超声组学对乳腺BI-RADS 4类病变的良恶性鉴别诊断价值

【目的】探讨超声组学对乳腺BI-RADS 4类病变的良恶性鉴别诊断价值。【方法】前瞻性收集本院2018年6月至2019年12月期间乳腺超声发现的、有病理结果的BI-RADS 4类病变,共计223例。将研究人群按时间节点分为训练组（114例）和验证组（109例）。基于训练组病例建立乳腺病灶的超声组学评分指标。绘制超声组学评分的受试者工作特征（receiver operating characteristic,ROC）曲线,以曲线下面积（area under the curve,AUC）定量评估超声组学评分鉴别BI-RADS 4类病变良恶性的效能,计算其敏感性和特异性,并于验证组中验证其诊断效能。【结果】纳入的223个病例中,恶性占32.29%。训练组和验证组的恶性占比分别为28.95%、35.78%。超声组学评分在训练组和验证组的AUC及其95%置信区间分别为0.826（0.743-0.909）和0.810（0.723-0.898）。在训练组中,超声组学评分鉴别BI-RADS 4类病变良恶性的敏感性和特异性分别为78.79%和81.48%。在验证组中,其对应的敏感性和特异性分别为66.67%和82.86%。【结论】超声组学评分指标对乳腺BI-RADS 4类病变具备良好的鉴别诊断价值。     

乳腺BI-RADS 4类结节超声图像特征分析

目的:对超声诊断乳腺BI-RADS 4类结节的超声图像特征进行分析,并与病理结果对比研究。方法:回顾性分析2017年10月至2018年12月我院383例超声诊断为BI-RADS4类乳腺结节的超声图像特征,以手术或穿刺活检病理为金标准,分析良恶性乳腺结节在形态、边界、边缘、钙化、后方回声等方面的差异。结果:与病理诊断结果比较,383例BI-RADS4类结节中,超声诊断良恶性结节的符合率分别为81.5%与71.1%。良性结节患者平均年龄(46.7±10.5)岁,恶性结节患者平均年龄(55.5±12.4)岁,两组具有显著性差异(P<0.05);绘制ROC曲线得出,以46岁为截断值,其曲线下面积为0.695,诊断的敏感性为69.8%,特异性为60.3%。良性结节与恶性结节的超声图像对比:良性结节多表现为形态规则,边界清晰,边缘光滑、分叶,多不伴钙化;恶性结节多表现为形态不规则、边界模糊,边缘成角、毛刺,多伴微钙化(P<0.05)。良恶性结节间后方回声变化比较无显著统计学差异(P>0.05)。结论:超声诊断BI-RADS4类结节中,良恶性病变具有不同的声像图特征,可为临床医生进行乳腺结节良恶性诊断提供重要参考。     

Factors Associated With Optimal Follow-up in Women With BI-RADS 3 Breast Findings

ObjectiveAssess rate of and factors associated with optimal follow-up in patients with BI-RADS 3 breast findings.MethodsThis Institutional Review Board–approved, retrospective cohort study, performed at an academic medical center, included all women undergoing breast imaging (ultrasound and mammography) in 2016. Index reports for unique patients with an assessment of BI-RADS 3 (retrieved via natural language processing) comprised the study population. Patient-specific and provider-related features were extracted from the Research Data Warehouse. The Institutional Cancer Registry identified patients diagnosed with breast cancer. Optimal follow-up rate was calculated as patients with follow-up imaging on the same breast 3 to 9 months from the index examination among patients with BI-RADS 3 assessments. Univariate analysis and multivariable logistic regression determined features associated with optimal follow-up. Malignancy rate and time to malignancy detection were recorded.ResultsAmong 93,685 breast imaging examinations, 64,771 were from unique patients of which 2,967 had BI-RADS 3 findings (4.6%). Excluding patients with off-site index examinations and those with another breast examination <3 months from the index, 1,125 of 1,511 patients (74%) had optimal follow-up. In univariate and multivariable analysis, prior breast cancer was associated with optimal follow-up; younger age, Hispanic ethnicity, divorced status, and lack of insurance were associated with not having optimal follow-up. Malignancy rate was 0.86%, and mean time to detection was 330 days.DiscussionFollow-up of BI-RADS 3 breast imaging findings is optimal in only 74% of women. Further interventions to promote follow-up should target younger, unmarried women, those with Hispanic ethnicity, and women without history of breast cancer and without insurance coverage.     

Automated Extraction of BI-RADS Final Assessment Categories from Radiology Reports with Natural Language Processing

The objective of this study is to evaluate a natural language processing (NLP) algorithm that determines American College of Radiology Breast Imaging Reporting and Data System (BI-RADS) final assessment categories from radiology reports. This HIPAA-compliant study was granted institutional review board approval with waiver of informed consent. This cross-sectional study involved 1,165 breast imaging reports in the electronic medical record (EMR) from a tertiary care academic breast imaging center from 2009. Reports included screening mammography, diagnostic mammography, breast ultrasound, combined diagnostic mammography and breast ultrasound, and breast magnetic resonance imaging studies. Over 220 reports were included from each study type. The recall (sensitivity) and precision (positive predictive value) of a NLP algorithm to collect BI-RADS final assessment categories stated in the report final text was evaluated against a manual human review standard reference. For all breast imaging reports, the NLP algorithm demonstrated a recall of 100.0 % (95 % confidence interval (CI), 99.7, 100.0 %) and a precision of 96.6 % (95 % CI, 95.4, 97.5 %) for correct identification of BI-RADS final assessment categories. The NLP algorithm demonstrated high recall and precision for extraction of BI-RADS final assessment categories from the free text of breast imaging reports. NLP may provide an accurate, scalable data extraction mechanism from reports within EMRs to create databases to track breast imaging performance measures and facilitate optimal breast cancer population management strategies.     

乳腺癌超声BI-RADS分级与病理分型及免疫组化的比较分析

目的比较分析乳腺癌超声BI-RADS分级与病理分型及免疫组化之间的关系。方法随机选取2014年12月~2016年12月间我院收治的乳腺癌患者62例作为研究对象,对62例患者的63个乳腺癌肿块的超声表现进行分析,并根据BI-RADS分级评估乳腺癌肿块,术后对标本进行病例组织学分类,分析免疫组化指标、超声表现两者间的相关性。结果 62例患者中,单侧多发1例,单侧单发61例。62例乳腺癌患者的63个肿块中3个(4.76%)3级,14个(22.22%)4级,46个(73.02%)5级;62例乳腺癌患者的63个肿块的位置,38个(60.32%)左乳、25个(39.68%)右乳。其中49个(77.78%)浸润性导管瘤,5个(7.94%)导管内癌,3个(4.76%)黏液腺癌,2个(3.17%)乳头状癌、3个(4.76%)浸润性小叶癌,1个(1.59%)鳞癌;49个浸润性导管瘤中有39个为5级,6个为4级,4个为3级,5个导管内癌中4个为5级,1个为4级,3个浸润性小叶癌中2个为5级1个为4级,2个乳头状癌和1个鳞癌均为5级,3个黏液腺癌为4级。结论 BI-RADS分级分析乳腺肿块的恶性特征准确性高,乳腺癌超声BI-RADS分级与病理分型及免疫组化间有相关性,BI-RADS分级能够对乳腺肿块的恶性特征进行比较准确的分析,能够为乳腺癌的临床治疗提供依据,确定有效的治疗方案,在乳腺癌的诊断中应用价值较高。     

Underestimation of invasive lesions in patients with ductal carcinoma in situ of the breast diagnosed by ultrasound-guided biopsy: A comparison between patients with and without HER2/neu overexpression

Purpose

To determine the rate of underestimation of ductal carcinoma in situ (DCIS) diagnosed at imaging-guided biopsy and to analyze its association with HER2/neu oncogene, an important biomarker in assessing the tumour aggressiveness and guiding hormone therapy for breast cancer.

Methods

We retrospectively reviewed 162 patients with DCIS diagnosed by imaging-guided core needle biopsy between January 2008 and March 2013. All of these patients received surgical excision, and in 25, the diagnosis was upgraded to invasive breast cancer. In this study, we examined the ultrasound, mammographic features and histopathological results for each patient, and compared these parameters between those with and without HER2/neu overexpression.

Results

Of the 162 DCIS lesions, 110 (67.9%) overexpressed HER2/neu. Nineteen patients with HER2/neu overexpressing DCIS (n = 19/110, 17.3%) were upgraded after surgery to a diagnosis of invasive breast cancer. In this group, the upgrade rate was highest in patients with a dilated mammary duct pattern (42.1%, n = 8/19, p = 0.02) and the presence of abnormal axillary nodes (40.0%, n = 12/30, p < 0.01) at ultrasound and was significantly associated with comedo tumour type on pathology.

Conclusions

Biopsy may underestimate the invasive component in DCIS patients. Sonographic findings of dilated mammary ducts and presence of abnormal axillary lymph nodes may help predicting the invasive components and possibly driving more targeted biopsy procedures.     

乳腺超声随访生长型BI-RADS3类病变与恶性肿瘤相关的特征

目的：分析乳腺超声随访生长型乳腺影像报告和数据系统(BI-RADS)类病变与恶性肿瘤相关的特征。方法：选择2018年11月~2021年11月医院随访115例生长型BI-RADS3类病变患者作为研究对象,患者诊断与随访均行乳腺超声检查,分析患者随访期间生长型BI-RADS3类病变变化,生长型BI-RADS3类病变变化与超声检查表现相关性,生长型BI-RADS3类病变恶性化影响因素,超声检查表现对患者病情变化预测价值。结果：115例患者随访结束证实良性91例,恶性24例;良性与恶性患者最大径增长率、前后径增长率、边界及内部回声等超声表现比较存在统计学意义(P＜0.05);多因素Logistic回归分析,结果显示内部回声不是生长型BI-RADS3类病变恶性化影响因素(P＞0.05),最大径增长率、前后径增长率以及边界是生长型BI-RADS3类病变恶性化影响因素(P＜0.05);受试者工作特征曲线显示,最大径增长率、前后径增长率以及边界用于预测生长型BI-RADS3类病变良恶性曲线下面积(AUC)分别为0.635、0.820、0.598,三指标联合AUC为0.868。结论：生长型BI-RADS3类病变病情变化与随访超声表现关系密切,而部分超声表现用于预测BI-RADS3类病变变化有一定价值。     

Variability of Breast Density Classification Between US and UK Radiologists

Purpose

To assess whether subjective breast density categorization remains the most useful way to categorize mammographic breast density and whether variations exist across geographic regions with differing national legislation.

BI-RADS3-4类乳腺病变X线征象与病理对照分析

目的 研究BI-RADS3-4类乳腺病变的X线征象与病理结果的相关性。方法 对2014-01~2015-08被评估为BI-RADS3-4类的181例患者共220个病灶的X线征象,采用χ²检验分析其与良恶性之间的关系。结果 被分类为BI-RADS3类的病变71例,经病理证实为良性者60例,恶性者11例;被分类为BI-RADS4类的病例共149例,经病理证实为恶性者97例,良性者52例。X线征象中,肿块形态、边缘、周围结构,钙化类型、钙化分布及淋巴结密度、形态在良恶性病变之间有统计学差异(P＜0.05);腺体类型、肿块大小、密度及淋巴结大小、数目与病变良恶性之间无统计学差异(P＞0.05)。结论 BI-RADS3-4类乳腺病变的X线征象对良恶性病变的鉴别具有重要意义,其中肿块边缘征象及周围结构在良恶性病变的定性分析中更具诊断价值。