用于脂肪肝分级诊断的超声图像增强算法

提出一种针对脂肪肝分级诊断的超声图像增强算法,提高超声图像对脂肪肝的分级诊断能力。通过分析正常肝和不同程度脂肪肝在超声图像上的表现特点,本研究提出了一种将灰度的分段线性变换方法和改进的局部对比度增强方法相结合的图像增强方法,该方法首先通过灰度分段线性变换处理来凸显图像的脂肪肝特征,然后利用改进的局部对比度增强处理来增强图像的细节,提高图像的整体质量。应用该方法分别对正常肝和轻度、中度以及重度脂肪肝超声图像进行增强处理并对比原图像,结果表明,增强后图像的脂肪肝特征更加凸显,图像细节得到了提高,不同程度脂肪肝图像之间的差异更明显,具有更好的脂肪肝诊断信息。本研究提出的方法可提高超声图像分级诊断脂肪肝的能力,具有一定的实际应用价值。     

基于BI-RADS的超声乳腺图像的计算机辅助诊断研究

目的 根据乳腺超声图像的分级标准(BI-RADS)为诊断的指导,初步完成了诊断系统的设计.在图像处理中引入LBM滤波,并用无初始化的C-V模型进行分割,从形态特征与纹理特征入手,提取图像中相应的特征参数.采用支持向量机方法 对所提取的特征参数进行分类.通过对88幅乳腺超声图像(其中良性37例、恶性51例)进行训练和测试,得到的判别准确率、敏感性和特异性分别为91.4%、94.4%和86.4%.结果表明,依据BI-RADS的分级特征研究有利于计算机辅助诊断在临床中的应用.     

基于改进型组织特异纹理滤波器的乳腺肿瘤超声图像处理

基于乳腺超声图像的多参数纹理分类实验,改进了Gjenna Stippel等的自适应纹理滤波器,通过引入模糊函数、增加重叠区域和迭代次数的措施,在减少图像噪声的同时,增强肿瘤与周围正常组织的视觉差别.量化比较乳腺超声图像经该滤波算法和几种常用滤波算法处理前后的的统计特征参量和肿瘤边缘检测的精确率,验证了该算法的有效性和优越性.     

乳腺叶状肿瘤的超声诊断与临床病理分析

目的探讨不同病理类型乳腺叶状肿瘤的超声声像图特征。方法收集2010年1月至2016年12月在内蒙古自治区人民医院肿瘤中心行乳腺肿物切除术后病理诊断为乳腺叶状肿瘤的患者28例,均为女性,年龄12~69岁,平均年龄39.07岁。术前均行乳腺超声检查,对其临床数据、病理特征及超声表现进行归纳分析。结果 28例乳腺叶状肿瘤患者,21例为良性叶状肿瘤,其中11例合并纤维腺瘤;5例为交界性叶状肿瘤,2例为恶性叶状肿瘤。良性组肿瘤瘤体内部回声呈漩涡样或小囊样改变。恶性/交界性组肿瘤大部分瘤体内部回声明显不均匀,漩涡样结构及小囊样结构杂乱、无规则,部分有较大的液化坏死区。良性组血流信号主要为Ⅰ、Ⅱ级;恶性/交界性组血流信号主要为Ⅱ、Ⅲ级。结论不同病理类型的乳腺叶状肿瘤超声声像图具有不同特点,通过分析超声图像对临床诊疗具有一定帮助。     

基于局部调整动态轮廓模型提取超声图像乳腺肿瘤边缘

提出一种基于局部调整动态轮廓模型提取超声图像乳腺肿瘤边缘的算法.该算法在Chan-Vese (CV)模型基础上,定义了一个局部调整项,采用基于水平集的动态轮廓模型提取超声图像乳腺肿瘤边缘.将该算法应用于89例临床超声图像乳腺肿瘤的边缘提取实验,结果表明:该算法比CV模型更适用于具有区域非同质性的超声图像的分割,可有效实现超声图像乳腺肿瘤边缘的提取.     

基于超声图像的乳腺钙化点自动检测技术

当前乳腺钙化点检测方法多基于X光片,难以应用于超声图像,本研究提出基于超声图像的乳腺钙化点自动检测技术,首先将乳腺超声图像中的肿瘤区域通过勾画模板提取出来,基于简单线性迭代聚类算法进行超像素分割;然后提取表征各超像素的特征量来计算显著性图,基于钙化区域显著性进行粗钙化点分割;最终对分割后的粗钙化点进行形态学检测,达到对超声图像中的细钙化点自动检测。该方法取得了较好的分割效果,具有较强的鲁棒性,为形成具有普适性的肿瘤自动诊断方案奠定了研究基础。     

乳腺肿瘤超声图像特征参数量化研究进展

乳腺肿瘤超声图像的特征量化分析对判别肿瘤的良、恶性具有重要价值。本文总结了良性和恶性乳腺肿瘤在超声图像上的特点，将乳腺良性肿瘤和恶性肿瘤鉴别特征在形状、边缘、边界、朝向、回声特点几个方面的量化方法和量化参数进行了较为全面的梳理，并对量化特征与肿瘤良、恶性之间的关系进行了分析。     

乳腺肿瘤超声图像中感兴趣区域的自动检测

由于斑点噪声、伪影以及病灶形状多变的影响,乳腺肿瘤超声图像中肿瘤区域的自动检测以及病灶的边缘提取比较困难,已有的方法主要是由医生先手工提取感兴趣区域(ROI)。本研究提出一种乳腺肿瘤超声图像中感兴趣区域自动检测的方法,选用超声图像的局部纹理、局部灰度共生矩阵以及位置信息作为特征,采用自组织映射神经网络进行分类,自动识别乳腺肿瘤区域。对包含168幅乳腺肿瘤超声图像的数据库进行识别的结果表明:该方法自动识别ROI的准确率达到86.9%,可辅助医生提取肿瘤的实际边缘以及进一步诊断。     

超声造影增强模式在乳腺良恶性肿块鉴别诊断中的价值

目的探讨超声造影增强模式对乳腺良恶性肿块鉴别诊断的价值。方法选择40例经病理组织检查证实的乳腺肿瘤患者,均为女性,年龄25～54岁,平均年龄35岁。其中良性肿块25例,恶性肿块15例。使用Siemens Sequoia 512彩色多普勒超声诊断仪,造影剂采用SonoVue,行超声造影增强方式检查。结果乳腺良恶性肿块超声增强方式不同,良性肿块以整体不同程度地均匀型增强改变为主(80%,20/25),恶性肿块主要表现为不均匀增强或周边增强(86.7%,13/15)。结论乳腺良恶性肿块超声造影增强模式不同,可为鉴别诊断提供帮助。     

基于卷积神经网络和多信息融合的三维乳腺超声分类方法

乳腺肿瘤超声图像的自动分类对于提高医生的工作效率和降低漏诊率具有十分重要的意义。新型的三维乳腺超声数据包含更多的可用于诊断的信息,但由于超声成像机理导致不同方向上的图像表现不同。针对该种乳腺超声数据,利用卷积神经网络结构的灵活性和自动学习的特性,提出3种改进的卷积神经网络模型,使其分别可以接受横截面图像输入、横截面和冠状面的双图像输入、图像和文本信息同时输入,并研究不同信息的融合对于提升乳腺肿瘤自动分类准确率的影响。在研究中,采用880幅图像(良性401幅,恶性479幅)及其标注信息进行5折交叉验证实验,得到各模型的准确率及AUC。实验结果表明,设计的模型可以适应图片与文本信息的输入,多信息融合的模型比只接受图像输入的模型准确率提升2.91%,达到75.11%的准确率和0.829 4的AUC。这些模型的提出,为多信息融合的卷积神经网络分类应用提供参考。     

高频超声、钼靶X射线在乳腺BI-RADSⅣ～Ⅴ级诊断中的应用对比研究

目的 探讨高频超声、钼靶X射线单独与联合应用在乳腺影像报告与数据系统(BI - RADS)Ⅳ～Ⅴ级诊断中的应用价值及对比研究.方法 136个病灶经病理证实为乳腺恶性肿瘤,回顾性分析高频超声、钼靶X射线影像表现,并对诊断的准确性进行统计学分析.结果 高频超声、钼靶X射线及两者联合应用对乳腺BI- RADSⅣ-Ⅴ级诊断的正确率、误诊率比较,差异有统计学意义,P＜0.01.结论 高频超声在乳腺肿块(BI - RADS Ⅳ～Ⅴ级)诊断正确率方面优于钼靶X射线,特别是肿瘤直径＜1.0cm,且不伴有钙化时,两者联合应用较单一方法更能提高乳腺肿块(BI - RADS Ⅳ～Ⅴ级)的检出率及良、恶性鉴别诊断.     

基于模糊数的乳腺肿瘤超声图像边缘快速提取方法

乳腺肿瘤边缘的准确提取在临床上对肿瘤良恶性的判别有重要的意义。本文利用三角模糊数的概念，采用重叠式窗口从图像中得到与不同隶属度对应的模糊数，从而建立以步进方格（marching square）为基本单元的模糊数平面；通过区间阈值得到步进方格上的映射区间，根据步进方格算法将对应映射区间着色绘制出肿瘤的边界。分别对恶性和良性肿瘤超声图像进行边缘提取。结果显示，本文方法相比一般提取边缘的算法具有快速准确提取乳腺肿瘤边缘的特点。实验证明本方法可以有效用于乳腺肿瘤超声图像边缘提取。     

Shape symmetry analysis of breast tumors on ultrasound images

Shape characteristics of malignant and benign breast tumors are significantly different. In this paper, the reflective symmetry of breast tumor shapes on ultrasound images was investigated. A new reflective symmetry measure (RSML) derived from multiscale local area integral invariant was proposed to quantify the shape symmetry of breast tumor, which could be computed directly from the binary mask image without the shape parameterization in terms of arc length. The performance of several symmetry measures for differentiating malignant and benign breast tumors at varying scales was evaluated and compared by receiver operating characteristic (ROC) analysis. RSML with Gaussian kernel at scale 0.04 (related to the maximal diameter) achieved the highest area under the ROC curve (0.85) on the image data of 168 tumors (104 benign and 64 malignant). The experimental results showed that the reflective symmetry of breast tumor shape was capable of providing potential diagnostic information, which could be characterized quantitatively by RSML with the appropriate scale parameter.     

基于定量影像组学的乳腺肿瘤良恶性诊断

乳腺癌是女性致死率最高的恶性肿瘤之一。为提高诊断效率,提供给医生更加客观和准确的诊断结果。借助影像组学的方法,利用公开数据集BreaKHis中82例患者的乳腺肿瘤病理图像,提取乳腺肿瘤病理图像的灰度特征、Haralick纹理特征、局部二值模式(LBP)特征和Gabor特征共139维影像组学特征,并用主成分分析(PCA)对影像组学特征进行降维,然后利用随机森林(RF)、极限学习机(ELM)、支持向量机(SVM)、k最近邻(kNN)等4种不同的分类器构建乳腺肿瘤良恶性的诊断模型,并对上述不同的特征集进行评估。结果表明,基于支持向量机的影像组学特征的分类效果最好,准确率能达到88.2%,灵敏性达到86.62%,特异性达到89.82%。影像组学方法可为乳腺肿瘤良恶性预测提供一种新型的检测手段,使乳腺肿瘤良恶性临床诊断的准确率得到很大提升。     

Computerized Determination Scheme for Histological Classification of Breast Mass Using Objective Features Corresponding to Clinicians’ Subjective Impressions on Ultrasonographic Images

It is often difficult for clinicians to decide correctly on either biopsy or follow-up for breast lesions with masses on ultrasonographic images. The purpose of this study was to develop a computerized determination scheme for histological classification of breast mass by using objective features corresponding to clinicians’ subjective impressions for image features on ultrasonographic images. Our database consisted of 363 breast ultrasonographic images obtained from 363 patients. It included 150 malignant (103 invasive and 47 noninvasive carcinomas) and 213 benign masses (87 cysts and 126 fibroadenomas). We divided our database into 65 images (28 malignant and 37 benign masses) for training set and 298 images (122 malignant and 176 benign masses) for test set. An observer study was first conducted to obtain clinicians’ subjective impression for nine image features on mass. In the proposed method, location and area of the mass were determined by an experienced clinician. We defined some feature extraction methods for each of nine image features. For each image feature, we selected the feature extraction method with the highest correlation coefficient between the objective features and the average clinicians’ subjective impressions. We employed multiple discriminant analysis with the nine objective features for determining histological classification of mass. The classification accuracies of the proposed method were 88.4 % (76/86) for invasive carcinomas, 80.6 % (29/36) for noninvasive carcinomas, 86.0 % (92/107) for fibroadenomas, and 84.1 % (58/69) for cysts, respectively. The proposed method would be useful in the differential diagnosis of breast masses on ultrasonographic images as diagnosis aid.     

Computer-Aided Diagnosis of Breast DCE-MRI Images Using Bilateral Asymmetry of Contrast Enhancement Between Two Breasts

Dynamic contrast material-enhanced magnetic resonance imaging (DCE-MRI) of breasts is an important imaging modality in breast cancer diagnosis with higher sensitivity but relatively lower specificity. The objective of this study is to investigate a new approach to help improve diagnostic performance of DCE-MRI examinations based on the automated detection and analysis of bilateral asymmetry of characteristic kinetic features between the left and right breast. An image dataset involving 130 DCE-MRI examinations was assembled and used in which 80 were biopsy-proved malignant and 50 were benign. A computer-aided diagnosis (CAD) scheme was developed to segment breast areas depicted on each MR image, register images acquired from the sequential MR image scan series, compute average contrast enhancement of all pixels in one breast, and a set of kinetic features related to the difference of contrast enhancement between the left and right breast, and then use a multi-feature based Bayesian belief network to classify between malignant and benign cases. A leave-one-case-out validation method was applied to test CAD performance. The computed area under a receiver operating characteristic (ROC) curve is 0.78 ± 0.04. The positive and negative predictive values are 0.77 and 0.64, respectively. The study indicates that bilateral asymmetry of kinetic features between the left and right breasts is a potentially useful image biomarker to enhance the detection of angiogenesis associated with malignancy. It also demonstrates the feasibility of applying a simple CAD approach to classify between malignant and benign DCE-MRI examinations based on this new image biomarker.     

Ultrastructural study of benign, low-malignant potential (LMP), and malignant ovarian tumors

Ultrastructural characteristics of benign, low-malignant potential (LMP), and malignant ovarian tumors were investigated, considering the aspects of histologic subtypes and histologic grading. In addition, the histogenesis of ovarian cancer was histologically investigated in an attempt to elucidate whether malignant tumor was generated from benign or LMP tumor, or whether it was generated de novo from normal tissues. Although all the benign, LMP, and malignant tumors appeared to be derived from Mullerian duct in serous tumors, the origin of endometrioid or mucinous tumor could not be ultrastructurally clarified. However, there was ultrastructural similarity between benign and malignant tumors among serous, endometrioid, and mucinous tumors, and it was suggested that benign adenoma may be the developmental origin of malignant tumors regardless of the histologic subtype. In addition, the investigation of endometrioid tumors revealed that the differences of histologic grading in malignant tumors reflected the ultrastructural differences, and that G1 tumor had an ultrastructure that was more similar to that of benign and LMP tumors than to that of G2 tumor.     

A comparative analysis of core needle biopsy and fine-needle aspiration cytology in the evaluation of palpable and mammographically detected suspicious breast lesions

The present study was undertaken to compare the efficacy of needle core biopsy (NCB) of the breast with fine-needle aspiration cytology (FNAC) in breast lesions (palpable and non-palpable) in the Indian set-up, along with the assessment of tumor grading with both the techniques. Fifty patients with suspicious breast lesions were subjected to simultaneous FNAC and ultrasound-guided NCB following an initial mammographic evaluation. Cases were categorized into benign, benign with atypia, suspicious and malignant groups. In cases of infiltrating duct carcinomas, grading was performed on cytological smears as well as on NCB specimens. Both the techniques were compared, and findings were correlated with radiological and excision findings. Out of 50 cases, 18 were found to be benign and 32 malignant on final pathological diagnosis. Maximum number of patients with benign diagnosis was in the fourth decade (42.11%) and malignant diagnosis in the fourth as well as fifth decade (35.48% each). Sensitivity and specificity of mammography for the diagnosis of malignancy was 84.37% and 83.33%, respectively. Sensitivity and specificity of FNAC for malignant diagnosis was 78.15% and 94.44%, respectively, and of NCB was 96.5% and 100%, respectively. But NCB had a slightly higher specimen inadequacy rate (8%). NCB improved diagnostic categorization over FNAC by 18%. Tumor grading in cases of IDC showed high concordance rate between NCB and subsequent excision biopsy (94.44%) but low concordance rate between NCB and FNAC (59.1%). NCB is superior to FNAC in the diagnosis of breast lesions in terms of sensitivity, specificity, correct histological categorization of the lesions as well as tumor grading.     

超微血管成像与乳腺肿瘤微血管密度的相关性研究

目的：探讨超微血管成像(superb microvascular imaging,SMI)与彩色多普勒血流显像(color Doppler flow imaging,CDFI)检出乳腺良恶性肿物的血流情况的差异,并分析二者与肿物病理微血管密度(microvessel density,MVD)的相关性。方法：对79名女性乳腺肿物患者共88个病灶(良性48个、恶性40个)进行SMI及CDFI检测,参照Adler分级标准,应用上述两种成像技术分别观察同一病灶的血流情况,Kappa分析以评估其一致性。对术后病理标本进行CD34免疫组织化学染色,检测肿瘤MVD表达,Spearman相关系数,分别分析MVD表达与两种模式的Adler分级的相关性。结果：两种技术方法对所有病灶血流丰富程度的一致性不佳(κ=0.67);对恶性病灶血流丰富程度的二者检测一致性差(κ=0.39);而SMI和CDFI对良性病灶血流丰富程度的检出一致性较好(κ=0.79)。相比较CDFI,SMI与MVD具有显著的正相关性(r=0.82、P<0.01)。结论：SMI对乳腺恶性肿物的微血管检出效果更佳,与病理MVD相关性较好,可作为术前无创性评估乳腺恶性肿瘤微血管的影像学方法。