超声积分法对乳腺实性肿块的鉴别诊断价值的研究

目的 探讨超声积分法在乳腺实性肿块良、恶性中的鉴别诊断价值.方法 选择经手术病理证实的125例136个乳腺实性肿块,常规记录全部乳腺肿块的超声征象,并给予赋值评分,计算每个肿块的总积分.根据病变的评分值将其分类,与病理结果对照,采用受试者工作特性曲线(ROC曲线)评价超声积分的诊断价值.结果 由肿块的形态、边界、有无包膜、纵横比例、后方回声、内部回声、有无微钙化及血流显示8项指标综合而成的肿块的总积分有差异,恶性肿块得分高于良性肿块;ROC曲线下的面积Az=0.915,其95%可信区间为(0.863、0.968).总积分13.5分作为临界值,其敏感性、特异性分别为84.9%、88.9%.结论 超声积分法能半定量分析乳腺实性肿块的二维及彩色多普勒超声征象,可以提高超声诊断的准确率.     

Comparative Study of Automated Breast 3-D Ultrasound and Handheld B-Mode Ultrasound for Differentiation of Benign and Malignant Breast Masses

The automated breast volume scanner (ABVS) represents a new technology for diagnosing breast masses. In this study, a total of 219 breast masses in 175 patients underwent both conventional handheld B-mode ultrasound (HHUS) and ABVS examinations, and the differences in the diagnostic values of the two modalities for benign and malignant breast masses were compared with the final pathologic findings. In addition, the diagnostic accuracy for breast masses with features including retraction phenomenon and hyperechoic rim in the coronal plane of the ABVS was evaluated. There were no differences between the ABVS and HHUS in terms of sensitivity (92.5% vs. 88.0%), specificity (86.2% vs. 87.5%), accuracy (88.1% vs. 87.2%), false-positive rate (13.8% vs. 12.5%), false-negative rate (11.8% vs. 7.5%), positive predictive value (74.7% vs. 75.6%) and negative predictive value (96.3% vs. 94.3%) (p > 0.05 for all). However, there were significant differences between the malignant and benign masses with respect to retraction phenomenon and hyperechoic rim in the coronal plane of the ABVS. For retraction phenomenon, both the specificity and positive predictive value of a malignant diagnosis reached 100%, and the accuracy and false-positive rate were 96.8% and 0, respectively; for the hyperechoic rim, the specificity, negative predictive value and accuracy of a benign diagnosis were 92.8%, 95.3% and 95.9%, respectively. Overall, ABVS is a promising modality for the clinical diagnosis of breast masses with retraction phenomenon and hyperechoic rim in the coronal plane, although the ABVS and HHUS do not differ in diagnostic accuracy for the differentiation of malignant or benign breast masses.     

三维超声成像在卵巢囊性肿物的应用研究

为了探讨三维超声成像在卵巢囊性肿物诊断中的应用价值，对３１例卵巢囊性肿物患者进行了三维超声成像研究，并与二维超声及术中所见进行对比。结果表明：三维超声重建图像清晰，形象直观，立体感强，可以确定病变的形态特征，各结构的空间位置关系及内部的细微结构，与术中所见一致，弥补了二维超声的不足，尤其对卵巢混合性肿物内部结构的观察，三维超声成像更显其优越性。     

Coherence-Based Beamforming Increases the Diagnostic Certainty of Distinguishing Fluid from Solid Masses in Breast Ultrasound Exams

Ultrasound is often used as a supplement for mammography to detect breast cancer. However, one known limitation is the high false-positive rates associated with breast ultrasound. We investigated the use of coherence-based beamforming (which directly displays spatial coherence) as a supplement to standard ultrasound B-mode images in 25 patients recommended for biopsy (26 masses in total), with the eventual goal of decreasing false-positive rates. Because of the coherent signal present within solid masses, coherence-based beamforming methods allow solid and fluid-filled masses to appear significantly different (p < 0.001). When presented to five board-certified radiologists, the inclusion of robust short-lag spatial coherence (R-SLSC) images in the diagnostic pipeline reduced the uncertainty of fluid-filled mass contents from 47.5% to 15.8% and reduced the percentage of fluid-filled masses unnecessarily recommended for biopsy from 43.3% to 13.3%. These results are promising for the potential introduction of R-SLSC (and related coherence-based beamforming methods) into the breast clinic to improve diagnostic certainty and reduce the number of unnecessary biopsies.     

超声造影增强强度在乳腺肿块诊断中的价值

目的研究声诺维超声造影增强强度在乳腺良恶性肿块诊断中的价值。方法应用超声造影技术观察35例乳腺肿块微血管分布，计算机定量测量肿块增强强度值，对比良恶性肿瘤的造影强度特征。结果乳腺肿块超声造影增强强度值恶性组明显大于良性组，恶性组增强开始时间、达峰值时间比良性组早，两组比较，差异有显著性意义。结论声诺维超声造影有助于鉴别诊断乳腺良恶性肿瘤及估测预后。     

三维超声成像测定卵巢囊性肿瘤容积

目的　为了探讨三维超声成像在卵巢囊性肿瘤定量分析中的应用价值。方法　本文采用二维、三维超声对 10例病人的卵巢囊性肿瘤容积进行测定 ,并与术后标本容积比较。结果　不论肿瘤规则与否 ,三维超声测量肿瘤容积与实际容积间无明显差异 ;而二维超声测值与实际值差异明显。结论　三维超声较二维超声能更准确地测定肿瘤容积 ,为临床诊断和治疗提供了可靠的定量依据     

B-flow超声显像技术诊断乳腺混浊性囊性肿块

目的探讨B-flow超声显像技术对乳腺混浊性囊性病变的诊断价值。方法前瞻性对经高频二维超声及CDFI难以判断液、实性质的102个低回声乳腺肿块进行B-flow显像,并结合病理对照分析。结果102个乳腺肿块经B-flow技术被判断为液性者或液性为主者87个,实性者15个。经穿刺抽液和/或外科手术后确诊囊肿10个,纤维囊性乳腺病81个,导管内乳头状癌1个,乳腺脓肿合并液化3个,乳腺炎性包块1个,纤维腺瘤6个。B-flow显像对102个低回声肿块中囊肿诊断的符合率为90.2%,灵敏度为90.5%,特异度为85.7%。其中有9个液性肿块经B-flow成像被误诊为实性肿块,9个肿块表面距离体表均>3cm。结论B-flow显像技术能更好地鉴别位置表浅的乳腺混浊性囊肿,可为乳腺的超声影像研究提供一种简便有效的检查方法。     

超声引导粗针活检乳腺肿块的临床研究

目的研究超声引导下应用粗针活检对乳腺可触及实性肿块诊断的价值。方法彩色超声引导下14G切割针自动活检枪活检30例患者的47个乳腺可触及实性肿块并与细针活检比较。结果47个病灶活检结果:良性病灶29个,恶性病灶17个,假阴性1例,手术切除病理诊断为乳腺腺病;超声引导下14G切割针取材成功率为98%,诊断正确率为83%。结论超声引导下14G切割针没有增加并发症的发生率,安全创伤小,标本满意率高,病理诊断准确性高。     

A Model for Predicting Malignant Sub-pleural Solid Masses Using Grayscale Ultrasound and Ultrasound Elastography

This article aimed to establish a prediction model of grayscale sonography and ultrasound elastography for malignant sub-pleural solid masses and evaluate its diagnostic value. The study included 153 patients, including 89 patients with malignant tumors and 64 patients with benign diseases. Statistical differences between the malignant and benign groups were found in the factors of age, air bronchogram, borderline, shape and elasticity score (p < 0.05). Age, elasticity score and borderline were effective factors for predicting malignant sub-pleural solid masses, offering an area under the receiver operating characteristic curve (AUROC) value of 0.72 (95% confidence interval [CI] 0.64–0.80), 0.73 (95% CI 0.65–0.79) and 0.70 (95% CI 0.62–0.77), respectively. The AUROC value of the prediction model for malignant sub-pleural solid masses was 0.88 (95% CI 0.81–0.92), which indicates that the prediction model was able to improve the diagnostic accuracy and that it may prove a useful auxiliary diagnostic tool for malignant sub-pleural solid masses, especially in primary health care institutions in developing countries.     

弹性成像结合卡方自动交互检测法在鉴别乳腺肿块良恶性中的应用

目的利用卡方自动交互检测法开发一种简单的算法来鉴别乳腺肿块的良恶性。方法经过病理证实的201例乳腺肿块患者纳入此项研究,每例患者都有一个乳腺肿块经常规超声检查、声触诊组织成像(VTI)及声触诊组织量化(VTQ)技术成像,并测量出VTI面积比(肿块VTI面积或肿块二维面积)及肿块VTQ或腺体VTQ。利用受试者操作特性曲线评价各项超声弹性成像参数的诊断性能,再使用卡方自动交互检测法进行分类分析。结果分类算法包括肿块VTQ及VTI面积比,其深度为两个分支(肿块VTQ>3.958或≤3.958,如果肿块VTQ≤3.958接着考虑VTI面积比≤1.304或1.304~1.493或>1.493)。分类算法的AUC为0.901、灵敏度为98.2%、特异度为68.1%,应用该算法,有30.8%的病例可以避免活检。结论联合应用肿块VTQ及VTI面积比的分类算法具有较高的诊断性能,准确度达97%,减少30%以上不必要的穿刺活检。     

乳腺增生症的声像图特征及鉴别诊断

目的 探讨乳腺增生症的声像图特征及鉴别诊断，以提高超声对乳腺增生症的诊断符合率。方法 回顾总结79例乳腺增生症的声像图特征，与病理学组织类型比较、分类，提出鉴别要点。结果 79例经手术病理证实的乳腺增生症声像图表现为单纯性小叶增生16例占20．3％，腺病及纤维腺病28例占35．4％，腺瘤样乳腺增生21例占26．6％，囊性增生9例占11．4％，硬化性增生5例占6．3％，本组诊断符合率为79．7％(63／79)，误诊率为20．3％(16／79)。结论 超声显像对乳腺增生症具有较大的诊断价值，但应注意与乳腺纤维腺瘤、乳腺癌等作鉴别。     

乳腺肿块的彩色多普勒血流显像与病理对照分析

本文对102例乳腺肿块患者进行彩色多普勒血流显像（CDFI）检查,获取肿块的二维影像、CDFI血流分级、最大流速、阻力指数等多参数指标,并与术后病理对照,结果：肿块边界不清晰形态不规则,CDFI血流分级为2-3级,Vmax≥20cm/sec,RI≥0.75诊断乳腺癌的准确性分别为81.4%,93.1%,69.2%,94%。其中,CDFI血流分级和RI尤为重要,诊断准确性均在90%以上。     

Sonoelastographic Strain Index for Differentiation of Benign and Malignant Nonpalpable Breast Masses

Objective. The purpose of this study was to evaluate the diagnostic potential of the sonoelastographic strain index for differentiation of nonpalpable breast masses. Methods. Ninety‐nine nonpalpable breast masses (79 benign and 20 malignant) in 94 women (mean age, 45 years; range, 21–68 years) who had been scheduled for a sonographically guided core biopsy were examined with B‐mode sonography and sonoelastography. Radiologists who had performed the biopsies analyzed the B‐mode sonograms and provided American College of Radiology Breast Imaging Reporting and Data System categories. The strain index (fat to lesion strain ratio) was calculated by dividing the strain value of the subcutaneous fat by that of the mass. The histologic result from the sonographically guided core biopsy was used as a reference standard. The diagnostic performance of the strain index and that of B‐mode sonography were compared by receiver operating characteristic (ROC) curve analysis. Results. The mean strain index values ± SD were 6.57 ± 6.62 (range, 1.29–28.69) in malignant masses and 2.63 ± 4.57 (range, 0.54–38.76) in benign masses (P = .019). The area under the ROC curve values were 0.835 (95% confidence interval [CI], 0.747–0.902) for B‐mode sonography and 0.879 (95% CI, 0.798–0.936) for the strain index (P = .490). The sensitivity, specificity, positive predictive value, and negative predictive value were 95% (19 of 20), 75% (59 of 79), 48% (19 of 39), and 98% (59 of 60), respectively, when a best cutoff point of 2.24 was used. Conclusions. The strain index based on the fat to lesion strain ratio has diagnostic performance comparable with that of B‐mode sonography for differentiation of benign and malignant breast masses.     

基于超声图像的迁移学习模型在 乳腺肿块良恶性鉴别诊断中的价值

目的 探讨基于超声图像的迁移学习模型在乳腺肿块良恶性鉴别诊断中的应用价值。方法 收集我院2018年5月至2021年3月经手术或穿刺活检病理证实的300例乳腺肿块患者共计582张超声图像作为超声数据集（训练集482张,测试集100张）。采用迁移学习方法对经过ImageNet数据集预训练的三种深度卷积神经网络模型（VGG-16,Inception-v3,ResNet-50）进行训练和测试。第一次迁移学习,三种模型分别对公共数据库CBIS-DDSM(Curated　Breast　Imaging　Subset　of　DDSM)数据集中的良恶性乳腺肿块X线图像进行识别学习,并对模型进行微调;第二次迁移学习,利用超声数据集中随机挑选的训练集超声图像对三种模型进行微调。分别比较三种模型使用不同次数迁移学习后对乳腺肿块良恶性诊断效能。结果 VGG-16、Inception-v3、ResNet-50三种模型经过迁移学习后所有评价指标均有提高,其中基于ResNet-50建立的模型对乳腺肿块良恶性鉴别具有更优的效果,准确率为88.0%,敏感性为82.7%、特异性为93.8%、AUC值为0.915。结论 基于超声图像的ResNet-50迁移学习模型在乳腺肿块良恶性鉴别诊断中具有较高的准确率,可为低年资医师精准诊断提供决策支持。     

超声显像对体表软组织实质性肿块诊断价值的探讨

目的 探讨超声对体表软组织实质性肿块的诊断价值及病理基础。方法 对77例体表软组织肿块进行超声诊断并与病理对照。结果 超声对病变检出率为100％，超声与病理对照符合率为76．6％(59／77)。结论 超声诊断软组织肿块检出率高，可作为诊断此病的首选方法，但对肿块定性有局限性，术前活组织检查十分重要。     

Attention-Enriched Deep Learning Model for Breast Tumor Segmentation in Ultrasound Images

Incorporating human domain knowledge for breast tumor diagnosis is challenging because shape, boundary, curvature, intensity or other common medical priors vary significantly across patients and cannot be employed. This work proposes a new approach to integrating visual saliency into a deep learning model for breast tumor segmentation in ultrasound images. Visual saliency refers to image maps containing regions that are more likely to attract radiologists’ visual attention. The proposed approach introduces attention blocks into a U-Net architecture and learns feature representations that prioritize spatial regions with high saliency levels. The validation results indicate increased accuracy for tumor segmentation relative to models without salient attention layers. The approach achieved a Dice similarity coefficient (DSC) of 90.5% on a data set of 510 images. The salient attention model has the potential to enhance accuracy and robustness in processing medical images of other organs, by providing a means to incorporate task-specific knowledge into deep learning architectures.     

BI-RADS诊断标准与超声弹性成像对乳腺导管内肿瘤的诊断价值

目的 评估乳腺影像学报告及数据系统(BI-RADS)诊断标准与超声弹性成像(UE)改良5分法判断导管内肿物良恶性的诊断价值.方法 回顾性分析手术病理证实的100例患者共107个病灶(良性84个,恶性23个)行常规超声检查按照BI-RADS评分标准进行评分,再行UE检查以改良5分法为标准进行评分以及二者综合评分.以病理诊断为金标准,构建受试者应用曲线(ROC),比较2种方法的诊断效率.结果 BI-RADS标准ROC曲线下面积(AUC)0.649,UE改良5分法AUC 0.594,二者结合AUC 0.649,三者之间的差异没有统计学意义(P＞0.05).BI-RADS诊断标准的敏感性高于UE,特异性、准确性较UE低;二者结合诊断的敏感性、准确性高于UE、特异性高于BI-RADS(P＜0.05).结论 BI-RADS标准对乳腺导管内肿物良恶性判断的价值不高,UE的应用可以提高诊断准确性,但对诊断行为无明显贡献.