基于定量影像组学的肺肿瘤良恶性预测方法

肺癌是世界范围内致死率最高的癌症之一,肺肿瘤的良恶性诊断对于治疗方式选择意义重大.本文借助影像组学（Radiomics）方法利用LIDC（Lung imaging database consortium）肺癌公开数据库中619例病人的肺癌计算机断层（Computed tomography,CT）影像数据,分割出病变区域,并结合肿瘤医学特性和临床认知,提取反映肿瘤形状大小、强度和纹理特性的60个定量影像特征,然后利用支持向量机（Support vector machine,SVM）构建诊断肺肿瘤良恶性的预测模型,筛选出对诊断肺肿瘤良恶性有价值的20个影像组学特征.为肺肿瘤良恶性预测提供了一种非入侵的检测手段.随着CT影像在肺癌临床诊断中的广泛使用,应用样本量的不断增加,本文方法有望成为一种辅助诊断工具,有效提高临床肺肿瘤良恶性诊断准确率.     

基于多特征融合和SVM分类器的植物病虫害检测方法

针对农业领域植物病虫害检测问题,提出一种基于高清视频图像融合特征的支持向量机(SVM)的检测方法,实现农业生产中植物病虫害的快速检测。对每幅植物叶片图像的颜色、HSV、纹理和方向梯度直方图四种特征采用基于特征包的多特征融合方法,形成特征向量,并利用SVM分类器进行训练分类。对单特征与融合特征的SVM分类器性能进行试验比较,所提出的方法具有较高的准确率。     

小波在基于CT图像的肝脏疾病良恶性分类中的研究

肝癌是一种常见的恶性肿瘤,近年来发病率呈缓慢上升的趋势,病死率也随之上升。文章利用小波在特征提取和模式识别方面的独特优势,提取了基于小波和灰度共生矩阵的纹理特征,结合遗传算法进行特征选择和优化,用KNN分类器设计出高精确度的肝脏疾病良恶性分类器。采用肝脏CT平扫图像,将肝癌与其他的良性病变进行分类,探讨了小波的不同性质及特征提取方式对分类结果的影响,对小波在肝脏CT图像良恶性分类中的研究有指导意义。     

利用PCA和AdaBoost建立基于贝叶斯的组合分类器

提出了一种使用基于贝叶斯的基分类器建立组合分类器的新方法PCABoost.本方法在创建训练样本时,随机地将特征集划分成K个子集,使用PCA得到每个子集的主成分,形成新的特征空间,并将全部的训练数据映射到新的特征空间作为新的训练集.通过不同的变换生成不同的特征空间,从而产生若干个有差异的训练集.在每一个新的训练集上利用AdaBoost建立一组基于贝叶斯的逐渐提升的分类器(即一个分类器组),这样就建立了若干个有差异的分类器组,然后在每个分类器组内部通过加权投票产生一个预测,再把每个组的预测通过投票来产生组合分类器的分类结果,最终建立一个具有两层组合的组合分类器.从UCI标准数据集中随机选取30个数据集进行实验.结果表明,本算法不仅能够显著提高基于贝叶斯的分类器的分类性能,而且与Rotation Forest和AdaBoost等组合方法相比,在大部分数据集上都具有更高的分类准确率.     

基于深度迁移学习的肺结节辅助诊断方法

在肺癌早期筛查过程中,人工诊断胸部CT扫描图像费时费力,而深度学习网络缺乏足够的医学数据进行训练。为此,提出一种渐进式微调(PFT)策略,将其应用于深度迁移学习网络以辅助诊断肺结节良恶性。利用神经网络在粗粒度的自然图像大数据集中学习特征知识,经重构网络分类层将所学到的特征信息迁移至肺结节的细粒度小数据集。采用PFT策略从全连接分类层开始,逐层释放、微调训练卷积层直至所有网络层,并通过定量分析各层微调后肺结节良恶性分类的AUC值,确定最佳微调深度。此外,采用梯度加权类激活映射图和t-SNE算法为网络预测结果提供相应的视觉支持与解释。在LIDC数据集中的实验结果表明,该方法对肺结节良恶性诊断的准确率可达91.44%,其AUC值为0.962 1。     

基于RF-PSO-SVM的烟叶等级分类模型

针对烤烟等级分类问题,论文利用数字图像处理技术对烤烟图像进行处理,根据烤烟等级影响因子,提取了烤烟正反两面的颜色特征、纹理特征与形状特征,并建立了一种烤烟等级分类模型——RF-PSO-SVM模型。首先利用RF-SVM对烤烟特征按其对分类模型的贡献度排序,筛选出对分类模型准确率影响较大的特征建立最优特征子集,并利用PSO对SVM的C、g参数寻优,建立RF-PSO-SVM分类模型,对筛选的特征子集进行学习训练,最后将RF-PSO-SVM分类模型与SVM分类模型、PSO-SVM分类模型进行对比,验证该方法的可靠性。经实验结果表明：1）烟叶的反面颜色特征与纹理特征对分类模型贡献度较大,形状特征对模型贡献度较小。2)RF-PSO-SVM算法建立的烟叶分类模型可以在保证分类准确率的情况下,降低分类算法的运行时间,减少了数据集的特征维度,对烟叶的分类识别具有一定的参考价值。     

基于灰度图纹理指纹的恶意软件分类

随着安卓恶意软件数量的快速增长,传统的恶意软件检测与分类机制存在检测率低、训练模型复杂度高等问题。为解决上述问题,结合图像纹理特征提取技术和机器学习分类器,提出基于灰度图纹理特征的恶意软件分类方法。该方法首先将恶意软件样本生成灰度图,设计并集成了包含GIST和Tamura特征提取算法在内的4种特征提取方法;然后将所得纹理特征集合作为源数据,基于Caffe高性能处理架构构造了5种分类学习模型,最终实现对恶意软件的检测和分类。实验结果表明,基于图像纹理特征的恶意软件分类具有较高的准确率,且Caffe架构能有效缩短学习时间,降低复杂度。     

运用超声造影特征选择的淋巴结良恶性鉴别

提取淋巴结超声造影(CEUS)图像的影像组学量化特征可用于淋巴结良恶性的计算机辅助诊断。由于大量特征之间存在冗余和干扰信息,需借助特征选择技术进行特征降维,以获得更具鉴别能力的特征子集。利用实时压缩感知算法进行CEUS视频中淋巴结病灶的运动补偿,提取时域与空域特征。运用最小绝对压缩(LASSO)法、支持向量机回归特征法(SVM-RFE)、Fisher准则法三种特征选择方法,对特征进行降维。运用支持向量机进行交叉验证,得到分类结果。相对原始特征,三种特征选择方法得到的特征子集的分类性能均有提升。其中,运用LASSO进行降维的效果最好,分类的准确率、精度、敏感性、特异性和约登指数分别达到98.5%、100%、97.1%、100%和97.1%,相较全体特征的分类结果分别提升11.4%、14.8%、15.0%、14.3%和29.2%。结果表明,对影像组学量化特征的降维能够筛选出更具鉴别能力的特征子集,从而提升计算机辅助诊断的性能。     

基于稀疏表示和决策融合的图像分类方法

利用多个稀疏表示分类器融合的决策信息对图像进行分类,可避免单个特征对图像分类的影响。提出一种自适应调节权重的多稀疏分类器融合图像分类方法。对原始图像分别提取3组不同特征,并训练出各自稀疏表示分类器;根据各个子分类器的准确率,通过迭代计算自适应确定各分类器最终权重;融合各子分类器的输出结果进行最终类别判断。基于Cifar-10图像数据集进行多组实验,结果表明,相对仅提取单特征的图像分类方法,该方法有效提高了图像分类准确率。     

超声乳腺肿瘤的全自动SVM检测与水平集分割算法

超声图像检测是当前乳腺癌诊断的主要辅助手段之一.为实现超声乳腺肿瘤的计算机自动辅助诊断,提出一种基于支持向量机(SVM)目标检测与水平集图像分割相结合的全自动肿瘤提取算法.首先提取超声图像训练集的分块特征来训练SVM分类器,对测试集图像进行检测得到可疑病灶区域;然后提取可疑区域边缘作为水平集的初始轮廓,使用加入Bhattacharyya距离项的Chan-Vese主动轮廓改进模型进行可疑病灶区域的轮廓演化,得到准确的轮廓;最后综合面积、位置、灰度、纹理等因素设计区域评价筛选准则,去除可疑病灶中的干扰区域,得到最终的肿瘤分割结果.在真实病例数据集上的测试结果表明,利用该算法在良恶性肿瘤检测分割中均有较好表现.     

Feature selection using mutual information in CT colonography

Computed tomographic (CT) colonography is a promising alternative to traditional invasive colonoscopic methods used in the detection and removal of cancerous growths, or polyps in the colon. Existing computer-aided diagnosis (CAD) algorithms used in CT colonography typically employ the use of a classifier to discriminate between true and false positives generated by a polyp candidate detection system based on a set of features extracted from the candidates. However, these classifiers often suffer from a phenomenon termed the curse of dimensionality, whereby there is a marked degradation in the performance of a classifier as the number of features used in the classifier is increased. In addition, an increase in the number of features used also contributes to an increase in computational complexity and demands on storage space.This paper investigates the benefits of feature selection on a polyp candidate database, with the aim of increasing specificity while preserving sensitivity. Two new mutual information methods for feature selection are proposed in order to select a subset of features for optimum performance. Initial results show that the performance of the widely used support vector machine (SVM) classifier is indeed better with the use of a small set of features, with receiver operating characteristic curve (AUC) measures reaching 0.78-0.88.     

基于改进ReliefF与k-means算法的良恶性肺结节分类模型

肺结节是肺癌的症状.在CT图像中,肺结节的形状和大小常被用来进行肺癌的诊断,然而良性和恶性结节的鉴别对于疾病的治疗具有重要意义.由于良恶性结节的边缘纹理特征区别大,因此本文首先利用基于改进的边缘检测算子的灰度-梯度共生矩阵(GGCM)提取小梯度优势、灰度分布不均匀性、能量、灰度熵、梯度熵、混合熵、逆差距、相关性等肺部CT图像的14种纹理特征.然后利用改进的ReliefF算法去除作用小的特征,保留重要特征的特征权重值.最后将重要特征的权重值应用于改进距离度量准则的k-means算法中进行良恶性结节的分类.应用本文算法在LIDC数据集上实验,实验分析结果表明,14种纹理特征对于结节良恶性的分类能力并不相同,而灰度差、梯度差、能量、小梯度优势、相关性、灰度熵、混合熵、逆差矩的组合得到的良恶性肺结节分类效果最好,最终实现了良性结节83.46%,恶性结节95.02%的识别率,可在临床应用中辅助医生进行肺结节的良恶性诊断.     

Comparison of multiwavelet, wavelet, Haralick, and shape features for microcalcification classification in mammograms

We present an evaluation and comparison of the performance of four different texture and shape feature extraction methods for classification of benign and malignant microcalcifications in mammograms. For 103 regions containing microcalcification clusters, texture and shape features were extracted using four approaches: conventional shape quantifiers; co-occurrence-based method of Haralick; wavelet transformations; and multi-wavelet transformations. For each set of features, most discriminating features and their optimal weights were found using real-valued and binary genetic algorithms (GA) utilizing a k-nearest-neighbor classifier and a malignancy criterion for generating ROC curves for measuring the performance. The best set of features generated areas under the ROC curve ranging from 0.84 to 0.89 when using real-valued GA and from 0.83 to 0.88 when using binary GA. The multi-wavelet method outperformed the other three methods, and the conventional shape features were superior to the wavelet and Haralick features.     

基于影像组学和机器学习的脑部胶质瘤分级模型研究

本文将影像组学的方法和机器学习算法结合起来,对脑部胶质瘤进行分级预测。利用BraTS2019公开数据集,从多模态MRI图像中分别提取肿瘤的448维影像组学特征:肿瘤形态学特征、一阶灰度特征、纹理特征等;然后通过最小绝对收缩和选择算子(Lasso)算法筛选出15个最佳的影像组学特征;最后根据筛选出的最佳特征集,利用随机森林分类算法构建脑部胶质瘤的分级预测模型。基于机器学习建立的模型在训练组患者中预测胶质瘤级别的准确率达到95.6%,ROC曲线下面积(AUC)达到0.99;在验证组患者中预测胶质瘤级别的准确率达到89.3%,AUC达到0.96。可见,基于机器学习算法,利用影像组学的方法可以对脑部肿瘤的高低级别进行准确的预测和分类。     

Color image segmentation using automatic pixel classification with support vector machine

Automatic segmentation of images is a very challenging fundamental task in computer vision and one of the most crucial steps toward image understanding. In this paper, we present a color image segmentation using automatic pixel classification with support vector machine (SVM). First, the pixel-level color feature is extracted in consideration of human visual sensitivity for color pattern variations, and the image pixel's texture feature is represented via steerable filter. Both the pixel-level color feature and texture feature are used as input of SVM model (classifier). Then, the SVM model (classifier) is trained by using fuzzy c-means clustering (FCM) with the extracted pixel-level features. Finally, the color image is segmented with the trained SVM model (classifier). This image segmentation not only can fully take advantage of the local information of color image, but also the ability of SVM classifier. Experimental evidence shows that the proposed method has a very effective segmentation results and computational behavior, and decreases the time and increases the quality of color image segmentation in compare with the state-of-the-art segmentation methods recently proposed in the literature.     

Diagnosis of breast tumors with ultrasonic texture analysis using support vector machines

This study presents a computer-aided diagnosis (CAD) system with textural features for classifying benign and malignant breast tumors on medical ultrasound systems. A series of pathologically proven breast tumors were evaluated using the support vector machine (SVM) in the differential diagnosis of breast tumors. The proposed CAD system utilized facile textural features, i.e., block difference of inverse probabilities, block variation of local correlation coefficients and auto-covariance matrix, to identify breast tumor. An SVM classifier using the textual features classified the tumor as benign or malignant. The proposed system identifies breast tumors with a comparatively high accuracy. This can help inexperienced physicians avoid misdiagnosis. The main advantage of the proposed system is that the training and diagnosis procedure of SVM are faster and more stable than that of multilayer perception neural networks. With the expansion of the database, new cases can easily be gathered and used as references. This study dramatically reduces the training and diagnosis time. The SVM is a reliable choice for the proposed CAD system because it is fast and excellent in ultrasound image classification.     

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.     

Automatic classification for solitary pulmonary nodule in CT image by fractal analysis based on fractional Brownian motion model

Perfusion computed tomography (CT) method has been used to differentiate malignant pulmonary nodules from benign nodules based on the assessment for the change of the CT attenuation value within the pulmonary nodules. Instead of using the change of the CT attenuation value, a set of fractal features based on fractional Brownian motion model is proposed in this paper to automatically distinguish malignant nodules from benign nodules. In a set of 107 CT images from 107 different patients with each image containing a solitary pulmonary nodule, our experimental results obtained from a support vector machine classifier show that the accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and the area under the ROC curve are 83.11%, 90.92%, 71.70%, 80.05%, 87.52%, and 0.8437, respectively, by using the proposed fractal-based feature set. Such a result outperforms the conventional method of using the change of the CT attenuation value as the feature for classification. When combining this conventional method with our proposed fractal-based method, the accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and the area under the ROC curve can be promoted to 88.82%, 93.92%, 82.90%, 87.30%, 90.20%, and 0.9019, respectively. In other words, a high performance of pulmonary nodule classification can be achieved with a single post-contrast CT scan.