Deep feature extraction and classification of breast ultrasound images

Controlled despeckling (structure/edges/feature preservation with smoothing the homogeneous areas) is a desired pre-processing step for the design of computer-aided diagnostic (CAD) systems using ultrasound images as the presence of speckle noise masks diagnostically important information making interpretation difficult even for experienced radiologist. For efficiently classifying the breast tumors, the conventional CAD system designs use hand-crafted features. However, these features are not robust to the variations in size, shape and orientation of the tumors resulting in lower sensitivity. Thus deep feature extraction and classification of breast ultrasound images have recently gained attention from research community. The deep networks come with an advantage of directly learning the representative features from the images. However, these networks are difficult to train from scratch if the representative training data is small in size. Therefore transfer learning approach for deep feature extraction and classification of medical images has been widely used. In the present work the performance of four pre-trained convolutional neural networks VGG-19, SqueezeNet, ResNet-18 and GoogLeNet has been evaluated for differentiating between benign and malignant tumor types. From the results of the experiments, it is noted that CAD system design using GoogLeNet architecture for deep feature extraction followed by correlation based feature selection and fuzzy feature selection using ANFC-LH yields highest accuracy of 98.0% with individual class accuracy value of 100% and 96% for benign and malignant classes respectively. For differentiating between the breast tumors, the proposed CAD system design can be utilized in routine clinical environment.

     

Fuzzy cluster based neural network classifier for classifying breast tumors in ultrasound images

The performance of supervised classification algorithms is highly dependent on the quality of training data. Ambiguous training patterns may misguide the classifier leading to poor classification performance. Further, the manual exploration of class labels is an expensive and time consuming process. An automatic method is needed to identify noisy samples in the training data to improve the decision making process. This article presents a new classification technique by combining an unsupervised learning technique (i.e. fuzzy c-means clustering (FCM)) and supervised learning technique (i.e. back-propagation artificial neural network (BPANN)) to categorize benign and malignant tumors in breast ultrasound images. Unsupervised learning is employed to identify ambiguous examples in the training data. Experiments were conducted on 178 B-mode breast ultrasound images containing 88 benign and 90 malignant cases on MATLAB® software platform. A total of 457 features were extracted from ultrasound images followed by feature selection to determine the most significant features. Accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUC) and Mathew's correlation coefficient (MCC) were used to access the performance of different classifiers. The result shows that the proposed approach achieves classification accuracy of 95.862% when all the 457 features were used for classification. However, the accuracy is reduced to 94.138% when only 19 most relevant features selected by multi-criterion feature selection approach were used for classification. The results were discussed in light of some recently reported studies. The empirical results suggest that eliminating doubtful training examples can improve the decision making performance of expert systems. The proposed approach show promising results and need further evaluation in other applications of expert and intelligent systems.     

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.     

一种改进的SVM算法在乳腺癌诊断方面的应用

针对计算机辅助诊断(CAD)技术在乳腺癌疾病诊断准确率的优化问题,提出了一种基于随机森林模型下Gini指标特征加权的支持向量机方法(RFG-SVM)。该方法利用了随机森林模型下的Gini指数衡量各个特征对分类结果的重要性,构造具有加权特征向量核函数的支持向量机,并在乳腺癌疾病诊断方面加以应用。经理论分析和实验数据验证,相比于传统的支持向量机(SVM),该方法提升了分类预测的性能,其结果与最新的方法相比也具有一定的竞争力,而且在医疗诊断应用方面更具优势。     

融合特征选取和学习策略的支持向量机研究

支持向量机是重要的机器学习方法之一,已成功解决了许多实际的分类问题。围绕如何提高支持向量机的分类精度与训练效率,以分类过程为主线,主要综述了在训练支持向量机之前不同的特征选取方法与学习策略。在此基础上,比较了不同的特征选取方法SFS,IWSS,IWSSr以及BARS的分类精度,分析了主动学习策略与支持向量机融合后获得的分类器在测试集上的分类精度与正确率/召回率平衡点两个性能指标。实验结果表明,包装方法与过滤方法相结合的特征选取方法能有效提高支持向量机的分类精度和减少训练样本量;在标签数据较少的情况下,主动学习能达到更好的分类精度,而为了达到相同的分类精度,被动学习需要的样本数量必须要达到主动学习的6倍。     

Ultrasonographic feature selection and pattern classification for cervical lymph nodes using support vector machines

A rough margin based support vector machine (RMSVM) classifier was proposed to improve the accuracy of ultrasound diagnoses for cervical lymph nodes. Thirty-six features belonging to 10 kinds of ultrasonographic characteristics were extracted for each of 110 lymph nodes in ultrasonograms. Comparison studies were done for three classifiers--the classical support vector machine (SVM), the general regression neural network and the proposed RMSVM, with or without the feature selection by the recursive feature elimination (RFE) algorithm, respectively, based on SVMs and the mean square error discriminant. It was indicated by experimental results that all classifiers benefited from the feature selection. The best classification performance was obtained by the RMSVM using thirteen features selected by the RMSVM based RFE, which yielded the normalized area under the receiver operating characteristic curve (A(z)) of 0.859. Compared with the radiologist's performance of A(z) of 0.787, the developed computer-aided diagnosis algorithm has the potential to improve the diagnostic accuracy.     

基于卷积神经网络及改进支持向量机的行人检测

针对自动驾驶实际道路场景复杂导致行人误检率高的问题,提出一种基于卷积神经网络及改进支持向量机的行人检测方法。利用聚合通道特征快速获取图像候选区域,将归一化后的候选区域图像输入卷积神经网络对其进行深度特征提取;利用主成分分析法将卷积神经网络末端所得到的特征向量进行降维处理,减少其冗余特征信息以获得精确的行人特征描述;将行人特征送至优化后的支持向量机完成分类。考虑支持向量机在分类过程中存在核函数参数选择困难的问题,利用改进后的蚁群算法对其进行优化选择,获得最优支持向量机参数以提高分类精度。实验结果表明,不同场景下的行人平均检测精确度达到92%,误检率大幅下降且具有较好的实时性。     

自监督对比特征学习的多模态乳腺超声诊断

超声图像的乳腺癌自动诊断具有重要的临床价值。然而,由于缺乏大量人工标注数据,构建高精度的自动诊断方法极具挑战。近年来,自监督对比学习在利用无标签自然图像产生具有辨别性和高度泛化性的特征方面展现出巨大潜力。然而,采用自然图像构建正负样本的方法在乳腺超声领域并不适用。为此,本文引入超声弹性图像(elastography ultrasound, EUS),利用超声图像的多模态特性,提出一种融合多模态信息的自监督对比学习方法。该方法采用同一病人的多模态超声图像构造正样本;采用不同病人的多模态超声图像构建负样本;基于模态一致性、旋转不变性和样本分离性来构建对比学习的目标学习准则。通过在嵌入空间中学习两种模态的统一特征表示,从而将EUS信息融入模型,提高了模型在下游B型超声分类任务中的表现。实验结果表明本文提出的方法能够在无标签的情况下充分挖掘多模态乳腺超声图像中的高阶语义特征,有效提高乳腺癌的诊断正确率。     

A new breast tumor ultrasonography CAD system based on decision tree and BI-RADS features

In this paper, we present a novel computer-aided diagnostic (CAD) system based on the Breast Imaging Reporting and Data System (BI-RADS) terminology scores of screening ultrasonography (US). The decision tree algorithm is adopted to analyze the BI-RADS information to differentiate between the malignant and benign breast tumors. Although many ultrasonography CAD systems have been developed for decades, there are still some problems in clinical practice. Previous CAD systems are opaque for clinicians and cannot process the ultrasound image from different ultrasound machines. This study proposes a novel CAD system utilizing BI-RADS scoring standard and Classification and Regression Tree (CART) algorithm to overcome the two problems. The original dataset consists of 1300 ultrasound breast images. Three well-experienced clinicians evaluated all of the images according to the BI-RADS feature scoring standard. Subsequently, each image could be transformed into a 25?×?1 vector. The CART algorithm was finally used to classify these vectors. In the experiments, we used the oversampling method to balance the number of malignant samples and benign samples. The 5-fold cross validation was employed to evaluate the performance of the system. The accuracy reached 94.58%, the specificity was 98.84%, the sensitivity was 90.80%, the positive predictive value (PPV) was 98.91% and the negative predictive value (NVP) was 90.56%. The experiment results show that the proposed system can obtain a sufficient performance in the breast diagnosis and can effectively recognize the benign breast tumors in BI-RADS 3.     

Support vector machines combined with feature selection for breast cancer diagnosis

Breast cancer is the second largest cause of cancer deaths among women. At the same time, it is also among the most curable cancer types if it can be diagnosed early. Research efforts have reported with increasing confirmation that the support vector machines (SVM) have greater accurate diagnosis ability. In this paper, breast cancer diagnosis based on a SVM-based method combined with feature selection has been proposed. Experiments have been conducted on different training-test partitions of the Wisconsin breast cancer dataset (WBCD), which is commonly used among researchers who use machine learning methods for breast cancer diagnosis. The performance of the method is evaluated using classification accuracy, sensitivity, specificity, positive and negative predictive values, receiver operating characteristic (ROC) curves and confusion matrix. The results show that the highest classification accuracy (99.51%) is obtained for the SVM model that contains five features, and this is very promising compared to the previously reported results.     

Kernel Function in SVM-RFE based Hyperspectral Data band Selection

Supporting vector machine recursive feature elimination (SVM-RFE) has a low efficiency when it is applied to band selection for hyperspectral dada,since it usually uses a non-linear kernel and trains SVM every time after deleting a band.Recent research shows that SVM with non-linear kernel doesn’t always perform better than linear one for SVM classification.Similarly,there is some uncertainty on which kernel is better in SVM-RFE based band selection.This paper compares the classification results in SVM-RFE using two SVMs,then designs two optimization strategies for accelerating the band selection process:the percentage accelerated method and the fixed accelerated method.Through an experiment on AVIRIS hyperspectral data,this paper found:① Classification precision of SVM will slightly decrease with the increasing of redundant bands,which means SVM classification needs feature selection in terms of classification accuracy;② The best band collection selected by SVM-RFE with linear SVM that has higher classification accuracy and less effective bands than that with non-linear SVM;③ Both two optimization strategies improved the efficiency of the feature selection,and percentage eliminating performed better than fixed eliminating method in terms of computational efficiency and classification accuracy.     

融合渐近性的灰狼优化支持向量机模型

大数据的发展对数据分类领域的分类准确性有了更高的要求;支持向量机(Support Vector Machine,SVM)的广泛应用需要一种高效的方法来构造一个分类能力强的SVM分类器;SVM的核函数参数与惩罚因子以及特征子集对预测模型的复杂度和预测精度有着重要影响。为提高SVM的分类性能,文中将SVM的渐近性融合到灰狼优化(Grey Wolf Optimization,GWO)算法中,提出了新的SVM分类器模型,该模型对SVM的参数与数据的特征子集同时进行优化,融合SVM渐近性的新灰狼个体将灰狼优化算法的搜索空间导向超参数空间中的最佳区域,能够更快地获得最优解;此外,将获得的分类准确率、所选特征个数和支持向量个数相结合,提出了一种新的适应度函数,新的适应度函数与融合渐近性的灰狼优化算法将搜索引向最优解。采用UCI中的多个经典数据集对所提模型进行验证,将其与网格搜素算法、未融合渐近性的灰狼优化算法以及其他文献中的方法进行对比,其分类准确率在不同数据集上均有不同程度的提升。实验结果表明,所提算法能找到SVM的最优参数与最小特征子集,具有更高的分类准确率和更短的平均处理时间。     

基于GA的遥感图像目标SVM自动识别

为了高效合理地确定支持矢量机(SVM)的参数,使其对复杂的二值遥感图像目标进行自动识别,采用实值编码遗传算法来实现SVM模型参数的自动选择.与穷举搜索的留一法及随机试凑法相比,采用遗传算法的SVM模型参数选择更简单、更易于实现,并使SVM具有更好的推广能力.二值遥感图像目标的分类识别结果表明,该方法不但可以提高分类识别率,而且显著地缩短了SVM的训练时间.     

面向乳腺超声计算机辅助诊断的两阶段深度迁移学习

目的 为了提升基于单模态B型超声（B超）的乳腺癌计算机辅助诊断（computer-aided diagnosis,CAD）模型性能,提出一种基于两阶段深度迁移学习（two-stage deep transfer learning,TSDTL）的乳腺超声CAD算法,将超声弹性图像中的有效信息迁移至基于B超的乳腺癌CAD模型之中,进一步提升该CAD模型的性能。方法 在第1阶段的深度迁移学习中,提出将双模态超声图像重建任务作为一种自监督学习任务,训练一个关联多模态深度卷积神经网络模型,实现B超图像和超声弹性图像之间的信息交互迁移;在第2阶段的深度迁移学习中,基于隐式的特权信息学习（learning using privilaged information,LUPI）范式,进行基于双模态超声图像的乳腺肿瘤分类任务,通过标签信息引导下的分类进一步加强两个模态之间的特征融合与信息交互;采用单模态B超数据对所对应通道的分类网络进行微调,实现最终的乳腺癌B超图像分类模型。结果 实验在一个乳腺肿瘤双模超声数据集上进行算法性能验证。实验结果表明,通过迁移超声弹性图像的信息,TSDTL在基于B超的乳腺癌诊断任务中取得的平均分类准确率为87.84±2.08%、平均敏感度为88.89±3.70%、平均特异度为86.71±2.21%、平均约登指数为75.60±4.07%,优于直接基于单模态B超训练的分类模型以及多种典型迁移学习算法。结论 提出的TSDTL算法通过两阶段的深度迁移学习,将超声弹性图像的信息有效迁移至基于B超的乳腺癌CAD模型,提升了模型的诊断性能,具备潜在的应用可行性。     

Parameter determination of support vector machine and feature selection using simulated annealing approach

Support vector machine (SVM) is a novel pattern classification method that is valuable in many applications. Kernel parameter setting in the SVM training process, along with the feature selection, significantly affects classification accuracy. The objective of this study is to obtain the better parameter values while also finding a subset of features that does not degrade the SVM classification accuracy. This study develops a simulated annealing (SA) approach for parameter determination and feature selection in the SVM, termed SA-SVM.To measure the proposed SA-SVM approach, several datasets in UCI machine learning repository are adopted to calculate the classification accuracy rate. The proposed approach was compared with grid search which is a conventional method of performing parameter setting, and various other methods. Experimental results indicate that the classification accuracy rates of the proposed approach exceed those of grid search and other approaches. The SA-SVM is thus useful for parameter determination and feature selection in the SVM.     

Algorithm learning based neural network integrating feature selection and classification

Feature selection and classification techniques have been studied independently without considering the interaction between both procedures, which leads to a degraded performance. In this paper, we present a new neural network approach, which is called an algorithm learning based neural network (ALBNN), to improve classification accuracy by integrating feature selection and classification procedures. In general, a knowledge-based artificial neural network operates on prior knowledge from domain experience, which provides it with better starting points for the target function and leads to better classification accuracy. However, prior knowledge is usually difficult to identify. Instead of using unknown background resources, the proposed method utilizes prior knowledge that is mathematically calculated from the properties of other learning algorithms such as PCA, LARS, C4.5, and SVM. We employ the extreme learning machine in this study to help obtain better initial points faster and avoid irrelevant time-consuming work, such as determining architecture and manual tuning. ALBNN correctly approximates a target hypothesis by both considering the interaction between two procedures and minimizing individual procedure errors. The approach produces new relevant features and improves the classification accuracy. Experimental results exhibit improved performance in various classification problems. ALBNN can be applied to various fields requiring high classification accuracy.     

Improving the SVM gender classification accuracy using clustering and incremental learning

Gender recognition has been playing a very important role in various applications such as human–computer interaction, surveillance, and security. Nonlinear support vector machines (SVMs) were investigated for the identification of gender using the Face Recognition Technology (FERET) image face database. It was shown that SVM classifiers outperform the traditional pattern classifiers (linear, quadratic, Fisher linear discriminant, and nearest neighbour). In this context, this paper aims to improve the SVM classification accuracy in the gender classification system and propose new models for a better performance. We have evaluated different SVM learning algorithms; the SVM‐radial basis function with a 5% outlier fraction outperformed other SVM classifiers. We have examined the effectiveness of different feature selection methods. AdaBoost performs better than the other feature selection methods in selecting the most discriminating features. We have proposed two classification methods that focus on training subsets of images among the training images. Method 1 combines the outcome of different classifiers based on different image subsets, whereas method 2 is based on clustering the training data and building a classifier for each cluster. Experimental results showed that both methods have increased the classification accuracy.     

基于混沌机制的人工蜂群算法优化的支持向量机分类器

支持向量机的分类性能在很大程度上取决于其相关参数的选择,为了改善支持向量机的分类准确率,本文采用基于混沌机制的人工蜂群算法对其参数进行优化。在传统人工蜂群算法的基础上,采用Logistic混沌映射初始化种群和锦标赛选择策略,进一步提高人工蜂群算法的收敛速度和寻优精度。该方法采用分类准确率作为适应度函数,利用人工蜂群算法对支持向量机的惩罚因子和核函数参数进行优化。通过对多个标准数据集的分类测试,证明基于混沌机制的人工蜂群算法优化的支持向量机分类器能够获得更高的分类准确率。     

Comparison of feature selection and classification algorithms in identifying malicious executables

Malicious executables, often spread as email attachments, impose serious security threats to computer systems and associated networks. We investigated the use of byte sequence frequencies as a way to automatically distinguish malicious from benign executables without actually executing them. In a series of experiments, we compared classification accuracies over seven feature selection methods, four classification algorithms, and variable byte sequence lengths. We found that single-byte patterns provided surprisingly reliable features to separate malicious executables from benign. Between classifiers and feature selection methods, the overall performance of the models depended more on the choice of classifier than the method of feature selection. Support vector machine (SVM) classifiers were found to be superior in terms of prediction accuracy, training time, and aversion to overfitting.     

Feature selection for hyperspectral data based on recursive support vector machines

In this article, a feature selection algorithm for hyperspectral data based on a recursive support vector machine (R‐SVM) is proposed. The new algorithm follows the scheme of a state‐of‐the‐art feature selection algorithm, SVM recursive feature elimination or SVM‐RFE, and uses a new ranking criterion derived from the R‐SVM. Multiple SVMs are used to address the multiclass problem. The algorithm is applied to Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) data to select the most informative bands and the resulting subsets of the bands are compared with SVM‐RFE using the accuracy of classification as the evaluation of the effectiveness of the feature selection. The experimental results for an agricultural case study indicate that the feature subset generated by the newly proposed algorithm is generally competitive with SVM‐RFE in terms of classification accuracy and is more robust in the presence of noise.