Gene subset selection in microarray data using entropic filtering for cancer classification

Abstract: In this work an entropic filtering algorithm (EFA) for feature selection is described, as a workable method to generate a relevant subset of genes. This is a fast feature selection method based on finding feature subsets that jointly maximize the normalized multivariate conditional entropy with respect to the classification ability of tumours. The EFA is tested in combination with several machine learning algorithms on five public domain microarray data sets. It is found that this combination offers subsets yielding similar or much better accuracies than using the full set of genes. The solutions obtained are of comparable quality to previous results, but they are obtained in a maximum of half an hour computing time and use a very low number of genes.     

Potential of near-field microwave imaging in breast cancer detection utilizing tapered rectangular waveguide probes

Microwave imaging for medical applications has been of interest for many years. A novel near-field microwave non-invasive testing and evaluation (NIT&E) technique utilizing tapered rectangular waveguide probes is presented for breast cancer detection. Near-field microwave NIT&E techniques can be a successful candidate for the detection of breast cancer because of their potential in dealing with materials of low conductivity (i.e. lossy dielectrics like the breast tissue). The physical basis for breast tumor detection with microwave imaging is the contrast in dielectric properties of normal and malignant breast tissues. A method adopting Fourier transform matching (FTM) technique and utilizing the reflection coefficient at the aperture of a tapered rectangular waveguide sensor radiating into a breast is described resulting in microwave images that indicate the presence of a tumor. These images demonstrate the feasibility of detecting breast tumors using this approach.     

Automatic detection of breast cancers in mammograms using structured support vector machines

Breast cancer is one of the most common cancers diagnosed in women. Large margin classifiers like the support vector machine (SVM) have been reported effective in computer-assisted diagnosis systems for breast cancers. However, since the separating hyperplane determination exclusively relies on support vectors, the SVM is essentially a local classifier and its performance can be further improved. In this work, we introduce a structured SVM model to determine if each mammographic region is normal or cancerous by considering the cluster structures in the training set. The optimization problem in this new model can be solved efficiently by being formulated as one second order cone programming problem. Experimental evaluation is performed on the Digital Database for Screening Mammography (DDSM) dataset. Various types of features, including curvilinear features, texture features, Gabor features, and multi-resolution features, are extracted from the sample images. We then select the salient features using the recursive feature elimination algorithm. The structured SVM achieves better detection performance compared with a well-tested SVM classifier in terms of the area under the ROC curve.     

基于改进Marching Cubes算法的乳腺MRI肿块三维重建

核磁共振成像MRI(Magnetic Resonance Imaging)是目前乳腺癌肿块诊断的常用辅助手段,对图像的正确解析是关键,针对传统MC(Marching Cubes)面绘制算法应用于乳腺MRI图像的不足,提出了改进方法。首先利用乳腺MRI序列图相邻帧间图像灰度分布的相似,肿块组织形状相近等相关性,在RSF(Region-Scalable Fitting)模型的基础上利用初始轮廓迭代的方法提取肿块区域。接着将多组参数下获得的结果,依据每一帧与其前后帧的重叠面积越大越好作为条件进行筛选,使提取的等值面最优化。最后采用基于加权二次误差度量的三角形折叠方法,对面绘制产生的大量三角网格进行了简化。将所提出的改进方法应用于30例乳腺MRI序列图,实验结果表明,对于乳腺MRI肿块的三维重建在精度和绘制速度上都比使用传统MC算法有很大提高。     

结肠癌基因表达谱的分类检测问题研究

随着大规模基因表达谱技术的发展,基于基因表达谱的癌症诊断方法正在成为临床医学上一种快速有效的诊断方法,但是由于基因表达数据维数过高、样本量小、噪声大,使得正确提取有关癌症的特征基因成为关键。以结肠癌肿瘤的基因表达谱数据为例,提出了结合Fisher权函数、离散傅里叶变换和主成分分析的混合特征基因提取方法,以多元Logistic回归分析和贝叶斯决策作为分类器进行肿瘤分类检测。实验结果表明,该方法对于结肠癌数据集CV识别准确率高达96.80%。     

Utilizing endoscopic technology to reveal real-time proteomic alterations in response to chemoprevention

Cancer chemoprevention approaches use either pharmacological or dietary agents to impede, arrest or reverse the carcinogenic process. Although several agents have shown effectiveness against colon cancer, present intervention strategies provide only partial reduction. In this study, we utilized high-resolution endoscopy to obtain colon tumor biopsy specimens from Apc mutant mice before and after 2-wk sulindac intervention. To acquire information beyond genomics, proteome analysis using the ProteomeLab PF2D platform was implemented to generate 2-D protein expression maps from biopsies. Chromatograms produced common signature profiles between sulindac and nonsulindac treated samples, and contrasting profiles termed "fingerprints". We selected a double peak that appeared in tumor biopsies from sulindac-treated mice. Further analyses using MS sequencing identified this protein as histone H2B. The location of H2B in the 1(st) dimension strongly suggested PTM, consistent with identification of two oxidized methionines. While further studies on sulindac proteomic fingerprints are underway, this study demonstrates the feasibility and advantages of "real-time" proteomic analysis for obtaining information on biomarker discovery and drug activity that would not be revealed by a genetic assay. This approach should be broadly applicable for assessing lesion responsiveness in a wide range of translational and human clinical studies.     

一个医学数据集上的决策树分类研究

人乳头瘤病毒(HPV)是导致宫颈癌的一大要素。利用Weka这个数据挖掘平台,对中国肿瘤防治数据库山西子宫颈癌医学数据集进行C4.5决策树分类研究,从决策树中提取了一些比较有意义的规则,发现一些容易导致感染HPV病毒的因素。     

Spectroscopy Study on Crystal Structure of Ce（NO3）3 （phen）2 and Interactions of Ce（NO3）3 （phen）2 with DNA

Inrecentyears ,Komiyaetal.[1] havefoundthatrareearthsionsmaybeoneofthestrongestcutre agentsofnucleicacids .Theexperimentalresults ,thatrareearthsrepresscancersonwholeanimalbodiesandonhumanbodies(invitro) ,indicatedthatrareearthselementsactuallyhavestrongf…     

Optimistic Personality and Psychosocial Well-Being During Treatment Predict Psychosocial Well-Being Among Long-Term Survivors of Breast Cancer.

In considering well-being among survivors of life-threatening illnesses such as breast cancer, 2 important questions are whether there is continuity between initial adjustment and longer term adjustment and what role personality plays in long-term adjustment. In this research, a sample of 163 early stage breast cancer patients whose psychosocial adjustment was first assessed during the year after surgery completed the same measures 5-13 years after surgery. Initial reports of well-being were relatively strong predictors of follow-up well-being on the same measures. Initial optimism and marital status also predicted follow-up adjustment, even controlling for earlier adjustment, which exerted a substantial unique effect in multivariate analyses. In contrast, initial medical variables played virtually no predictive role. There is substantial continuity of subjective well-being across many years among survivors of breast cancer, rooted partly in personality and social connection. (PsycINFO Database Record (c) 2010 APA, all rights reserved)