S-DetectTM分类技术诊断BI-RADS 4类乳腺肿块

目的 观察S-Detect^TM分类技术鉴别诊断BI-RADS 4类乳腺良恶性肿块的价值。方法 对94例经二维超声诊断为BI-RADS 4类乳腺肿块患者（共104个肿块）行S-Detect^TM分类技术检查，以手术或穿刺活检病理结果作为金标准，评价S-Detect^TM分类技术、BI-RADS分类及二者联合应用诊断乳腺BI-RADS 4类良恶性肿块的价值。结果 104个乳腺肿块，经病理确诊为良性41个、恶性63个。S-Detect^TM分类技术诊断乳腺BI-RADS 4a类乳腺肿块的敏感度（SE）66.67%，特异度（SP）89.29%、阳性预测值（PPV）57.14%、阴性预测值（NPV）92.59%；对乳腺BI-RADS 4b类肿块分别为90.91%、60.00%、88.24%及66.67%；对乳腺BI-RADS 4c类肿块分别为95.83%、66.67%、95.83%及66.67%。S-Detect^TM分类技术联合BI-RADS分类诊断乳腺肿块的SE、SP、准确率明显均高于单独运用（P均<0.05）。结论 S-Detect^TM分类技术判断乳腺BI-RADS 4a类良性肿块、BI-RADS 4b类及BI-RADS 4c类恶性肿块均有较高价值。S-Detect^TM分类技术联合BI-RADS分类可明显提高鉴别BI-RADS 4类乳腺良恶性肿块的效能。     

剪切波弹性成像联合CEUS校正乳腺影像报告和数据系统3~5类乳腺病变

目的 探讨剪切波弹性成像（SWE）联合CEUS在校正乳腺影像报告和数据系统（BI-RADS）3~5类乳腺肿瘤中的应用价值。方法 收集50例乳腺病变患者（57个病灶）,其中良性病灶28个,恶性29个。对所有病灶术前行常规超声、SWE和CEUS检查,以常规超声进行BI-RADS分类,并采用SWE、CEUS及SWE联合CEUS对BI-RADS分类进行校正。以病理结果为金标准,计算常规超声、SWE、CEUS及SWE联合CEUS诊断乳腺良恶性病灶的敏感度、特异度和诊断正确率。结果 SWE参数最大杨氏模量值（E_max）诊断乳腺良恶性病灶的临界值为87.2 kPa,CEUS的临界值为8.5分,SWE联合CEUS的多因素Logistic回归模型为Y（P）=-18.785+0.161X₁+11.822X₂,X₁为E_max,X₂为增强后病灶大小改变。SWE联合CEUS将11个病灶正确降为3级,4个病灶误诊;SWE联合CEUS诊断乳腺良恶性病灶的敏感度、特异度和诊断正确率分别为100%（29/29）、85.71%（24/28）和92.98%（53/57）。结论 SWE联合CEUS对BI-RADS 3~5类乳腺病灶具有良好的校正作用,可提高超声诊断正确率。     

3.0T MR对乳腺X线摄影表现为单纯微小钙化病变的诊断价值

目的 探讨动态增强MRI（DCE-MRI）联合DWI对乳腺X线摄影表现为单纯微小钙化病变的诊断价值。方法 回顾性分析行全视野数字化乳腺X线摄影（FFDM）显示为BI-RADS 3~5类单纯微小钙化病变的患者101例（104个病变）。对患者均行乳腺FFDM和MR检查。计算病灶ADC值与正常腺体ADC值的比值（nADC值）。对病变进行BI-RADS分类。采用ROC曲线计算ADC和nADC鉴别乳腺良、恶性病变的诊断效能;分别计算FFDM、DCE-MRI和DCE-MRI联合nADC值3种方法诊断乳腺良、恶性病变的敏感度和特异度。结果 恶性病变40个,良性病变64个。ADC值及nADC值鉴别乳腺良、恶性病变的ROC曲线下面积分别为0.81和0.89。FFDM归为BI-RADS 3类病变,FFDM、DCE-MRI、DCE-MRI联合nADC值诊断乳腺恶性病变的特异度差异无统计学意义;对BI-RADS 4类病变3种方法诊断的敏感度差异无统计学意义,DCE-MRI诊断的特异度明显高于FFDM ,DCE-MRI联合nADC值诊断的特异度高于DCE-MRI。3种方法均正确诊断BI-RADS 5类病变。结论 对于FFDM检出的微小钙化病变,DCE-MRI联合nADC值有助于检出BI-RADS 4类的恶性病变。     

CEUS评估不同大小BI-RADS 4类乳腺病灶恶性风险

目的 探讨CEUS对不同大小乳腺影像报告和数据系统（BI-RADS）4类乳腺病灶恶性风险的评估价值。方法 回顾性分析经获病理结果的直径≤ 2 cm（n=120）与直径>2 cm（n=63）的BI-RADS 4类乳腺良恶性病灶的CEUS特征,采用二元Logistic回归分析筛选能够预测恶性病灶的CEUS特征参数。结果 直径≤ 2 cm良恶性病灶的CEUS增强形态、增强程度、增强均匀性、灌注模式、滋养血管、增强范围扩大及初始增强速度、消退速度差异均有统计学意义（P均<0.05）,回归分析筛选出增强范围扩大、有滋养血管与BI-RADS 4类乳腺恶性病灶独立相关（P均<0.05）;直径>2 cm良恶性病灶的增强形态、灌注模式、滋养血管、增强范围扩大及初始增强速度差异均有统计学意义（P均<0.05）,回归分析筛出有滋养血管、灌注模式呈向心性、增强范围扩大与BI-RADS 4类乳腺恶性病灶独立相关（P均<0.05）。结论 CEUS能够用于评估BI-RADS 4类不同大小乳腺病灶的恶性风险。     

数字乳腺断层摄影诊断致密型乳腺无钙化肿块

目的 通过与常规乳腺X线摄影（DM）和超声进行对比,分析数字乳腺断层摄影（DBT）对致密型乳腺内无钙化肿块的诊断价值。方法 参照乳腺影像报告和数据系统（BI-RADS）标准,回顾性分析DBT、DM及超声表现为无钙化肿块的致密型乳腺的1 144例患者资料,以组织病理结果为金标准,评估DBT、DM及超声对乳腺无钙化肿块的检出率、诊断符合率、敏感度、特异度、假阴性率及BI-RADS分类,并进行统计学分析。结果 DBT、DM及超声检查对致密型乳腺无钙化肿块的检出率和诊断符合率分别为86.62%（991/1 144）、77.80%（890/1 144）、99.65%（1 140/1 144）和83.92%（960/1 144）、75.00%（858/1 144）、94.67%（1 083/1 144）,差异均有统计学意义（P均< 0.05）。DBT、DM及超声对致密型乳腺肿块恶性病变的诊断敏感度、特异度和假阴性率分别为89.39%（312/349）、79.93%（231/289）、92.70%（432/466）,81.51%（648/795）、73.33%（627/855）、96.02%（651/678）和10.60%（37/349）、20.07%（58/289）、7.30%（34/466）。3种检查对乳腺良性肿块病变的BI-RADS分类评估差异无统计学意义（P=0.75）,对乳腺恶性肿块的BI-RADS分类差异有统计学意义（P<0.01）,其中超声与DM和DBT、DBT与DM对乳腺恶性肿块的BI-RADS分类评估差异均有统计学意义（P均< 0.016 7）。结论 DBT对致密型乳腺无钙化肿块的检出及诊断较DM具有更大优势;DBT和超声对致密型乳腺无钙化肿块的检出及诊断价值相近。     

乳腺X线片直方图分析鉴别乳腺BI-RADS 3~5类良恶性肿块

目的 探讨基于乳腺X线片直方图分析鉴别乳腺影像报告和数据系统（BI-RADS）3~5类良恶性肿块的价值。方法 回顾性分析经手术病理证实的114例BI-RADS 3~5类乳腺肿块患者，包括61例良性病变（良性组，68个肿块）和53例恶性病变（恶性组，55个肿块）。分析2组图像的直方图，比较组间直方图参数差异，包括平均值、方差、偏斜度、峰度及第1、10、50、90、99百分位数；分别绘制差异有统计学意义的参数鉴别诊断BI-RADS 3~5类乳腺良恶性肿块的受试者工作特征（ROC）曲线，计算曲线下面积（AUC），分析其诊断效能。结果 2组平均值、方差及第1、10、50、90、99百分位数差异均有统计学意义（t=－5.49、－3.14、－3.01、－3.97、－5.49、－5.84、－6.45，P均<0.05）。ROC曲线分析结果显示第99百分位数诊断效能最佳，其AUC为0.81，最佳阈值为0.50时，特异度为88.20%，敏感度为61.80%。结论 乳腺X线片直方图分析可用于鉴别诊断乳腺BI-RADS 3~5类良恶性肿块。     

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。     

超声弹性成像定量分析诊断BI-RADS4类乳腺肿块良恶性

目的 探讨超声弹性成像（UE）定量分析鉴别乳腺影像和报告数据系统（BI-RADS） 4类乳腺肿块良恶性的应用价值。方法 对86例经超声诊断为BI-RADS 4类乳腺肿块的患者行UE检查,检测弹性指数（EI）和弹性指数差（EID）。以病理结果为金标准,绘制ROC曲线,评价EI、EID判断乳腺肿块良恶性的效能。结果 86例肿块经病理证实良性44例,恶性42例。ROC曲线分析显示,EI、EID鉴别BI-RADS 4类乳腺肿块良恶性的曲线下面积（AUC）分别为0.81、0.95。以EID≥2.5为临界值,敏感度、特异度、准确率、阳性预测值、阴性预测值分别为92.86%（39/42）、90.91%（40/44）、91.86%（79/86）、90.70%（39/43）、93.02%（40/43）;以EI≥3.6为临界值,敏感度、特异度、准确率、阳性预测值、阴性预测值分别为61.90%（26/42）、86.36%（38/44）、74.42%（64/86）、81.25%（26/32）、70.37%（38/54）。EID的诊断准确率、敏感度及阴性预测值均高于EI（χ²=9.33、11.50、7.80,P均<0.05）,二者特异度及阳性预测值差异无统计学意义（χ²=0.45、1.42,P均>0.05）。结论 UE定量分析参数EI、EID均有助于鉴别乳腺BI-RADS 4类肿块的良恶性,且EID诊断准确率更高。     

弹性指数差在鉴别乳腺影像报告数据系统3~5类乳腺肿块良恶性中的应用

目的 探讨弹性指数差（EID）鉴别乳腺影像报告数据系统（BI-RADS）3~5类肿块良恶性的应用价值。方法 回顾分析164例经病理证实的BI-RADS 3~5类乳腺肿块患者（193个病灶）的超声检查资料。通过弹性成像定量分析软件测定肿块与正常腺体间的EID。以EID≥2.5判断为恶性,重新调整BI-RADS分类。绘制ROC曲线并计算曲线下面积（AUC）。比较BI-RADS联合EID与单独采用BI-RADS分类诊断乳腺恶性肿块的AUC及诊断准确率。结果 以病理结果为金标准,单独采用BI-RADS诊断乳腺恶性肿块的敏感度、特异度、准确率分别为96.00%（72/75）、67.80%（80/118）、78.76%（152/193）;BI-RADS联合EID诊断乳腺恶性肿块的敏感度、特异度、准确率分别为97.33%（73/75）、83.05%（98/118）、88.60%（171/193）。BI-RADS联合EID的AUC（0.931）高于单独应用BI-RADS的AUC（0.875）,差异有统计学意义（Z=2.06,P<0.05）;且2种方法的诊断准确率差异亦有统计学意义（χ²=15.21,P<0.05）。结论 BI-RADS联合EID对鉴别乳腺肿块良恶性较单纯采用BI-RADS更具优势。     

对比增强能谱乳腺X线摄影诊断乳腺影像报告和数据系统4类钙化

目的 对比分析全视野数字化乳腺X线（FFDM）与对比增强能谱乳腺X线摄影（CESM）对乳腺影像报告和数据系统（BI-RADS）4类钙化的诊断价值。方法 收集常规乳腺X线片中以钙化为唯一征象、且诊断报告定为BI-RADS 4类乳腺病变患者，根据检查方式不同分为FFDM组（n=48）和CESM组（n=31）。FFDM根据钙化分布及形态、CESM根据钙化相应处有无强化为依据作出良恶性诊断，以病理结果为金标准，计算并比较FFDM及CESM对恶性钙化的诊断效能。结果 FFDM诊断恶性钙化的敏感度、特异度、阳性预测值、阴性预测值和准确率分别为69.23%（9/13）、77.14%（27/35）、52.94%（9/17）、87.10%（27/31）和75.00%（36/48），CESM组分别为90.00%（9/10）、95.24%（20/21）、90.00%（9/10）、95.24%（20/21）和93.55%（29/31）。CESM诊断恶性钙化的阳性预测值和准确率高于FFDM，差异有统计学意义（χ²=3.891、4.444，P=0.049、0.035）。结论 与FFDM比较，CESM可提高对BI-RADS 4类钙化的诊断效能。     

超声造影在常规超声BI-RADS 4类病变中的应用——与DCE-MRI的对比研究

目的探讨超声造影(CEUS)在常规超声BI-RADS 4类乳腺病变中的临床应用价值,并与动态增强磁共振(DCE-MRI)对比研究。方法选取86个常规超声发现的BI-RADS 4类乳腺病灶,均进行超声造影及磁共振增强检查,采用BI-RADS分类法进行重新分类,以病理结果为金标准,比较两种影像学检查方法的诊断效能。结果乳腺恶性病变65个,良性病变21个,CEUS和DCE-MRI两种诊断方法的敏感度、特异度、阳性预测值、阴性预测值分别为89.23%、80.95%、93.55%、70.83%;92.31%、85.71%、95.24%、78.26%,二者差异无统计学意义(P0.05)。常规超声BI-RADS 4类病变降至3类:CEUS 17个,DCE-MRI 18个;BI-RADS 4类升至5类病变:CEUS 11个,DCE-MRI 13个。结论在常规超声的基础上,超声造影对于常规超声BI-RADS 4类乳腺病变,能够进一步提供更多的诊断信息,与增强磁共振具有较好的一致性,具有较好的临床应用价值。     

BIRADS联合CEUS鉴别诊断乳腺肿瘤的良恶性

目的 探讨乳腺影像报告和数据系统(BIRADS)分类联合CEUS鉴别诊断乳腺肿瘤良恶性的价值。方法 对490例患者共524个病灶进行乳腺常规超声和CEUS检查,以病理为金标准,比较BIRADS分类及BIRADS分类联合CEUS诊断乳腺肿瘤良恶性的效能。结果 524个病灶中,良性病灶232个,恶性病灶292个。BIRADS分类诊断乳腺恶性肿瘤的特异度17.24%(40/232)、敏感度99.32%(290/292)、准确率62.98%(330/524)、阳性预测值60.17%(290/482)、阴性预测值95.24%(40/42),ROC曲线下面积0.583。BIRADS分类联合CEUS后诊断乳腺恶性肿瘤的特异度90.09%(209/232)、敏感度89.04%(260/292)、准确率89.50%(469/524)、阳性预测值91.87%(260/283)、阴性预测值86.72%(209/241),ROC曲线下面积0.896;两者曲线下面积差异有统计学意义(P<0.05)。结论 BIRADS联合CEUS有利于对乳腺肿瘤的鉴别诊断。     

CEUS鉴别诊断肾脏高回声局灶性病变

目的 探讨CEUS鉴别诊断肾脏局灶性高回声良恶性病变的价值。方法 回顾性分析56例肾脏单发高回声局灶性病变患者的常规超声（US）及CEUS声像图资料,对其进行定性诊断;以病理诊断为金标准,计算并比较两者的诊断效能。结果 US及CEUS诊断肾恶性高回声病变的敏感度、特异度、阳性预测值、阴性预测值、准确率为70.00%（14/20）、75.00%（27/36）、60.87%（14/23）、81.82%（27/33）、73.21%（41/56）和80.00%（16/20）、94.44%（34/36）、88.89%（16/18）、89.47%（34/38）、89.29%（50/56）,CEUS的诊断准确率、特异度和阳性预测值均高于US（P均<0.05）。CEUS结果与病理诊断一致性好（Kappa值=0.761）,US与病理诊断一致性一般（Kappa值=0.435）。结论 CEUS可提高对于肾脏局灶性高回声良、恶性肿物的诊断及鉴别诊断效能。     

Imaging detection of new HCCs in cirrhotic patients treated with different techniques: Comparison of conventional US,spiral CT,and 3-dimensional contrast-enhanced US with the Navigator technique (Nav 3D CEUS)

IntroductionThe commercially available Navigator system^© (Esaote, Italy) allows easy 3D reconstruction of a single 2D acquisition of contrast-enhanced US (CEUS) imaging of the whole liver (with volumetric correction provided by the electromagnetic device of the Navigator^©). The aim of our study was to compare the efficacy of this panoramic technique (Nav 3D CEUS) with that of conventional US and spiral CT in the detection of new hepatic lesions in patients treated for hepatocellular carcinoma (HCC).Materials and methodsFrom November 2006 to May 2007, we performed conventional US, Nav 3D CEUS, and spiral CT on 72 cirrhotic patients previously treated for 1 or more HCCs (M/F: 38/34; all HCV-positive; Child: A/B 58/14) (1 examination: 48 patients; 2 examinations: 20 patients; 3 examinations: 4 patients). Nav 3D CEUS was performed with SonoVue^© (Bracco, Milan, Italy) as a contrast agent and Technos MPX^© scanner (Esaote, Genoa, Italy). Sensitivity, specificity, diagnostic accuracy, and positive and negative predictive values (PPV and NPV, respectively) were evaluated. Differences between the techniques were assessed with the chi-square test (SPSS release-15).ResultsDefinitive diagnoses (based on spiral CT and additional follow-up) were: 6 cases of local recurrence (LocRecs) in 4 patients, 49 new nodules >2 cm from a treated nodule (NewNods) in 34 patients, and 10 cases of multinodular recurrence consisting of 4 or more nodules (NewMulti). The remaining 24 patients (22 treated for 1–3 nodules, 2 treated for >3 nodules) remained recurrence-free. Conventional US correctly detected 29/49 NewNods, 9/10 NewMultis, and 3/6 LocRecs (sensitivity: 59.2%; specificity: 100%; diagnostic accuracy: 73.6%; PPV: 100%; NPV: 70.1%). Spiral CT detected 42/49 NewNods plus 1 that was a false positive, 9/10 NewMultis, and all 6 LocRecs (sensitivity: 85.7%; specificity: 95.7%; diagnostic accuracy: 90.9%; PPV: 97.7%; NPV: 75.9%). 3D NAV results were: 46N (+9 multinodularN and 6 LR), 3 false-negatives, and one false-positive (sensitivity: 93.9; specificity: 97.9%; diagnostic accuracy: 95.6; PPV: 97.9; NPV: 93.9).Conclusions3D Nav CEUS is significantly better than US and very similar to spiral CT for detection of new HCCs. This technique revealed the presence of lesions that could not be visualized with spiral CT.     

Reducing Unnecessary Biopsy of Breast Lesions: Preliminary Results with Combination of Strain and Shear-Wave Elastography

The aim of our study was to compare strain elastography (SE), acoustic radiation force impulse-inducing Virtual Touch Imaging ([VTI] Siemens Medical Solutions, Mountain View, CA, USA), Virtual Touch Imaging Quantification ([VTIQ] Siemens Medical Solutions) and combined methods in the evaluation of ultrasound (US) Breast Imaging-Reporting and Data System (BI-RADS) category 4 lesions to explore an applicable way to reduce unnecessary biopsy by reducing false positives of conventional US without yielding false-negative cases. A total of 267 patients with 278 BI-RADS category 4 lesions (151 benign and 127 malignant) were evaluated with conventional B-mode US, SE, VTI and VTIQ implemented on a Siemens Acuson S2000 US system. Diagnostic performance, including area under the receiver operating characteristic curve, sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) were evaluated. Overall, VTI alone exhibited the highest NPV (91.74%), although combined elastic methods exhibited higher NPV than single methods, with the highest NPV at 100% when the VTI, SE and VTIQ methods were combined. Compared with conventional US, PPV increased from 45.7% (127 of 278) to 63.18% (127 of 201) when adding combined elastography (VTI + SE +VTIQ). In addition, 52.5% (63/120) and 50.8% (61/120) of BI-RADS 4 A lesions were downgraded when using combined methods (VTI + SE and VTI + SE + VTIQ, respectively) without missing any cancer. However, 2 intraductal papillomas and 1 phyllodes tumor were not identified. In conclusion, the combination of different elastic methods have the potential to downgrade BI-RADS 4A lesions to reduce false-positive biopsies without increasing the risk of missing cancers.     

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.     

Application of Deep Learning to Reduce the Rate of Malignancy Among BI-RADS 4A Breast Lesions Based on Ultrasonography

The aim of the work described here was to develop an ultrasound (US) image–based deep learning model to reduce the rate of malignancy among breast lesions diagnosed as category 4A of the Breast Imaging-Reporting and Data System (BI-RADS) during the pre-operative US examination. A total of 479 breast lesions diagnosed as BI-RADS 4A in pre-operative US examination were enrolled. There were 362 benign lesions and 117 malignant lesions confirmed by postoperative pathology with a malignancy rate of 24.4%. US images were collected from the database server. They were then randomly divided into training and testing cohorts at a ratio of 4:1. To correctly classify malignant and benign tumors diagnosed as BI-RADS 4A in US, four deep learning models, including MobileNet, DenseNet121, Xception and Inception V3, were developed. The performance of deep learning models was compared using the area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Meanwhile, the robustness of the models was evaluated by five-fold cross-validation. Among the four models, the MobileNet model turned to be the optimal model with the best performance in classifying benign and malignant lesions among BI-RADS 4A breast lesions. The AUROC, accuracy, sensitivity, specificity, PPV and NPV of the optimal model in the testing cohort were 0.897, 0.913, 0.926, 0.899, 0.958 and 0.784, respectively. About 14.4% of patients were expected to be upgraded to BI-RADS 4B in US with the assistance of the MobileNet model. The deep learning model MobileNet can help to reduce the rate of malignancy among BI-RADS 4A breast lesions in pre-operative US examinations, which is valuable to clinicians in tailoring treatment for suspicious breast lesions identified on US.