|
【medical-news】WJG:一项新的超声内镜影像处理... 已解决
悬赏分:0
- 解决时间 2024-11-24 15:23
【medical-news】WJG:一项新的超声内镜影像处理方法有效评估同位素间质内放射治疗胰腺癌的预后
|
|
举报
2013-11-27 07:53
文献题目:A new endoscopic ultrasonography imageprocessing method to evaluate the prognosis for pancreatic cancer treated withinterstitial brachytherapy
发表期刊:World Journal of Gastroenterology PMID: 24151368 文献首页截图: A new endoscopic ultrasonography image processing.pdf(1212.16k) |
|
举报
2013-11-22 07:22
AIM: To develop a fuzzy classification method to score the texturefeatures of pancreatic cancer in endoscopic ultrasonography (EUS)images andevaluate its utility in making prognosis judgments forpatients with unresectable pancreatic cancer treated byEUS-guided interstitial brachytherapy. 目的:开发一种模糊分类方法对超声内镜下胰腺癌实质特征的影响进行评分。同时对这种处理方法能否用于无法切除而需超声内镜引导下同位素间质内放射治疗的胰腺癌患者预后评估及其评估效率进行评价。 METHODS: EUS images from our retrospective database were analyzed. The regions ofinterest were drawn, and texture features were extracted, selected, and scoredwith a fuzzy classification method using a C++ program. Then,patients with unresectable pancreatic cancer were enrolled toreceive EUS-guided iodine 125 radioactive seed implantation. Their fuzzyclassification scores, tumor volumes, and carbohydrate antigen 199 (CA199)levels before and after the brachytherapy were recorded. Theassociation between the changes in these parameters and overall survival wasanalyzed statistically. 方法:分析我院回顾性数据库中超声影像数据,描绘出感兴趣的区域,利用C++程序使用一项模糊分类的方法对实质特征进行提取、筛选及评分。将无法进行切除而接受超声内镜引导放射性碘125种植治疗的胰腺癌患者进行登记,在放射治疗前后分别记录这些患者的模糊分类评分、肿瘤体积、CA199的水平。这些参数变化之间的相关性以及完全生存率进行统计学分析。 RESULTS: EUS images of 153 patients with pancreatic cancer and 63non-cancer patients were analyzed. A total of 25 consecutive patients wereenrolled, and they tolerated the brachytherapy well without anycomplications. There was a correlation between the change in the fuzzyclassification score and overall survival (Spearman test, r = 0.616, P =0.001), whereas no correlation was found to be significant between the changein tumor volume (P = 0.663), CA199 level (P = 0.659), and overall survival.There were 15 patients with a decrease in their fuzzy classification scoreafterbrachytherapy, whereas the fuzzy classification score increased in another10 patients. There was a significant difference in overall survival between thetwo groups (67 d vs 151 d, P = 0.001), but not in the change of tumor volumeand CA199 level. 结果:共对153名胰腺癌患者及63名无癌症患者的超声内镜影像进行了分析。共纳入了25名患者。这25名患者对放射治疗耐受性良好,无任何并发症。在模糊分类评分与完全生存率之间存在相关性(Spearman检验方法,r=0.616,P=0.001)。同时在肿瘤体积、CA199水平与生存期之间无具有统计学意义的相关性,P值分别为0.663和0.659。在25名患者中,有15名患者在进行放射治疗后模糊分类评分较治疗前下降,而另外10名患者该项评分在放射治疗后水平上升。上述两组人群中完全生存时间有显著差异,分别为67天及151天,P=0.001),但在肿瘤体积、CA199水平之间无明显差异。 CONCLUSION: Using the fuzzy classification method to analyze EUS images of pancreatic cancer isfeasible, and the method can be used to makeprognosis judgmentsfor patients with unresectable pancreatic cancer treated by interstitial brachytherapy. 结论:对胰腺癌患者利用模糊分类评分方法对超声内镜影像进行分析十分简单易行,而且可以对不能进行手术切除而接受同位素间质内放射治疗的胰腺癌患者的预后进行良好的评估。 INTRODUCTION:The application of digital imageprocessing (DIP) in endoscopic ultrasonography (EUS) images and other imagingscenarios has been proven to be a useful adjunct to endoscopic diagnoses andoften comparable with specialists’ interpretation in different pathologicsettings. The texture parameters of EUS images are extracted and classifiedfrom the returned echoes to identify the tissue type present in the images. Oneeffective approach is to use DIP based on a support vector machine (SVM), whichis a computer algorithm that learns by example to assign labels to objects. TheSVM technique, as a subfield of digital signal processing, has been applied toa series of pathologically proven diseases. The typical method of SVM, which is onlyable to provide a differential diagnosis for solid tumors (“yes” or “no”),cannot provide numerical data describing the texture parameters in the EUSimage. In this study, a new DIP method based on fuzzy classification is appliedto obtain the feature value of texture parameters in EUS images of pancreaticcancer and observe the change of texture parameters to evaluate its utility inmaking prognosis judgments for patients with unresectable pancreatic cancerafter EUS-guided interstitial brachytherapy. 研究背景:数字图像处理在超声内镜及其他成像情景中的应用被证实是对内镜诊断的一个有效辅助,并在不同的病理设置中常与专家的诊断解释进行比较。根据返回的回声进行提取和分析的超声内镜影像可以形成实质组织影像的各种参数,这些影像参数可以对实质组织的组织类型进行鉴定。其中一项有效的影响识别方法是利用一种基于辅助向量机械的数字图像处理方法,这是一种通过实例对目标图像进行标记并从中获得信息的计算机的计算方法。辅助向量机械技术,作为数字信息处理的一个子区域,目前被应用于一系列疾病的病理判断。 辅助向量机械技术的一个典型应用方法,是对实体肿瘤的鉴别诊断添加标签(即完成是或不是的判断),但不能对超声内镜提供的影像提供大量能够描述实质参数的数字化数据。在本项研究中,采用了一种新的基于模糊分类的数字图像处理方法以获得超声内镜所提供的胰腺癌患者的影像中实质的特征性数据。并评估该方法获得的差异实质参数用于无法切除而接受超声内镜引导下间质放射性治疗的患者的预后评估的效能。 |
|
举报
2013-11-21 09:37
编译:(字数统计:1266) 研究要点: 数字图像处理在超声内镜及其他成像情景中的应用被证实是对内镜诊断的一个有效辅助。但目前应用无法对器官实质改变的影像提供更多的描述性参数数据。作者采用新的基于模糊分类的数字图像处理方法以获得超声内镜所提供的胰腺癌患者的影像中实质的特征性数据。并评估该方法获得的差异实质参数用于无法切除而接受超声内镜引导下间质放射性治疗的患者的预后评估的效能。结果发现对胰腺癌患者利用模糊分类评分方法对超声内镜影像进行分析十分简单易行,而且可以对不能进行手术切除而接受同位素间质内放射治疗的胰腺癌患者的预后进行良好的评估。 摘要编译: 我国第二军医大学消化内科Wu Wei等人开发了一种模糊分类方法对超声内镜下胰腺癌实质特征的影响进行评分。同时对这种处理方法能否用于无法切除而需超声内镜引导下同位素间质内放射治疗的胰腺癌患者预后评估及其评估效率进行评价。 分析该院回顾性数据库中超声影像数据,描绘出感兴趣的区域,利用C++程序使用一项模糊分类的方法对实质特征进行提取、筛选及评分。将无法进行切除而接受超声内镜引导放射性碘125种植治疗的胰腺癌患者进行登记,在放射治疗前后分别记录这些患者的模糊分类评分、肿瘤体积、CA199的水平。这些参数变化之间的相关性以及完全生存率进行统计学分析。 该项研究共对153名胰腺癌患者及63名无癌症患者的超声内镜影像进行了分析。共纳入了25名患者。这25名患者对放射治疗耐受性良好,无任何并发症。在模糊分类评分与完全生存率之间存在相关性(Spearman检验方法,r=0.616,P=0.001)。同时在肿瘤体积、CA199水平与生存期之间无具有统计学意义的相关性,P值分别为0.663和0.659。在25名患者中,有15名患者在进行放射治疗后模糊分类评分较治疗前下降,而另外10名患者该项评分在放射治疗后水平上升。上述两组人群中完全生存时间有显著差异,分别为67天及151天,P=0.001),但在肿瘤体积、CA199水平之间无明显差异。 上述结果表明,对胰腺癌患者利用模糊分类评分方法对超声内镜影像进行分析十分简单易行,而且可以对不能进行手术切除而接受同位素间质内放射治疗的胰腺癌患者的预后进行良好的评估。 研究背景: 数字图像处理在超声内镜及其他成像情景中的应用被证实是对内镜诊断的一个有效辅助,并在不同的病理设置中常与专家的诊断解释进行比较。根据返回的回声进行提取和分析的超声内镜影像可以形成实质组织影像的各种参数,这些影像参数可以对实质组织的组织类型进行鉴定。其中一项有效的影响识别方法是利用一种基于辅助向量机械的数字图像处理方法,这是一种通过实例对目标图像进行标记并从中获得信息的计算机的计算方法。辅助向量机械技术,作为数字信息处理的一个子区域,目前被应用于一系列疾病的病理判断。 辅助向量机械技术的一个典型应用方法,是对实体肿瘤的鉴别诊断添加标签(即完成是或不是的判断),但不能对超声内镜提供的影像提供大量能够描述实质参数的数字化数据。在本项研究中,采用了一种新的基于模糊分类的数字图像处理方法以获得超声内镜所提供的胰腺癌患者的影像中实质的特征性数据。并评估该方法获得的差异实质参数用于无法切除而接受超声内镜引导下间质放射性治疗的患者的预后评估的效能。 |
|
举报
2013-11-19 11:02
先投@tiancai_erbao 一票.
接下来做点补充. 1。texture features 译成纹理特征更准确。 2。The application of digital imageprocessing (DIP) in endoscopic ultrasonography (EUS) images and other imagingscenarios has been proven to be a useful adjunct to endoscopic diagnoses andoften comparable with specialists’ interpretation in different pathologicsettings. 数字图像处理在超声内镜及其他成像情景中的应用被证实是对内镜诊断的一个有效辅助,并在不同的病理设置中常与专家的诊断解释进行比较。 后半句我的理解是DIP用于EUS成像使得不同病理实验室的专家获得大致相同的读图结论(前提是软件算法相同) 3。译文的“研究背景”清楚地交代了本研究的新贡献是用模糊分类法取代SVM。 为便于理解,我找到来2009年一篇论文的摘要 http://d.wanfangdata.com.cn/Periodical_zhxhnjzz98200904004.aspx 目的 观察利用数字图像处理技术提取超声内镜图像纹理特征,并运用于胰腺癌诊断的价值.方法 随机选择2005年2月-2007年2月间行胰腺EUS榆查的216名患者.其中胰腺癌153例,非胰腺癌患者(包括正常胰腺与慢性胰腺炎)63例,所有胰腺癌病例均经EUS-FNA细胞学检查确诊.选样EUS图像并提取纹理特征.根据最优特征组合,通过支撑向量机将病例进行自动分类为胰腺癌和非胰腺癌病例,并计算该诊断方法的敏感性、特异性和准确率.结果 根据EUS图像共提取9大类,69个特征用于模式分类特征,其中类间距最大的25个特征被选取作为初始特征.将现有216例病例,随机划分为训练集和测试集,训练集108例(癌症76例,非癌症32例)、测试集108例(癌症77例,非癌症31例),用训练集训练分类器,测试集进行测试.共进行50次随机实验,最终得出胰腺癌分类的准确性为(97.98±1.237)%,敏感性为(94.32±0.0354)%,特异性为(99.45±0.0102)%.结论 数字图像处理技术与计算机辅助EUS图像判别法准确率高,无创伤性,为胰腺癌的临床诊断提供了一个新的、有价值的研究片向. Abstract: Objective To process the image of endoscopic uhrasonography(EUS)by digital imaging processing(DIP)and pattem recognition,and to evaluate its efficacy in diagnosis of pancreatic adenocarcinoma.Methods Two hundreds and sixteen patients,who underwent EUS between Feb 2005 and Feb 2007,were randomly recruited to the study.The cohort jncluded 153 cases of pancreatic cancer,which were confirmed by cytological findings after fine-needle aspiration,and 63 cases of non-pancreatic cancer(normal pancreas and chronic panereatitis).The texture features of the EUS image were selected and extracted,and cases were automatically divided into cancer and non-cancer based on findings of support vector machine (SVM).Sensitivity,specificity and accuracy of the technique were calculated.Results From each region of interest(ROI),a total of69 texture features vest in 9 sets were extracted,and 25 features with most set interval were taken as initial.The images of 216 cases were divided randomly into training set(108 eases,76 cancer and 32 non cancer)and testing set(108 cases,77 cancer and 31 non cancer).After 50 times of random tests,the average accuracy,sensitivity and specificity of the diagnosis of pancreatic cancer were (97.98±1.237)%,(94.32±0.0354)%,and(99.45±0.0102)%respectively.Conclusion DIP,combined with computer aided EUS imaging,is an accurate and noninvasive technique in diagnosis of pancreatic cancer.which warrants novel and further researches. 百度上找到的SVM解释是: 支持向量机SVM(Support Vector Machine)作为一种可训练的机器学习方法,依靠小样本学习后的模型参数进行导航星提取,可以得到分布均匀且恒星数量大为减少的导航星表 SVM的主要思想可以概括为两点: 1) 它是针对线性可分情况进行分析,对于线性不可分的情况,通过使用非线性映射算法将低维输入空间线性不可分的样本转化为高维特征空间使其线性可分,从而 使得高维特征空间采用线性算法对样本的非线性特征进行线性分析成为可能; 2) 它基于结构风险最小化理论之上在特征空间中建构最优分割超平面,使得学习器得到全 svm 系列产品局最优化,并且在整个样本空间的期望风险以某个概率满足一定上界。 在学习这种方法时,首先要弄清楚这种方法考虑问题的特点,这就要从线性可分的最简单情况讨论起,在没有弄懂其原理之前,不要急于学习线性不可分等较复杂的情况,支持向量机在设计时,需要用到条件极值问题的求解,因此需用拉格朗日乘子理论,但对多数人来说,以前学到的或常用的是约束条件为等式表示的方式,但在此要用到以不等式作为必须满足的条件,此时只要了解拉格朗日理论的有关结论就行。 维基百科词条我觉得更清楚一些 In machine learning, support vector machines (SVMs, also support vector networks[1]) are supervised learning models with associated learning algorithms that analyze data and recognize patterns, used for classification and regression analysis. The basic SVM takes a set of input data and predicts, for each given input, which of two possible classes forms the output, making it a non-probabilistic binary linear classifier. Given a set of training examples, each marked as belonging to one of two categories, an SVM training algorithm builds a model that assigns new examples into one category or the other. An SVM model is a representation of the examples as points in space, mapped so that the examples of the separate categories are divided by a clear gap that is as wide as possible. New examples are then mapped into that same space and predicted to belong to a category based on which side of the gap they fall on. In addition to performing linear classification, SVMs can efficiently perform a non-linear classification using what is called the kernel trick, implicitly mapping their inputs into high-dimensional feature spaces. |