Multi-task learning for segmentation and classification of tumors in 3D automated breast ultrasound images

Tumor classification and segmentation are two important tasks for computer-aided diagnosis (CAD) using 3D automated breast ultrasound (ABUS) images. However, they are challenging due to the significant shape variation of breast tumors and the fuzzy nature of ultrasound images (e.g., low contrast and signal to noise ratio). Considering the correlation between tumor classification and segmentation, we argue that learning these two tasks jointly is able to improve the outcomes of both tasks. In this paper, we propose a novel multi-task learning framework for joint segmentation and classification of tumors in ABUS images. The proposed framework consists of two sub-networks: an encoder-decoder network for segmentation and a light-weight multi-scale network for classification. To account for the fuzzy boundaries of tumors in ABUS images, our framework uses an iterative training strategy to refine feature maps with the help of probability maps obtained from previous iterations. Experimental results based on a clinical dataset of 170 3D ABUS volumes collected from 107 patients indicate that the proposed multi-task framework improves tumor segmentation and classification over the single-task learning counterparts.     

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.     

Completely automated segmentation approach for breast ultrasound images using multiple-domain features

Lesion segmentation is a challenging task for computer aided diagnosis systems. In this article, we propose a novel and fully automated segmentation approach for breast ultrasound (BUS) images. The major contributions of this work are: an efficient region-of-interest (ROI) generation method is developed and new features to characterize lesion boundaries are proposed. After a ROI is located automatically, two newly proposed lesion features (phase in max-energy orientation and radial distance), combined with a traditional intensity-and-texture feature, are utilized to detect the lesion by a trained artificial neural network. The proposed features are tested on a database of 120 images and the experimental results prove their strong distinguishing ability. Compared with other breast ultrasound segmentation methods, the proposed method improves the TP rate from 84.9% to 92.8%, similarity rate from 79.0% to 83.1% and reduces the FP rate from 14.1% to 12.0%, using the same database. In addition, sensitivity analysis demonstrates the robustness of the proposed method.     

Computer-aided diagnosis based on speckle patterns in ultrasound images

For breast ultrasound, the scatterer number density from backscattered echo was demonstrated in previous research to be a useful feature for tumor characterization. To take advantage of the scatterer number density in B-mode images, spatial compound imaging was obtained, and the statistical properties of speckle patterns were analyzed in this study for use in distinguishing between benign and malignant lesions. A total of 137 breast masses (95 benign cases and 42 malignant cases) were used in the proposed computer-aided diagnosis (CAD) system. For each mass, the average number of speckle pixels in a region of interest (ROI) was calculated to use the concept of scatterer number density. In addition, the first-order and second-order statistics of the speckle pixels were quantified to obtain the distributions of the pixel values and the spatial relations among the pixels. The performance of the speckle features extracted from each ROI was compared with the performance of the segmentation features extracted from each segmented tumor. As a result, the proposed CAD system using the speckle features achieved an accuracy of 89.1% (122/137); a sensitivity of 81.0% (34/42); and a specificity of 92.6% (88/95). All of the differences between the speckle features and the segmentation features are not statistically significant (p > 0.05). In a receiver operating characteristic (ROC) curve analysis, the Az value, area under ROC curve, of the speckle features was significantly better than the Az value of the segmentation features (0.93 vs. 0.86, p = 0.0359). The performance of this approach supports the notion that the speckle patterns induced by the scatterers in tissues can provide information for classifying tumors. The proposed speckle features, which were extracted readily from drawing an ROI without any preprocessing, also provide a more efficient classification approach than tumor segmentation.     

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.     

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.     

2-D ultrasound strain images for breast cancer diagnosis using nonrigid subregion registration

Tissue elasticity of a lesion is a useful criterion for the diagnosis of breast ultrasound (US). Elastograms are created by comparing ultrasonic radio-frequency waveforms before and after a light-tissue compression. In this study, we evaluate the accuracy of continuous US strain image in the classification of benign from malignant breast tumors. A series of B-mode US images is applied and each case involves 60 continuous images obtained by using the steady artificial pressure of the US probe. In general, after compression by the US probe, a soft benign tumor will become flatter than a stiffened malignant tumor. We proposed a computer-aided diagnostic (CAD) system by utilizing the nonrigid image registration modality on the analysis of tumor deformation. Furthermore, we used some image preprocessing methods, which included the level set segmentation, to improve the performance. One-hundred pathology-proven cases, including 60 benign breast tumors and 40 malignant tumors, were used in the experiments to test the classification accuracy of the proposed method. Four characteristic values--normalized slope of metric value (NSM), normalized area difference (NAD), normalized standard deviation (NSD) and normalized center translation (NCT)--were computed for all cases. By using the support vector machine, the accuracy, sensitivity, specificity and positive and negative predictive values of the classification of continuous US strain images were satisfactory. The A(z) value of the support vector machine based on the four characteristic values used for the classification of solid breast tumors was 0.9358.     

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。     

乳腺肿瘤常规超声联合超声造影影像组学特征与乳腺癌分子分型相关性的研究进展

影像组学（radiomics）是一种从医学影像中高通量地提取影像特征来深入挖掘内部数据信息的技术方法,通过肿瘤分割、特征提取与模型建立来辅助临床对肿瘤的诊断与治疗。在精准医疗时代,乳腺癌（breast cancer,BC）的个体化早期诊治尤为重要。常规超声是诊断乳腺肿瘤的重要影像学方法,超声造影（contrast enhanced ultrasound,CEUS）可以实时显示乳腺肿瘤微血管灌注的形态学及功能学变化,在此基础上产生的超声及超声造影影像组学在乳腺肿瘤良恶性诊断及判断乳腺癌分子分型中具有潜在临床应用价值。本文就乳腺肿瘤常规超声联合超声造影影像组学特征与乳腺癌分子分型相关性方面进行综述。     

Automated Segmentation of Ultrasonic Breast Lesions Using Statistical Texture Classification and Active Contour Based on Probability Distance

Because of its complicated structure, low signal/noise ratio, low contrast and blurry boundaries, fully automated segmentation of a breast ultrasound (BUS) image is a difficult task. In this paper, a novel segmentation method for BUS images without human intervention is proposed. Unlike most published approaches, the proposed method handles the segmentation problem by using a two-step strategy: ROI generation and ROI segmentation. First, a well-trained texture classifier categorizes the tissues into different classes, and the background knowledge rules are used for selecting the regions of interest (ROIs) from them. Second, a novel probability distance-based active contour model is applied for segmenting the ROIs and finding the accurate positions of the breast tumors. The active contour model combines both global statistical information and local edge information, using a level set approach. The proposed segmentation method was performed on 103 BUS images (48 benign and 55 malignant). To validate the performance, the results were compared with the corresponding tumor regions marked by an experienced radiologist. Three error metrics, true-positive ratio (TP), false-negative ratio (FN) and false-positive ratio (FP) were used for measuring the performance of the proposed method. The final results (TP = 91.31%, FN = 8.69% and FP = 7.26%) demonstrate that the proposed method can segment BUS images efficiently, quickly and automatically. (E-mail: hengda.cheng@usu.edu)     

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.))     

Computer-Aided Diagnosis Based on Quantitative Elastographic Features with Supersonic Shear Wave Imaging

Supersonic shear wave imaging (SSI) has recently been explored as a technique to evaluate tissue elasticity modulus and has become a valuable tool for tumor characterization. The purpose of this study was to develop a novel computer-aided diagnosis (CAD) system that can acquire quantitative elastographic information from color SSI elastography images automatically and objectively for the purpose of classifying benign and malignant breast tumors. Conventional ultrasonography (US) and SSI elastography images of 125 breast tumors (81 benign, 44 malignant), in 93 consecutive patients (mean age: 40 y, age range: 16–75 y), were obtained. After reconstruction of tissue elasticity data and automatic segmentation of each breast tumor, 10 quantitative elastographic features of the tumor and peri-tumoral areas, respectively (elasticity modulus mean, maximum and standard deviation, hardness degree and elasticity ratio), were computed and evaluated. A support vector machine (SVM) classifier was used for optimum classification via combination of these features. The B-mode Breast Imaging Reporting and Data System (BI-RADS) was used to compare gray-scale US and SSI elastography with respect to diagnostic performance. Histopathologic examination was used as the reference standard. Student's t-test, the Mann-Whitney U-test, the point biserial correlation coefficient and receiver operating characteristic curve analysis were performed for statistical analysis. As a result, the accuracy, sensitivity, specificity, positive predictive value and negative predictive value of benign/malignant classification were 95.2% (119/125), 90.9% (40/44), 97.5% (79/81), 95.2% (40/42) and 95.2% (79/83) for the CAD scheme, respectively, and 79.2% (99/125), 90.9% (40/44), 72.8% (59/81), 64.5% (40/62) and 93.7% (59/63) for BI-RADS assessment, respectively. The area under the receiver operating characteristic curve (A_z value) for the proposed CAD system using the combination of elastographic features was significantly higher than the A_z value for visual assessment by the radiologists using BI-RADS (0.97 vs. 0.91). The results indicate that SSI elastography could be used for computer-aided feature extraction, and the proposed CAD method could improve the diagnostic accuracy of classification of breast tumors to avoid unnecessary biopsy. Furthermore, elastographic features of the peri-tumoral area have the potential to provide critical information in differential diagnosis.     

应用增强算法辅助乳腺肿块的超声诊断研究

目的 探讨基于模糊逻辑和纹理分析的增强算法对超声图像乳腺肿块良恶性的检测与分类的价值.方法 研制增强算法和软件程序,选用211个病例603张乳腺肿块超声图片(其中良性109例,恶性102例)进行增强处理,以手术病理结果作为金标准,超声专家通过对原始乳腺肿块图片和处理后乳腺肿块图片进行分析,区分乳腺肿块的良、恶性,利用ROC曲线下面积(Az)表示增强前后的诊断性能,得出其敏感性、特异性、阳性预测值及阴性预测值,计算常规超声检查和增强后诊断的正确诊断率.结果 增强后乳腺肿块的超声诊断结果与病理诊断结果符合率明显提高,敏感性从原片的75.4%提高至89.6%,特异性从66.7%提高至91.2%.准确率从78.20%提高至89.57%.ROC曲线计算出增强前、后乳腺图片对乳腺肿块的定性诊断Az面积:原始图片A1=0.842,增强图片A2=0.914,Z值为5.101,二者之间差异有显著统计学意义(P<0.001).结论 新的超声图像增强算法明显改善了图像质量,提高了乳腺肿块的正确诊断率,减低误诊率,可为乳腺肿块良,恶性的诊断提供可靠依据.     

介入性超声鉴别诊断后方衰减乳腺肿瘤良恶性的应用价值

目的探讨介入性超声鉴别诊断后方衰减乳腺肿瘤良恶性的应用价值。方法回顾性分析2018年1月至2020年1月本院彩色多普勒超声检查提示肿瘤后方衰减的131例乳腺肿瘤患者的临床资料。患者均接受介入性超声、彩色多普勒超声检查、术后病理检查,统计分析介入性超声和彩色多普勒超声对乳腺肿瘤良恶性的诊断结果及诊断效能。结果以术后病理检查结果作为金标准。介入性超声检查恶性乳腺肿瘤的灵敏度、准确度、阳性预测值、阴性预测值均显著高于彩色多普勒超声检查,差异具有统计学意义(P<0.05);两种检查方法的特异度比较,差异不具有统计学意义(P>0.05)。结论介入性超声鉴别诊断后方衰减乳腺肿瘤良恶性的应用价值高,值得临床推广。     

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。     

Watershed segmentation for breast tumor in 2-D sonography

Automatic contouring for breast tumors using medical ultrasound (US) imaging may assist physicians without relevant experience, in making correct diagnoses. This study integrates the advantages of neural network (NN) classification and morphological watershed segmentation to extract precise contours of breast tumors from US images. Textural analysis is employed to yield inputs to the NN to classify ultrasonic images. Autocovariance coefficients specify texture features to classify breasts imaged by US using a self-organizing map (SOM). After the texture features in sonography have been classified, an adaptive preprocessing procedure is selected by SOM output. Finally, watershed transformation automatically determines the contours of the tumor. In this study, the proposed method was trained and tested using images from 60 patients. The results of computer simulations reveal that the proposed method always identified similar contours and regions-of-interest (ROIs) to those obtained by manual contouring (by an experienced physician) of the breast tumor in ultrasonic images. As US imaging becomes more widespread, a functional automatic contouring method is essential and its clinical application is becoming urgent. Such a method provides robust and fast automatic contouring of US images. This study is not to emphasize that the automatic contouring technique is superior to the one undertaken manually. Both automatic and manual contours did not, after all, necessarily result in the same factual pathologic border. In computer-aided diagnosis (CAD) applications, automatic segmentation can save much of the time required to sketch a precise contour, with very high stability.     

增强乳腺能谱摄影与常规乳腺X线摄影对乳腺良恶性疾病的诊断价值比较

目的探讨比较常规乳腺X线摄影(MG)与对比增强乳腺能谱摄影(CESM)对乳腺良恶性疾病的诊断价值。方法对2018年5月~2020年4月同时完成CESM和MG检查并最终获得病理诊断的74例患者纳入研究，均为女性，年龄22~56岁(41.02±8.24岁)。采用Stenographe Essential全数字化乳腺机，经由上肢静脉注射碘对比剂后采用头尾位(CC位)和内外斜位(MLO位)，一次压迫高低能曝光，得到低能图像和经过特定算法处理的高能减去低能的减影图像，由3名放射科乳腺专业医师对所得图像进行质量分析并做出影像学诊断，以病理为标准，比较CESM与MG对乳腺良恶性疾病诊断差异，并进一步对比两种方法诊断为同一肿瘤分级的诊断符合率差异，分析比较两种方法的诊断效。结果共40例乳腺恶性肿瘤、42例良性病变。MG在诊断良恶性病变的灵敏度、特异度、阳性预测值、阴性预测值及准确率分别为77.50%、80.95%、79.48%、70.27%及79.07%，而CESM的灵敏度、特异度、阳性预测值、阴性预测值及准确率分别为100%、90.47%、90.90%、100%及95.12%(P < 0.05)。MG在诊断乳腺肿瘤分级3~5级中的诊断符合率分别为79.00%、66.70%、86.70%、85.70%及100%，CESM为100%、92.30%、87.50%、90%及100%(P < 0.05)。结论CESM诊断乳腺良恶性疾病优于MG，尤其是在诊断3级及4A级的肿瘤中。      

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。     

Multi-class classification of breast tissue using optical coherence tomography and attenuation imaging combined via deep learning

We demonstrate a convolutional neural network (CNN) for multi-class breast tissue classification as adipose tissue, benign dense tissue, or malignant tissue, using multi-channel optical coherence tomography (OCT) and attenuation images, and a novel Matthews correlation coefficient (MCC)-based loss function that correlates more strongly with performance metrics than the commonly used cross-entropy loss. We hypothesized that using multi-channel images would increase tumor detection performance compared to using OCT alone. 5,804 images from 29 patients were used to fine-tune a pre-trained ResNet-18 network. Adding attenuation images to OCT images yields statistically significant improvements in several performance metrics, including benign dense tissue sensitivity (68.0% versus 59.6%), malignant tissue positive predictive value (PPV) (79.4% versus 75.5%), and total accuracy (85.4% versus 83.3%), indicating that the additional contrast from attenuation imaging is most beneficial for distinguishing between benign dense tissue and malignant tissue.     

边界增强像素级多模态声像图融合方法评估良、恶性乳腺肿瘤

目的 观察以边界增强多模态乳腺声像图像素级特征融合方法评估良、恶性乳腺肿瘤性质的价值。方法 基于乳腺肿瘤B型声像图提取边界增强图像,于超声弹性复合声像图中提取纯弹性信息图像。对多模态乳腺肿瘤声像图进行像素级特征融合,形成边界特征增强的融合图像,再以卷积神经网络(CNN)进行分类;评估融合方法分类良、恶性乳腺肿瘤的性能,并与单模态方法、特征级融合方法、无边界增强像素级图像融合方法及其他CNN模型进行对比。结果 边界增强像素级特征融合方法有助于CNN提取乳腺肿瘤特征,分类良、恶性乳腺性能最佳,其分类准确率为85.71%,特异度为85.49%,敏感度为86.16%,模型稳定。结论 边界特征增强像素级多模态声像图融合方法可用于判断良、恶性乳腺肿瘤。