乳腺钼钯X射线影像中微钙化点的检测方法

乳腺癌是一种常见的妇科恶性肿瘤。早期发现、早期诊断、早期治疗对医治乳腺癌、降低死亡率至关重要。实现乳癌早期诊断的关键技术之一是及时发现乳腺X线影像中的微小钙化点并判断其是否有恶化倾向。本就目前为止乳腺X片微钙化点的检测方法进行了综述,并展望其近期发展趋势。     

基于小波分析和灰度纹理特征的乳腺X线图像微钙化点区域的提取

目的乳腺癌的早期发现对患者意义重大。为帮助医生进行乳腺癌的早期检查和诊断,本文提出利用小波分析与图像纹理特征提取相结合的方法来提取乳腺X线图像微钙化点区域,在提高检查准确性的同时避免漏检误检。方法首先利用灰度共生矩阵所提取的能量、熵、对比度、相关性以及小波分解后得到的各层高频系数的方差、能量作为图像的特征向量,然后利用支持向量机进行训练建立最优分类模型。最后利用建立的最优分类模型实现乳腺X线图像微钙化点区域的提取并利用检出率和误检率对结果进行评估。结果使用临床数据进行验证,结果表明利用小波分析与图像纹理特征提取相结合的方法能有效提取乳腺图像中的微钙化点区域。结论基于小波分析和灰度纹理特征的乳腺X线图像微钙化点区域的提取方法比单一的图像纹理特征提取或小波分析等方法,提取的效果更好。另外,该方法设计简单,更易于实现乳腺癌的自动化诊断。     

采用多尺度多级组合分类器快速定位乳腺X片中的感兴趣区域

乳腺癌是妇女常见恶性肿瘤之一,早期诊断和治疗是降低乳腺癌患者死亡率的关键. 微钙化是乳腺癌早期的一个重要标志,因此快速准确地找出乳腺X光片中含有微钙化簇的感兴趣区域(ROI)是成功诊断的第一步.乳腺X光片中含有大量无病变区域和少量微钙化区域,形成了一种典型的不对称分类问题.本研究结合大量无病变区域的信息训练多级组合分类器,并借助多尺度方法加快筛选速度,以定位ROI.在真实的数字化X线乳腺照片上的实验表明,该方法在无漏检的情况下,可以排除92.64%的正常区域,而且基于Matlab处理,对于每幅图片的平均处理时间仅为7 s.     

基于钼靶X线影像的乳腺微钙化点良恶性识别算法研究

目的:乳腺癌是女性最常见的恶性肿瘤之一,早期发现、早期诊断,对提高乳腺癌治愈率和降低死亡率具有重大意义。早期乳腺癌的计算机辅助诊断方面的研究已经成为乳腺图像处理领域研究的热点和难点问题之一,具有重大的理论价值和社会意义。方法:本论文正是针对上述问题,对早期乳腺癌的计算机辅助诊断算法问题作了探索性研究,进行了微钙化点病变类型识别算法的研究。结果:通过钙化点特征提取和优化及病变类型识别,给出初步诊断结果。结论:用该算法对钙化点进行计数是可行的,具有快速、简单、准确的优点,而且计数结果不受钙化点形态、大小的影响。     

基于小波变换的乳腺X线影像微钙化点感兴趣区域提取新技术

为乳腺癌早期诊断和乳腺X线影像微钙化点计算机辅助检测作前期预处理,提出了一种基于小波变换的微钙化点感兴趣区提取新技术。其具体思路是:(1)将乳腺区域图像提取成等大的子图像;(2 )对每一幅子图像进行小波变换,根据特征参数ρ讨论最优小波变化参数和阈值T;(3)根据阈值T判别子图像是否属于感兴趣区。对临床实际病例(2 0幅乳腺X线影像)的试验结果表明,该方法具有较高的检出率(89.7% ) ,和较为满意的假阳性率(2 .1% )。     

基于医学图像内容检索的计算机辅助乳腺X线影像诊断技术

乳腺癌是女性中高发的恶性肿瘤疾病.近年来,其发病率呈增高趋势.早期发现、早期诊断和早期治疗是降低乳腺癌患者死亡率的关键.计算机辅助诊断(CAD)技术能够有效提高早期诊断的准确性,而基于内容医学图像检索(CBMIR)技术的引入,为乳腺癌的诊断提供了有效的决策支持.文中就近年来基于医学图像内容检索的计算机辅助乳腺X线影像诊断关键技术进行了较为详尽的综述,包括微钙化和肿块检测、特征提取、相似性测度和相关反馈技术等,同时对该领域的发展趋势进行了展望.     

乳腺X线图像的计算机辅助诊断技术研究进展

乳腺癌是妇女中多发的癌症 ,其发病率近年来有增高趋势。早期发现、早期诊断、早期治疗是降低乳腺癌患者死亡的关键。本文就临床上首选的影像学诊断方法——钼靶 X线乳腺摄影的计算机辅助诊断技术进行了较为详细的综述 ,并就该技术的发展趋势进行了展望     

数字图像增强中灰度变换方法在乳腺X线片中的应用

图像增强技术作为一种基本的图像处理技术,其目的是对原始图像进行加工,得到视觉效果更好更有用的图像.乳腺X线片是当今早期诊断乳腺癌的有效手段,但由于人体肉眼分辨能力有限以及人为疏忽等原因,其中有很大一部分诊断信息没有被人们所利用,因此对乳腺X线片进行增强处理很重要.本文在讨论包括线性变换、非线性变换和直方图均衡化三种用于图像增强灰度变换方法基础上,利用MATLAB编程实现相关算法,将其用于乳腺X线片的处理.结果表明,以上三种灰度变换方法均提高了图像的对比度,改善了图像的显示效果.上述三种灰度变换方法应用于临床,均将有利于医生进行微钙化点检测和疾病诊断.     

乳腺钼靶X线影像中结构扭曲检测技术研究的进展

乳腺癌是全球女性发病率最高的恶性肿瘤,通过筛查实现早期发现、早期诊断和早期治疗对降低乳腺癌死亡率至关重要。乳腺钼靶X线摄影术是目前最普遍适用的乳腺癌筛查方法。有效检测乳腺钼靶X线影像中的结构扭曲病灶有利于提高筛查的质量和效率。就目前乳腺钼靶X线影像中结构扭曲检测技术的研究现状、存在的问题和发展趋势进行了综述。     

乳腺X线检查在早期乳腺癌诊断中的价值

目的:探讨早期乳腺癌的X线诊断价值。方法:回顾性分析经手术病理证实的122个乳腺癌(114例)的乳腺X线表现,依据美国放射学会乳腺影像报告和数据系统(Breast imaging reporting and data system,BI-RADS)分类标准,进行乳腺X线判读。结果:122个乳腺癌中导管内原位癌23例(18.9%),浸润性导管癌77例(63.1%),小叶原位癌1例,浸润性小叶癌4例,乳头状癌12例,粘液癌5例。导管内原位癌乳腺X线影像学多不具备典型恶性征象,21例(91%)伴钙化,诊断BI-RADS-4a以上正确率为91%。浸润性导管癌1级多数不具备典型恶性征象,诊断BI-RADS-4a以上正确率为75%。浸润性导管癌2级(33例)和3级(40例)乳腺X线影像有相同的征象,二者较导管原位癌具有较明显的恶性征象,浸润性导管癌2级和3级诊断BI-RADS-4b以上正确率为77%。结论:按照BI-RADS分类标准判读乳腺X线影像在诊断早期乳腺癌中有重要临床意义。     

“Hippocrates-mst”: a prototype for computer-aided microcalcification analysis and risk assessment for breast cancer

One of the most common cancer types among women is breast cancer. Regular mammographic examinations increase the possibility for early diagnosis and treatment and significantly improve the chance of survival for patients with breast cancer. Clustered microcalcifications have been considered as important indicators of the presence of breast cancer. We present “Hippocrates-mst”, a prototype system for computer-aided risk assessment of breast cancer. Our research has been focused in developing software to locate microcalcifications on X-ray mammography images, quantify their critical features and classify them according to their probability of being cancerous. A total of 260 cases (187 benign and 73 malignant) have been examined and the performance of the prototype is presented through receiver operating characteristic (ROC) analysis. The system is showing high levels of sensitivity identifying correctly 98.63% of malignant cases.     

基于空-频域差值与超分辨率反馈网络的乳腺微钙化区域检测技术

【摘要】乳腺癌的早期症状在乳腺钼靶图像中主要表现为微钙化点,微钙化区域的真假阳性检测对于乳腺癌早期筛查具有重要意义。首先,对DDSM乳腺数据集中的图像进行预处理,去除噪声及无关组织干扰;其次,基于空-频域差值图像技术实现了疑似微钙化点的分割,取得的敏感性为91.00%,但假阳性率也较高（34.00%）,并根据疑似点的质心位置自动截取感兴趣区域;然后,通过超分辨率反馈网络算法进行微钙化区域超分辨率重建;最后,提取感兴趣区域的纹理特征,将Gentle AdaBoost算法和单层决策树算法相结合,构建强分类器GAB-DS对区域进行分类,将微钙化区域和正常组织分离开来,GAB-DS分类模型取得了96.25%的准确率、94.38%的敏感性以及98.13%的特异性。实验结果表明,该模型在微钙化区域检测上性能优越,可用于辅助临床乳腺癌检测及诊断,具有一定的临床应用价值。     

Initial diagnosis of breast cancer via cytological examination of a pleural effusion: a rare event facilitated by recognition of an unusual morphological pattern

It is uncommon for breast carcinoma to present as a malignant serous effusion. Here, we describe a case in which the initial diagnosis of an occult invasive ductal carcinoma of the breast was made via cytological examination of a pleural effusion. Recognition of a cribriform architecture with intraluminal necrosis and microcalcifications in a cell block preparation was critical in making that diagnosis. To our knowledge, this specific morphological pattern of breast carcinoma in a cell block preparation from an effusion has not been reported previously.     

Detection of single and clustered microcalcifications in mammograms using fractals models and neural networks

Microcalcifications (microCas) are often early signs of breast cancer. However, detecting them is a difficult visual task and recognizing malignant lesions is a complex diagnostic problem. In recent years, several research groups have been working to develop computer-aided diagnosis (CAD) systems for X-ray mammography. In this paper, we propose a method to detect and classify microcalcifications. In order to discover the presence of microCas clusters, particular attention is paid to the analysis of the spatial arrangement of detected lesions. A fractal model has been used to describe the mammographic image, thus, allowing the use of a matched filtering stage to enhance microcalcifications against the background. A region growing algorithm, coupled with a neural classifier, detects existing lesions. Subsequently, a second fractal model is used to analyze their spatial arrangement so that the presence of microcalcification clusters can be detected and classified. Reported results indicate that fractal models provide an adequate framework for medical image processing; consequently high correct classification rates are achieved.     

基于Adaboost-决策树算法的乳腺微钙化区域真假阳性检测

乳腺癌的早期症状在乳腺钼靶图像中主要表现为微钙化点,微钙化区域的真假阳性检测对于乳腺癌早期筛查具有重要意义。本研究选取DDSM图像进行实验,手动截取了400个疑似钙化区域。首先提取全部区域的Haralick纹理特征和灰度游程矩阵特征建立特征集,然后使用Adaboost算法集成决策树,构建强分类器AB-DT,对400个疑似钙化区域进行分类。实验发现当集成462棵决策树时,模型分类性能最佳。最后进行10折交叉验证,AB-DT算法达到了91.75%的准确率,91.75%的敏感性,91.79%的特异性,F1指数为0.918 7。该模型在微钙化真假阳性检测上性能优越,可用于辅助乳腺微钙化点检测,具有一定的临床应用价值。     

Immunhistochemie in der Mammapathologie

Proliferative epithelial breast lesions include a wide variety of benign hyperplastic and noninvasive neoplastic lesions, as well as invasive carcinomas. Mammographically these lesions may show microcalcifications, architectural distortions or mass lesions. The task of the pathologist begins with a preoperative diagnosis by means of minimally invasive biopsy. His diagnosis forms the basis for not only the radiological-pathological correlation diagnosis, but also for the management of benign proliferative breast disease lesions, as well as therapeutic decisions in the case of malignant lesions. In daily practice, immunohistochemistry is the method of choice for clarifying difficult cases. The aim of this chapter is to describe the relevant markers in breast pathology and to provide an algorithmic approach to different proliferative breast disease lesions.     

Cellular composition of the nipple aspirate specimen of breast fluid. II. Abnormal findings.

Studies of cellular findings in nipple aspirate specimens from 796 women revealed 50 women with abnormal cells and/or microcalcifications. The clinical correlation of these abnormalities with breast cancer appears to be highly significant: abnormal cells were found in 50% of the satisfactory specimens from women who had breast cancer or who had had a previous mastectomy for breast cancer. Continued observation of the women for evidence of regression, persistence, or progression of the cytologic abnormalities is required to determine the significance of the abnormalities. Microcalcifications were present in nipple aspirates from 27% of the women whose mammograms were interpreted as showing calcification. The absence of mammographic confirmation of the cytologic findings of microcalcifications may be an indication for re-evaluation of the existing mammograms and repeat clinical and mammographic examination at more frequent intervals for early localization of small lesions.     

Improvement of digital mammogram images using histogram equalization, histogram stretching and median filter

Breast cancer is one of the most important diseases in females worldwide. According to the Malaysian Oncological Society, about 4% of women who are 40 years old and above are involved have breast cancer. Masses and microcalcifications are two important signs of breast cancer diagnosis on mammography. Enhancement techniques, i.e. histogram equalization, histogram stretching and median filters, were used to provide better visualization for radiologists in order to help early detection of breast abnormalities. In this research 60 digital mammogram images which includes 20 normal and 40 confirmed diagnosed cancerous cases were selected and manipulated using the mentioned techniques. The original and manipulated images were scored by three expert radiologists. Results showed that the selected methods have a positive significant effect on image quality.     

Detection of Microcalcification Clusters Using Hessian Matrix and Foveal Segmentation Method on Multiscale Analysis in Digital Mammograms

Mammography is the most efficient technique for detecting and diagnosing breast cancer. Clusters of microcalcifications have been mainly targeted as a reliable early sign of breast cancer and their earliest detection is essential to reduce the probability of mortality rate. Since the size of microcalcifications is very tiny and may be overlooked by the observing radiologist, we have developed a Computer Aided Diagnosis system for automatic and accurate cluster detection. A three-phased novel approach is presented in this paper. Firstly, regions of interest that corresponds to microcalcifications are identified. This can be achieved by analyzing the bandpass coefficients of the mammogram image. The suspicious regions are passed to the second phase, in which the nodular structured microcalcifications are detected based on eigenvalues of second order partial derivatives of the image and microcalcification pixels are segmented out by exploiting the foveal segmentation in multiscale analysis. Finally, by combining the responses coming out from the second order partial derivatives and the foveal method, potential microcalcifications are detected. The detection performance of the proposed method has been evaluated by using 370 mammograms. The detection method has a TP ratio of 97.76 % with 0.68 false positives per image. We have examined the performance of our computerized scheme using free-response operating characteristics curve.     

Negative prognostic value of intra-ductal fat infiltrate in breast cancer

BackgroundRecent studies showed a correlation between Body Mass Index and both breast cancer occurrence and progression. Nevertheless, no study reported an accurate evaluation of intra-ductal fat infiltrate. Therefore, the main aim of this study was to evaluate the putative association between intra-ductal fat infiltrate (IDFi) and breast cancer subtypes by using digital pathology.MethodsWe retrospectively collected 220 breast biopsies. Paraffin serial sections were used for haematoxylin and eosin staining and immunohistochemical evaluation of the following markers: estrogen receptor (ER), progesterone receptor (PR), Ki67 and c-erb2. Three haematoxylin and eosin sections for each paraffin block were digitalized. Digital slides were used to evaluate the areas of IDFi. Five randomized areas were evaluated for each slide. By using GraphPad software IDFi areas was correlated with a) breast cancer histotype, b) presence of microcalcifications and c) biomarkers expression.ResultsBreast biopsies were classified as follow: 20 normal breast, 50 benign lesions, and 150 malignant lesions (85 ductal in situ carcinomas; 65 ductal infiltrating carcinomas). Statistical analysis showed a significant increase of IDFi in malignant lesions as compared to both normal breast and benign lesions. We noted higher IDFi in breast ductal carcinomas as compared to lobular lesions. Significant differences were observed between breast lesions with microcalcifications respect to lesions without calcifications. Noteworthy, we also found a positive association between IDFi and the expression of both ER and Ki67.ConclusionResults of our study highlighted the possible role of fat in breast cancer progression suggesting a negative prognostic value of IDFi.