基于灰度共生矩阵的乳腺钼靶图像分析

目的 应用灰度共生矩阵对乳腺钼靶图像进行纹理分析,自动分类识别乳腺肿块,实现乳腺肿瘤的辅助检测.资料与方法 纳入60例乳腺钼靶图像,其中正常乳腺组织20例,良恶性乳腺肿块各20例.对图像进行预处理后,计算各感兴趣区基于灰度共生矩阵的纹理特征值,采用支持向量机和概率神经网络分别对肿块进行分类.结果 三组各项纹理特征参数间差异有统计学意义(P＜0.05);d=2时支持向量机的三组分类准确率为91.67％、86.73％、95.00％,SPREAD值取0.1时概率神经网络的三组分类准确率为79.22％、81.77％、81.13％.结论 文中计算的纹理特征参数对乳腺肿块的良恶性判别有较显著的规律,支持向量机的分类准确率比概率神经网络的分类准确率高,该方法可成为乳腺肿瘤良恶性辅助诊断的有效方法之一.     

基于深度学习的计算机辅助诊断系统在肺癌早期诊断中的应用与进展

胸部CT扫描是肺癌早期筛查和诊断的主要检查手段,应用于胸部影像诊断领域的基于深度学习的计算机辅助诊断(CAD)系统可对CT图像上的肺结节进行检测和分类。深度学习技术可提高CAD系统的性能,尤其是在提高肺结节检测的准确率和降低假阳性率方面。笔者就CAD系统中的深度学习模型在肺结节中的应用现状和研究进展作一综述。     

人工神经元网络鉴别星形胶质细胞瘤良恶性的初步研究

目的:基于磁共振影像特点,应用人工神经元网络建立计算机辅助诊断系统,研究其判断星形胶质细胞肿瘤良、恶性的可行性及其诊断效果.材料和方法:搜集280例星形胶质细胞肿瘤病例的MRI影像资料,其中良性169例,恶性111例.由放射科医生对MRI图像进行12方面的特征提取并记录.然后将其输入人工神经元网络,对网络训练,建立计算机辅助诊断系统,以数据库病例初步评价其诊断效果并与放射科专家比较其诊断准确性.结果:数据库病例测试表明人工神经元网络的诊断结果为,对于良性和恶性星形胶质细胞瘤的诊断准确率分别为92.1%和94.3%,特异性分别为93.6%和89.9%诊断准确性接近放射科专家.结论:神经元网络可以用来进行星形胶质细胞瘤良、恶性的鉴别诊断.本研究建立的计算机辅助诊断系统对于提高良、恶性星形胶质细胞瘤鉴别诊断的准确性和医学影像学教学方面具有一定的实用价值.随着人工智能的快速发展,建立计算机辅助诊断系统帮助放射科医生提高诊断的准确性逐渐成为可能.     

基于形态特征的肺癌CT图像计算机辅助诊断初探

目的 评价计算机辅助诊断(computer-aided diagnosis,CAD)在孤立性肺结节定性诊断中的价值.方法 收集30例有病理结果的肺结节CT图像.6名具有不同临床经验的受试者首先独立阅读CT图像,判断良恶性,再应用课题组制作的软件,判断肺结节的良恶性.比较6名受试者软件使用前后的敏感度、特异度和准确率.结果 CAD使诊断敏感度由71.93%(82/114)提高到80.70%(92/114),特异度由45.45%(30/66)下降到30.30%(20/66),准确率(62.22%,112/180)无改变.结论 计算机辅助诊断可以提高肺癌诊断的敏感度.调整征象组的设置,用图片来指导征象的判断,改进算法,有可能改善辅助诊断的结果.     

人工智能在医学影像CAD中的应用

深度学习是目前人工智能领域备受关注和极具应用前景的机器学习算法，有望革新传统计算机辅助诊断系统，在精准影像诊断中发挥重要作用。本文就人工智能、机器学习、深度学习、卷积神经网络、迁移学习的基本概念以及基于深度学习的计算机辅助诊断系统在肺、乳腺、心脏、颅脑、肝脏、前列腺、骨骼影像领域及病理领域的研究现状予以综述。     

横形腹直肌肌皮瓣再造术后常规乳腺X线普查探查不能触及的复发性乳腺癌

目的评价计算机辅助诊断（CAD）工作站利用代表临床诊断陛乳腺超声（US）实践的真实数据集对癌肿分类的应用。方法数据库包括连续收集经机构审查委员会同意及HIPAA法案允许的乳腺超声扫描图像。采用了508例病人的图像数据，其中有1046个明确病灶。101例乳腺癌病人。经活检或针吸证实异常病灶的病人（n=183）数据与所有不考虑活检情况的病人（n=508）数据均被列出。通过leave—one-out—by—case分析法评价CAD工作站帮助鉴别病变良、恶性的能力。根据活检率及其结果确定放射医生对于此数据库的临床特异性。     

彩色多普勒密度量化值在诊断乳腺肿块中的价值

目的:通过与半定量分析方法的比较,评价计算机辅助定量分析彩色多普勒信号密度在乳腺癌诊断中的应用价值.材料和方法:50例乳腺肿块患者(恶性37例,良性13例),分别用半定量和计算机辅助定量分析方法检测,比较这两种方法对良、恶性乳腺肿块鉴别诊断的灵敏度、特异度和准确性.结果:良、恶性乳腺肿块CDFI等级间的差异无显著性.而良、恶性乳腺肿块CDFI密度量化值间的差异存在显著性,P＜0.01.以CDFI密度量化值大于3.62(良性乳腺肿块的CDFI密度量化平均值)作为乳腺恶性肿块的诊断标准:准确性76.0%,特异度83.8%,灵敏度53.8%,均高于CDFI等级法.结论:信号密度量化分析方法由于在对彩色血流信号的识别上,并没受到主观因素的影响,因此较半定量分析方法能更客观和可靠地反映肿块内的血供情况.     

基于深度学习的人工智能在肌骨影像中的研究进展

人工智能(AI)已成为当今社会信息技术领域最重要的技术革命,随着深度学习算法的进步及硬件的升级,人工智能发展迅猛.基于深度学习的人工智能在医学影像的图像分割、图像分类识别和计算机辅助诊断方面都有较大的发展,本文主要讲述人工智能在肌骨影像中的研究进展.     

孤立性肺结节在HDCT的计算机辅助诊断

目的本文尝试设计一款基于高清晰度CT(HDCT)图像的孤立性肺结节(SPN)计算机辅助诊断系统(CADS),以提高恶性SPN的检出率,使诊断更加客观、科学。方法收集经临床病理证实的孤立性肺结节120例,包括恶性肿瘤、良性肿瘤、结核和炎性假瘤,随机抽取60例作为实验集,60例作为验证集。实验集HDCT图像经图像预处理、感兴趣区域(ROI)基于标记的分水岭算法分割和ROI纹理特征参数提取,对获得的5项纹理特征参数做统计学处理,将统计结果应用于系统以对SPN做良恶性分析并给出提示信息。验证集HDCT图像输入系统后,对比系统预测结果与主任医师和住院医师预测结果来评价系统的可靠性。结果对比度、相关性、熵、平稳度和二阶矩t检验P值分别为0.000、0.002、0.914、0.295、0.002。对比度、相关性和二阶矩良性区间分别为(903,2003)、(2.76,3.48)、(0.01,1.54),恶性区间分别为(502,898)、(3.49,3.71)、(1.79,29.86)。系统、主任医师和住院医师的敏感度分别为83.3%、93.3%、76.7%,假阳性率分别为13.3%、16.7%、26.7%,正确率分别为85%、88.3%、75%。结论基于标记的分水岭算法对与胸壁或纵隔粘连的结节及磨玻璃病变等均可以较好地将其分割提取出来。对比度、相关性和二阶矩有统计学意义。系统在预测SPN良恶性具有较高的敏感性和准确性及最低的假阳性。CAD在SPN良恶性诊断具有一定的临床使用价值,本系统可以辅助临床医师诊断SPN良恶性。     

利用体元轮廓分组的计算机辅助超声诊断乳腺病变

<正>目的开发一种计算机辅助诊断算法来自动描绘病灶边界以对乳腺的良恶性病变进行超声鉴别,并探讨计算机辅助诊断算法的边界显示质量效果。材料与方法该研究经伦理     

基于深度学习的人工智能技术在乳腺癌筛查及影像诊断中的应用进展

人工智能技术可使计算机模拟人类的思考过程和智能活动,在医学影像领域具有强大的图像处理和特征提取能力,应用基于人工智能的乳腺癌影像筛查能够在减轻放射科医生工作负担的同时提高乳腺癌筛查和诊断的准确性及敏感性。简要总结了目前常用的乳腺X线图像公共数据集和近期乳腺癌影像学人工智能辅助诊断竞赛情况,并对基于深度学习的人工智能技术在乳腺癌影像学筛查和诊断中的最新进展予以综述。     

合成MRI技术在乳腺癌中的研究进展

合成MRI（SyMRI）是一种基于定量数据实现多种对比加权影像重建的新技术,通过一次扫描即可完成T₁、T₂值及质子密度的定量测量。其可用于乳腺肿瘤的良恶性评估,并进行乳腺癌的组织病理学分级和分子分型,在乳腺癌的诊断及指导临床治疗方面发挥了重要作用。就SyMRI技术的原理及在乳腺癌中的应用进展进行综述。     

A computerized global MR image feature analysis scheme to assist diagnosis of breast cancer: a preliminary assessment

Objectives

To develop a new computer-aided detection scheme to compute a global kinetic image feature from the dynamic contrast enhanced breast magnetic resonance imaging (DCE-MRI) and test the feasibility of using the computerized results for assisting classification between the DCE-MRI examinations associated with malignant and benign tumors.

Materials and Methods

The scheme registers sequential images acquired from each DCE-MRI examination, segments breast areas on all images, searches for a fraction of voxels that have higher contrast enhancement values and computes an average contrast enhancement value of selected voxels. Combination of the maximum contrast enhancement values computed from two post-contrast series in one of two breasts is applied to predict the likelihood of the examination being positive for breast cancer. The scheme performance was evaluated when applying to a retrospectively collected database including 80 malignant and 50 benign cases.

Results

In each of 91% of malignant cases and 66% of benign cases, the average contrast enhancement value computed from the top 0.43% of voxels is higher in the breast depicted suspicious lesions as compared to another negative (lesion-free) breast. In classifying between malignant and benign cases, using the computed image feature achieved an area under a receiver operating characteristic curve of 0.839 with 95% confidence interval of [0.762, 0.898].

Conclusions

We demonstrated that the global contrast enhancement feature of DCE-MRI can be relatively easily and robustly computed without accurate breast tumor detection and segmentation. This global feature provides supplementary information and a higher discriminatory power in assisting diagnosis of breast cancer.     

Performance of computer-aided diagnosis in the interpretation of lesions on breast sonography

RATIONALE AND OBJECTIVES: To investigate the potential usefulness of computer-aided diagnosis as a tool for radiologists in the characterization and classification of mass lesions on ultrasound. MATERIALS AND METHODS: Previously, a computerized method for the automatic classification of breast lesions on ultrasound was developed. The computerized method includes automatic segmentation of the lesion from the ultrasound image background and automatic extraction of four features related to lesion shape, margin, texture, and posterior acoustic behavior. In this study, the effectiveness of the computer output as an aid to radiologists in their ability to distinguish between malignant and benign lesions, and in their patient management decisions in terms of biopsy recommendation are evaluated. Six expert mammographers and six radiologists in private practice at an institution accredited by the American Ultrasound Institute of Medicine participated in the study. Each observer first interpreted 25 training cases with feedback of biopsy results, and then interpreted 110 additional ultrasound cases without feedback. Simulating an actual clinical setting, the 110 cases were unknown to both the observers and the computer. During interpretation, observers gave their confidence that the lesion was malignant and also their patient management recommendation (biopsy or follow-up). The computer output was then displayed, and observers again gave their confidence that the lesion was malignant and theirpatient management recommendation. Statistical analyses included receiver operator characteristic analysis and Student t-test. RESULTS: For the expert mammographers and for the community radiologists, the Az (area under the receiver operator characteristic curve) increased from 0.83 to 0.87 (P = .02) and from 0.80 to 0.84 (P = .04), respectively, when the computer aid was used in the interpretation of the ultrasound images. Also, the Az values for the community radiologists with aid and for the expert mammographers without aid are similar to the Az value for the computer alone (Az = 0.83). CONCLUSION: Computer analysis of ultrasound images of breast lesions has been shown to improve the diagnostic accuracy of radiologists in the task of distinguishing between malignant and benign breast lesions and in recommending cases for biopsy.     

Dermoscopic diagnosis of melanoma in a 4D space constructed by active contour extracted features

Dermoscopy, also known as epiluminescence microscopy, is a major imaging technique used in the assessment of melanoma and other diseases of skin. In this study we propose a computer aided method and tools for fast and automated diagnosis of malignant skin lesions using non-linear classifiers. The method consists of three main stages: (1) skin lesion features extraction from images; (2) features measurement and digitization; and (3) skin lesion binary diagnosis (classification), using the extracted features. A shrinking active contour (S-ACES) extracts color regions boundaries, the number of colors, and lesion's boundary, which is used to calculate the abrupt boundary. Quantification methods for measurements of asymmetry and abrupt endings in skin lesions are elaborated to approach the second stage of the method. The total dermoscopy score (TDS) formula of the ABCD rule is modeled as linear support vector machines (SVM). Further a polynomial SVM classifier is developed. To validate the proposed framework a dataset of 64 lesion images were selected from a collection with a ground truth. The lesions were classified as benign or malignant by the TDS based model and the SVM polynomial classifier. Comparing the results, we showed that the latter model has a better f-measure then the TDS-based model (linear classifier) in the classification of skin lesions into two groups, malignant and benign.     

Multimodality computerized diagnosis of breast lesions using mammography and sonography

RATIONALE AND OBJECTIVES: The purpose of this study is to investigate the use of computer-extracted features of lesions imaged by means of two modalities, mammography and breast ultrasound, in the computerized classification of breast lesions. MATERIAL AND METHODS: We performed computerized analysis on a database of 97 patients with a total of 100 lesions (40 malignant, 40 benign solid, and 20 cystic lesions). Mammograms and ultrasound images were available for these breast lesions. There was an average of three mammographic images and two ultrasound images per lesion. Based on seed points indicated by a radiologist, the computer automatically segmented lesions from the parenchymal background and automatically extracted a set of characteristic features for each lesion. For each feature, its value averaged over all images pertaining to a given lesion was input to a Bayesian neural network for classification. We also investigated different approaches to combine image-based features into this by-lesion analysis. In that analysis, mean, maximum, and minimum feature values were considered for all images representing a lesion. We considered performance by using a leave-one-lesion-out approach, based on image features from mammography alone (two to five features), ultrasound alone (three to four features), and a combination of features from both modalities (three to five features total). RESULTS: For the classification task of distinguishing cancer from other abnormalities in a lesion-based analysis by using a single modality, areas under the receiver operating characteristic curves (A(z) values) increased significantly when the computer selected the manner (mean, minimum, or maximum) in which image-based features were combined into lesion-based features. The highest performance was found for lesion-based analysis and automated feature selection from mean, maximum, and minimum values of features from both modalities (resulting in a total of four features being used). That A(z) value for the task of distinguishing cancer was 0.92, showing a statistically significant increase over that achieved with features from either mammography or ultrasound alone. CONCLUSION: Computerized classification of cancer significantly improved when lesion features from both modalities were combined. Classification performance depended on specific methods for combining features from multiple images per lesion. These results are encouraging and warrant further exploration of computerized methods for multimodality imaging.     

数字化X线钼靶检查对女性乳腺疾病诊断的价值

目的：研究乳腺良、恶性病变的钼靶影像学特征,评价钼靶影像学对乳腺良、恶性病变诊断的临床价值及早期发现乳腺癌的意义。方法对2010年2月至2011年3月100例经病理证实乳腺良恶性病变病例,进行回顾性钼靶影像学分析研究。结果乳腺良性病变64例,术前钼靶检查诊断符合51例,正确率为80％;乳腺恶性病变36例,术前钼靶检查诊断符合31例,正确率为86％。结论数字化钼靶摄影对乳腺良、恶性病变鉴别诊断优越于超声检查,诊断早期乳腺癌有其独特优势。     

Experimental investigation on breast tissue classification based on statistical feature extraction of mammograms.

An important approach for describing a region is to quantify its structure content. In this paper, the use of functions for computing texture based on statistical measures is described. Six textural features for mammogram images are defined. The segmentation based on these textures would classify the breast tissue under four categories. The algorithm evaluates the region properties of the mammogram image and thereby would classify the image under four important categories based on the intensity level of histograms. Experiments have been conducted on images of mini-MIAS database (Mammogram Image Analysis Society database (UK)). The breast tissue classification thus obtained is comparatively better than the other normal methods. The validation of the work has been done by visual inspection of the segmented image by an expert radiologist. This work is a part of developing a computer aided decision (CAD) system for early detection of breast cancer. The classification results agree with the standard specified by the ACR-BIRADS (American College of Radiology-Breat Imaging And Reporting Data Systems). The accuracy of classification has been found to be 80% as per the visual inspection by an expert radiologist.     

Classification of breast ultrasound images using fractal feature

Fractal analyses have been applied successfully for the image compression, texture analysis, and texture image segmentation. The fractal dimension could be used to quantify the texture information. In this study, the differences of gray value of neighboring pixels are used to estimate the fractal dimension of an ultrasound image of breast lesion by using the fractal Brownian motion. Furthermore, a computer-aided diagnosis (CAD) system based on the fractal analysis is proposed to classify the breast lesions into two classes: benign and malignant. To improve the classification performances, the ultrasound images are preprocessed by using morphology operations and histogram equalization. Finally, the k-means classification method is used to classify benign tumors from malignant ones. The US breast image databases include only histologically confirmed cases: 110 malignant and 140 benign tumors, which were recorded. All the digital images were obtained prior to biopsy using by an ATL HDI 3000 system. The receiver operator characteristic (ROC) area index AZ is 0.9218, which represents the diagnostic performance.