161）、70.00%（70/100）、88.12%（230/261）、84.21%（160/190）、98.59%（70/71）。SWE分型的特异度和阳性预测值均高于BI-RADS分类及联合诊断（P均<0.05）,BI-RADS分类及联合诊断的敏感度和阴性预测值均高于SWE分型（P均<0.05）,三者诊断准确率差异均无统计学意义（P均>0.05）。结论 SWE定性技术有助于乳腺良恶性病灶的鉴别诊断。     

卵巢-附件报告与数据系统在超声诊断卵巢-附件肿块良恶性中的价值

目的探讨美国放射学会卵巢-附件报告与数据系统（O-RADS）在卵巢-附件肿块超声诊断中的价值。 方法本研究为回顾性诊断试验。对象为2019年1月至2020年12月在湖北省妇幼保健院进行手术且有病理结果的卵巢或附件肿块患者441例,患者术前均行超声检查。参照O-RADS分类标准对每个卵巢及附件区肿块进行O-RADS恶性风险分层。绘制受试者工作特征（ROC）曲线分析O-RADS分类法诊断卵巢-附件肿块良恶性的诊断价值,最后以病理诊断为参考标准,绘制诊断四格表分析该分类诊断系统的有效性。 结果441例肿块中良性353例,恶性88例。O-RADS 2-5类中,其恶性肿块分别占1.1%、3.7%、47.8%、91.1%。O-RADS分类法诊断卵巢-附件肿块良恶性的ROC曲线下面积为0.947,95%可信区间为0.919~0.975,良恶性截断值为3.5。当将O-RADS 4和5类作为恶性肿块的预测指标时,其诊断卵巢-附件肿块良恶性的敏感度、特异度、阳性预测值、阴性预测值、阳性似然比、阴性似然比及约登指数分别为94.3%、88.6%、67.5%、98.4%、8.27、0.06、0.82。当只将O-RADS 5类作为恶性肿块的预测指标时,其诊断卵巢-附件肿块良恶性的敏感度、特异度、阳性预测值、阴性预测值、阳性似然比、阴性似然比及约登指数分别为57.9%、98.6%、91.1%、90.3%、41.36、0.43、0.57。 结论O-RADS可作为超声诊断卵巢-附件肿块良恶性的可靠方法,建议以O-RADS 4和5类为预测卵巢-附件肿块恶性的指标。     

超声联合纹理分析对乳腺结节良恶性的诊断价值

目的以乳腺结节的灰阶超声及剪切波弹性超声影像为基础，分析超声图像的纹理特征，探索常规超声联合纹理分析对乳腺结节良恶性的诊断价值。 方法前瞻性收集2018年8月至2018年12月于首都医科大学附属北京友谊医院常规超声检查发现乳腺结节并获得病理诊断的患者113例，共113个结节。所有患者均行常规超声及剪切波弹性成像检查，并对113个乳腺结节依据乳腺影像报告和数据系统（BI-RADS）进行分类；对超声图像进行纹理分析，获得纹理特征参数并建立诊断模型。以病理结果为"金标准"，分析纹理特征诊断模型、常规超声联合纹理特征诊断模型对乳腺结节良恶性的诊断价值。 结果以乳腺结节穿刺病理结果为"金标准"，纹理分析诊断乳腺结节良恶性的敏感度、特异度、阳性预测值、阴性预测值及准确性分别为0.64、0.91、0.75、0.86、0.83，ROC曲线下面积为0.77；常规超声与纹理分析联合方法诊断乳腺结节良恶性的敏感度、特异度、阳性预测值、阴性预测值及准确性分别为0.88、0.85、0.71、0.94、0.86，ROC曲线下面积为0.86。联合诊断的ROC曲线下面积高于纹理分析，差异有统计学意义（Z=2.133，P=0.03）。采用常规超声联合纹理分析方法，90.0%（72/80）的BI-RADS 4a类乳腺结节可以降级为BI-RADS 3类，病理结果显示，降级为BI-RADS 3类的乳腺结节中94.4%（68/72）为良性结节。 结论常规超声联合纹理分析对乳腺结节良恶性有较好的诊断效能，可减少不必要的有创性检查，具有良好的应用前景。     

Prospective evaluation of the value of negative sonographic and mammographic findings in patients with palpable abnormalities of the breast.

OBJECTIVE: To evaluate the value of combined negative sonographic and mammographic findings in patients with palpable breast abnormalities. METHODS: One hundred seventy-two patients with 186 palpable abnormalities who had combined negative sonographic and mammographic findings were prospectively studied. Patients who did not undergo biopsy had imaging and clinical follow-up; the mean follow-up period was 28.9 months (range, 24-33 months). RESULTS: Twelve patients underwent biopsy; benign histologic diagnoses were reported in all 12 (12 [6.9%] of 172). In the remaining 160 patients who were followed, there was no interval development of breast cancer at the site of the palpable abnormality. The negative predictive value of combined negative mammographic and sonographic findings in a patient with a palpable abnormality of the breast was 100%. CONCLUSIONS: Our findings suggest that in a patient with a palpable abnormality of the breast, the negative predictive value of combined normal sonographic and mammographic findings is very high and is therefore reassuring to the patient.     

常规超声特征联合内部粗大钙化特征鉴别甲状腺结节良恶性的价值

目的探讨常规甲状腺结节声像图特征联合内部粗大钙化特征鉴别结节良恶性的价值。 方法回顾性分析2018年1月至2020年7月于常州市第一人民医院就诊并经病理证实的217例患者共229个甲状腺结节的超声图像。纳入结节的超声声像图均提示结节内存在粗大钙化。以病理结果为金标准,将甲状腺结节分为良性组（n=110）和恶性组（n=119）。单因素分析比较2组结节的常规超声声像图特征以及内部粗大钙化特征的差异,其中常规结节特征包括最大径、纵横比、回声强度、生长方式、成分、边缘和彩色多普勒血流信息,内部粗大钙化特征包括厚度、钙化连续性中断（简称“中断”）、形态、钙化外软组织边缘、钙化回声均匀性和位置。采用二元Logistic回归分析建立常规结节特征、常规结节特征与内部粗大钙化特征相结合的联合预测模型（模型1、模型2）。采用ROC曲线和Z检验分析比较各参数及联合预测模型的诊断效能。 结果恶性组甲状腺结节的最大径≤1.25 cm、纵横比＞0.78、实性成分、垂直位生长、边缘不规则或腺外侵犯以及内部粗大钙化厚度不规则、中断、回声高低不一、存在软组织边缘、中央型钙化均较良性组多见,且差异均具有统计学意义（P均＜0.05）。模型1纳入结节最大径、纵横比和边缘,模型2纳入结节最大径、纵横比、钙化厚度、连续性中断和钙化位置。模型2的敏感度、特异度、阳性预测值、阴性预测值和准确性分别为81.85%、82.73%、82.29%、80.18%和81.22%,其ROC曲线下面积高于模型1（0.877 vs 0.753,Z=4.197,P＜0.001）。 结论结节内粗大钙化厚度不规则、连续性中断、中央型钙化等声像图特征有助于结节良恶性的诊断。在观察结节常规声像图特征的同时,联合评估内部粗大钙化的特征对鉴别甲状腺结节的良恶性有重要意义。     

Prospective evaluation of the value of combined mammographic and sonographic assessment in patients with palpable abnormalities of the breast.

OBJECTIVE: To evaluate the role of combined mammographic and sonographic imaging in patients with palpable abnormalities of the breast. METHODS: Four hundred eleven consecutive cases of palpable abnormalities of the breast underwent combined mammographic and sonographic evaluation. Patients who did not undergo biopsy had imaging and clinical follow-up; the mean follow-up period was 28.9 months (range, 24-33 months). RESULTS: One hundred sixty-five (40.1%) of 411 palpable abnormalities had a benign assessment; 97 (58.7%) of the 165 benign lesions were visible on both mammography and sonography; 66 (40%) of 165 benign lesions were mammographically occult and identified at sonographic evaluation. In 60 (14.6%) of the 411 cases, imaging evaluation resulted in a suspicious assessment; 49 (81.7%) of the 60 lesions categorized as suspicious underwent biopsy; 14 (28.5%) of 49 lesions were histologically proved to be carcinoma. Nineteen (31.6%) of the 60 lesions categorized as suspicious were mammographically occult and identified only on sonography; 14 (73.7%) of these 19 lesions underwent biopsy; 12 (63.1%) of 19 were benign, and 2 (10.5%) were malignant. One hundred eighty-six (45.2%) of the 411 palpable abnormalities had negative imaging assessment findings; 12 patients with negative imaging findings underwent biopsy, and all had benign findings. The sensitivity (14 of 14) and negative predictive value (186 of 186) for a combined mammographic and sonographic assessment were 100%; the specificity was 80.1% (186 of 232). CONCLUSIONS: Cancer was diagnosed in 14 (3.4%) of 411 women who underwent combined imaging for palpable abnormalities of the breast. Combined mammographic and sonographic assessment was shown to be very helpful in identifying benign as well as malignant lesions causing palpable abnormalities of the breast.     

Use of the bootstrap technique with small training sets for computer-aided diagnosis in breast ultrasound

The purpose of this study was to test the efficacy of using small training sets in computer-aided diagnostic systems (CAD) and to increase the capabilities of ultrasound (US) technology in the differential diagnosis of solid breast tumors. A total of 263 sonographic images of solid breast nodules, including 129 malignancies and 134 benign nodules, were evaluated by using a bootstrap technique with 10 original training samples. Texture parameters of a region-of-interest (ROI) were resampled with a bootstrap technique and a decision-tree model was used to classify the tumor as benign or malignant. The accuracy was 87.07% (229 of 263 tumors), the sensitivity was 95.35% (123 of 129), the specificity was 79.10% (106 of 134), the positive predictive value was 81.46% (123 of 151), and the negative predictive value was 94.64% (106 of 112). This analysis method provides a second opinion for physicians with high accuracy. The new method shows a potential to be useful in future application of CAD, especially when a large database cannot be obtained for training or a newly developed ultrasonic system has smaller sets of samples.