The improvement of breast cancer prognosis accuracy from integrated gene expression and clinical data

Predicting the accurate prognosis of breast cancer from high throughput microarray data is often a challenging task. Although many statistical methods and machine learning techniques were applied to diagnose the prognosis outcome of breast cancer, they are suffered from the low prediction accuracy (usually lower than 70%). In this paper, we propose a better method (genetic algorithm-support vector machine, we called GASVM) to significant improve the prediction accuracy of breast cancer from gene expression profiles. To further improve the classification performance, we also apply GASVM model using combined clinical and microarray data. In this paper, we evaluate the performance of the GASVM model based on data provided by 97 breast cancer patients. Four kinds of gene selection methods are used: all genes (All), 70 correlation-selected genes (C70), 15 medical literature-selected genes (R15), and 50 T-test-selected genes (T50). With optimized parameter values identified from GASVM model, the average predictive accuracy of our model approaches 95% for T50 and 90% for C70 or R15 in all four kernel functions using integrated clinical and microarray data. Our model produces results more accurately than the average 70% predictive accuracy of other machine learning methods. The results indicate that the GASVM model has the potential to better assist physicians in the prognosis of breast cancer through the use of both clinical and microarray data.     

面向乳腺超声图像分割的混合监督双通道反馈U-Net

目的 基于超声图像的乳腺病灶分割是实现乳腺癌计算机辅助诊断和定量分析的基本预处理步骤。由于乳腺超声图像病灶边缘通常较为模糊,而且缺乏大量已标注的分割图像,增加了基于深度学习的乳腺超声图像分割难度。本文提出一种混合监督双通道反馈U-Net（hybrid supervised dual-channel feedback U-Net,HSDF-U-Net）算法,提升乳腺超声图像分割的准确性。方法 HSDF-U-Net通过融合自监督学习和有监督分割实现混合监督学习,并且进一步通过设计双通道反馈U-Net网络提升图像分割准确性。为了改善标记数据有限的问题,首先在自监督学习框架基础上结合标注分割图像中的标签信息,设计一种边缘恢复的辅助任务,以实现对病灶边缘表征能力更强的预训练模型,然后迁移至下游图像分割任务。为了提升模型在辅助边缘恢复任务和下游分割任务的表现,将循环机制引入经典的U-Net网络,通过将反馈的输出结果重新送入另一个通道,构成双通道编码器,然后解码输出更精确的分割结果。结果 在两个公开的乳腺超声图像分割数据集上评估HSDF-U-Net算法性能。HSDF-U-Net对Dataset B数据集中的图像进行分割获得敏感度为0.848 0、Dice为0.826 1、平均对称表面距离为5.81的结果,在Dataset BUSI（breast ultrasound images）数据集上获得敏感度为0.803 9、Dice为0.803 1、平均对称表面距离为6.44的结果。与多种典型的U-Net分割算法相比,上述结果均有提升。结论 本文所提HSDF-U-Net算法提升了乳腺超声图像中的病灶分割的精度,具备潜在的应用价值。     

基于预测对抗网络的图像二分类模型

正未标记学习仅使用无标签样本和正样本训练一个二分类器, 而生成式对抗网络(generative adversarial networks, GAN)中通过对抗性训练得到一个图像生成器. 为将GAN的对抗训练方法迁移到正未标记学习中以提升正未标记学习的效果, 可将GAN中的生成器替换为分类器C, 在无标签数据集中挑选样本以欺骗判别器D, 对C与D进行迭代优化. 本文提出基于以Jensen-Shannon散度(JS散度)为目标函数的JS-PAN模型. 最后, 结合数据分布特点及现状需求, 说明了PAN模型在医疗诊断图像二分类应用的合理性及高性能. 在MNIST, CIFAR-10数据集上的实验结果显示: KL-PAN模型与同类正未标记学习模型对比有更高的精确度(ACC)及F1-score; 对称化改进后, JS-PAN模型在两个指标上均有所提升, 因此JS-PAN模型的提出更具有合理性. 在Med-MNIST的3个子图像数据集上的实验显示: KL-PAN模型与4个benchmark有监督模型有几乎相同的ACC, JS-PAN也有更高表现. 因此, 综合PAN模型的出色分类效果及医疗诊断数据的分布特征, PAN作为半监督学习方法可获得更快、更好的效果, 在医学图像的二分类的任务上具有更高的性能.     

支持向量机在鼻咽癌患者5年生存状态预测中的应用

利用最小二乘支持向量机和文献[10]中的半监督学习算法,我们对鼻咽癌患者5年生存状态进行了预测.实验结果表明:当已标注数据比较少时,两种方法的判别精度都比较低;随着已标注数据的增多,最小二乘支持向量机的推广能力逐渐增加,而半监督学习算法并没有给出更好的结果.这说明:对于鼻咽癌患者5年生存状态预测问题,最小二乘支持向量机比半监督学习方法更具有优势.     

A systematic review of machine learning techniques for software fault prediction

BackgroundSoftware fault prediction is the process of developing models that can be used by the software practitioners in the early phases of software development life cycle for detecting faulty constructs such as modules or classes. There are various machine learning techniques used in the past for predicting faults.MethodIn this study we perform a systematic review of studies from January 1991 to October 2013 in the literature that use the machine learning techniques for software fault prediction. We assess the performance capability of the machine learning techniques in existing research for software fault prediction. We also compare the performance of the machine learning techniques with the statistical techniques and other machine learning techniques. Further the strengths and weaknesses of machine learning techniques are summarized.ResultsIn this paper we have identified 64 primary studies and seven categories of the machine learning techniques. The results prove the prediction capability of the machine learning techniques for classifying module/class as fault prone or not fault prone. The models using the machine learning techniques for estimating software fault proneness outperform the traditional statistical models.ConclusionBased on the results obtained from the systematic review, we conclude that the machine learning techniques have the ability for predicting software fault proneness and can be used by software practitioners and researchers. However, the application of the machine learning techniques in software fault prediction is still limited and more number of studies should be carried out in order to obtain well formed and generalizable results. We provide future guidelines to practitioners and researchers based on the results obtained in this work.     

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。     

基于k个标记样本的弱监督学习框架

聚类是机器学习领域中的一个研究热点,弱监督学习是半监督学习中一个重要的研究方向,有广泛的应用场景.在对聚类与弱监督学习的研究中,提出了一种基于k个标记样本的弱监督学习框架.该框架首先用聚类及聚类置信度实现了标记样本的扩展.其次,对受限玻尔兹曼机的能量函数进行改进,提出了基于k个标记样本的受限玻尔兹曼机学习模型.最后,完成了对该模型的推理并设计相关算法.为了完成对该框架和模型的检验,选择公开的数据集进行对比实验,实验结果表明,基于k个标记样本的弱监督学习框架实验效果较好.     

语义拉普拉斯金字塔多中心乳腺肿瘤分割网络

目的 乳腺肿瘤分割对乳腺癌的辅助诊疗起着关键作用,但现有研究大多集中在单中心数据的分割上,泛化能力不强,无法应对临床的复杂数据。因此,本文提出一种语义拉普拉斯金字塔网络（semantic Laplacian pyramids network,SLAPNet）,实现多中心数据下乳腺肿瘤的准确分割。方法 SLAPNet主要包含高斯金字塔和语义金字塔两个结构,前者负责得到多尺度的图像输入,后者负责提取多尺度的语义特征并使语义特征能在不同尺度间传播。结果 网络使用Dice相似系数（Dice similarity coefficient,DSC）作为优化目标。为了验证模型性能,采用多中心数据进行测试,与AttentionUNet、PSPNet （pyramid scene parsing network）、UNet 3+、MSDNet （multiscale dual attention network）、PyConvUNet （pyramid convolutional network）等深度学习模型进行对比,并利用DSC和Jaccard系数（Jaccard coefficient,JC）等指标进行定量分析。使用内部数据集测试时,本文模型乳腺肿瘤分割的DSC为0.826;使用公开数据集测试时,DSC为0.774,比PyConvUNet提高了约1.3%,比PSPNet和UNet3+提高了约1.5%。结论 本文提出的语义拉普拉斯金字塔网络,通过结合多尺度和多级别的语义特征,可以在多中心数据上准确实现乳腺癌肿瘤的自动分割。     

Breast Mammogram Analysis and Classification Using Deep Convolution Neural Network

One of the fast-growing disease affecting women’s health seriously is breast cancer. It is highly essential to identify and detect breast cancer in the earlier stage. This paper used a novel advanced methodology than machine learning algorithms such as Deep learning algorithms to classify breast cancer accurately. Deep learning algorithms are fully automatic in learning, extracting, and classifying the features and are highly suitable for any image, from natural to medical images. Existing methods focused on using various conventional and machine learning methods for processing natural and medical images. It is inadequate for the image where the coarse structure matters most. Most of the input images are downscaled, where it is impossible to fetch all the hidden details to reach accuracy in classification. Whereas deep learning algorithms are high efficiency, fully automatic, have more learning capability using more hidden layers, fetch as much as possible hidden information from the input images, and provide an accurate prediction. Hence this paper uses AlexNet from a deep convolution neural network for classifying breast cancer in mammogram images. The performance of the proposed convolution network structure is evaluated by comparing it with the existing algorithms.     

一种基于标签传播的半监督核学习算法

一个好的核函数能提升机器学习模型的有效性,但核函数的选择并不容易,其与问题背景密切相关,且依赖于领域知识和经验。核学习是一种通过训练数据集寻找最优核函数的机器学习方法,能通过有监督学习的方式寻找到一组基核函数的最优加权组合。考虑到训练数据集获取标签的代价,提出一种基于标签传播的半监督核学习方法,该方法能够同时利用有标签数据和无标签数据进行核学习,通过半监督学习中被广泛使用的标签传播方法结合和谐函数获得数据集统一的标签分布。在UCI数据集上对提出的算法进行性能评估,结果表明该方法是有效的。     

基于半监督极限学习机的轴承故障诊断

鉴于在实际的应用中滚动轴承的故障信号所属的类别往往是未知的,而且为了得到一定的测试数据需要花费大量的时间,甚至对机械设备造成了一些损害.利用极限学习机训练速度快且泛化能力强的特点,提出了一种基于半监督极限学习机的滚动轴承故障诊断方法,该方法允许在有少量带标签的轴承故障数据的情况下,将带标签的历史数据与新采集到的部分未带标签的数据一起用来训练得到一个最优的诊断模型.首先通过相空间重构将原始一维信号映射到一个高维的相空间,在相空间中提取初始的轴承特征集,然后将特征集输入半监督的极限学习机中进行训练和测试.实验结果表明,这种基于半监督算法的诊断模型简单,在神经元个数较少的情况下仍然具有很好的泛化能力,具有一定的应用价值.     

拉普拉斯多层极速学习机

极速学习机不仅仅是有效的分类器,还能应用到半监督学习中.但是,半监督极速学习机和拉普拉斯光滑孪生支持向量机一样是一种浅层学习算法.深度学习实现了复杂函数的逼近并缓解了以前多层神经网络算法的局部最小性问题,目前在机器学习领域中引起了广泛的关注.多层极速学习机（ML-ELM）是根据深度学习和极速学习机的思想提出的算法,通过堆叠极速学习机-自动编码器算法（ELM-AE）构建多层神经网络模型,不仅实现复杂函数的逼近,并且训练过程中无需迭代,学习效率高.我们把流形正则化框架引入ML-ELM中提出拉普拉斯多层极速学习机算法（Lap-ML-ELM）.然而,ELM-AE不能很好的解决过拟合问题,针对这一问题我们把权值不确定引入ELM-AE中提出权值不确定极速学习机-自动编码器算法（WU-ELM-AE）,它学习到更为鲁棒的特征.最后,我们在前面两种算法的基础上提出权值不确定拉普拉斯多层极速学习机算法（WUL-ML-ELM）,它堆叠WU-ELM-AE构建深度模型,并且用流形正则化框架求取输出权值,该算法在分类精度上有明显提高并且不需花费太多的时间.实验结果表明,Lap-ML-ELM与WUL-ML-ELM都是有效的半监督学习算法.     

Breast Cancer Diagnosis Using Feature Selection Approaches and Bayesian Optimization

Breast cancer seriously affects many women. If breast cancer is detected at an early stage, it may be cured. This paper proposes a novel classification model based improved machine learning algorithms for diagnosis of breast cancer at its initial stage. It has been used by combining feature selection and Bayesian optimization approaches to build improved machine learning models. Support Vector Machine, K-Nearest Neighbor, Naive Bayes, Ensemble Learning and Decision Tree approaches were used as machine learning algorithms. All experiments were tested on two different datasets, which are Wisconsin Breast Cancer Dataset (WBCD) and Mammographic Breast Cancer Dataset (MBCD). Experiments were implemented to obtain the best classification process. Relief, Least Absolute Shrinkage and Selection Operator (LASSO) and Sequential Forward Selection were used to determine the most relevant features, respectively. The machine learning models were optimized with the help of Bayesian optimization approach to obtain optimal hyperparameter values. Experimental results showed the unified feature selection-hyperparameter optimization method improved the classification performance in all machine learning algorithms. Among the various experiments, LASSO-BO-SVM showed the highest accuracy, precision, recall and F1-score for two datasets (97.95%, 98.28%, 98.28%, 98.28% for MBCD and 98.95%, 97.17%, 100%, 98.56% for MBCD), yielding outperforming results compared to recent studies.     

基于深度学习的乳腺癌病理图像分类研究综述

准确、高效的乳腺癌病理图像分类是计算机辅助诊断的重要研究内容之一。随着机器学习技术的发展，深度学习日渐成为一种有效的乳腺癌病理图像分类处理方法。分析了乳腺癌病理图像分类方法及目前存在的问题；介绍了四种相关的深度学习模型，对基于深度学习的乳腺癌病理图像分类方法进行梳理，并通过实验对比分析现有模型的性能；最后对乳腺癌病理图像分类的关键问题进行了总结，并讨论了未来研究的发展趋势。     

基于联合训练的分类器的乳腺癌图像分类

利用机器学习的乳腺癌组织病理图像诊断节省了大量的人力物力,因此提高乳腺癌组织病理图像识别准确率有很好的现实意义;针对单一分类器和集成学习分类器模型观测域有限容易陷入局部最优的问题,提出一种基于联合训练的分类器模型;通过单一分类器相互影响扩大观测感知域来寻找损失最小的估计点,根据估计点来迭代优化超参数进而联合训练出拟合性能最好的分类器,这样既汲取不同分类器模型的可取之处来增强泛化能力,又加大了模型观测域在可以更快的得到全局最优的同时提升了识别准确率;实验表明,提出的联合训练的分类器能够提升乳腺癌组织病理学图像的分类性能,在不同放大倍数40×、100×、200×、400×下图像良恶性分类准确率分别为99.67%、98.08%、99.01%、96.34%。     

A systematic literature review on the use of machine learning in code clone research

Context:Research related to code clones includes detection of clones in software systems, analysis, visualization and management of clones. Detection of semantic clones and management of clones have attracted use of machine learning techniques in code clone related research.Objective:The aim of this study is to report the extent of machine learning usage in code clone related research areas.Method:The paper uses a systematic review method to report the use of machine learning in research related to code clones. The study considers a comprehensive set of 57 articles published in leading conferences, workshops and journals.Results:Code clone related research using machine learning techniques is classified into different categories. Machine learning and deep learning algorithms used in the code clone research are reported. The datasets, features used to train machine learning models and metrics used to evaluate machine learning algorithms are reported. The comparative results of various machine learning algorithms presented in primary studies are reported.Conclusion:The research will help to identify the status of using machine learning in different code clone related research areas. We identify the need of more empirical studies to assess the benefits of machine learning in code clone research and give recommendations for future research.     

基于多学习器协同训练模型的人体行为识别方法

人体行为识别是计算机视觉研究的热点问题,现有的行为识别方法都是基于监督学习框架.为了取得较好的识别效果,通常需要大量的有标记样本来建模.然而,获取有标记样本是一个费时又费力的工作.为了解决这个问题,对半监督学习中的协同训练算法进行改进,提出了一种基于多学习器协同训练模型的人体行为识别方法.这是一种基于半监督学习框架的识别算法.该方法首先通过基于Q统计量的学习器差异性度量选择算法来挑取出协同训练中基学习器集,在协同训练过程中,这些基学习器集对未标记样本进行标记;然后,采用了基于分类器成员委员会的标记近邻置信度计算公式来评估未标记样本的置信度,选取一定比例置信度较高的未标记样本加入到已标记的训练样本集并更新学习器来提升模型的泛化能力.为了评估算法的有效性,采用混合特征来表征人体行为,从而可以快速完成识别过程.实验结果表明,所提出的基于半监督学习的行为识别系统可以有效地辨识视频中的人体动作.     

Chaotic multi-swarm whale optimizer boosted support vector machine for medical diagnosis

Support vector machine (SVM) is a widely used pattern classification method that its classification accuracy is greatly influenced by both kernel parameter setting and feature selection. Therefore, in this study, to perform parameter optimization and feature selection simultaneously for SVM, we propose an improved whale optimization algorithm (CMWOA), which combines chaotic and multi-swarm strategies. Using several well-known medical diagnosis problems of breast cancer, diabetes, and erythemato-squamous, the proposed SVM model, termed CMWOAFS-SVM, was compared with multiple competitive SVM models based on other optimization algorithms including the original algorithm, particle swarm optimization, bacterial foraging optimization, and genetic algorithms. The experimental results demonstrate that CMWOAFS-SVM significantly outperformed all the other competitors in terms of classification performance and feature subset size.     

分段光滑的半监督支持向量分类机

为了解决半监督支持向量分类优化模型中的非凸非光滑问题,基于分段逼近的思想提出了一个分段函数,并以此逼近非凸非光滑的目标函数。给出的分段函数可以根据不同的精度要求选择不同的逼近参数,同时构造出基于上述分段函数的光滑半监督支持向量机模型。采用了LDS(Low Density Separation)算法求解模型,分析了其对对称铰链损失函数的逼进精度。理论分析和数值实验结果都证明分段光滑的半监督支持向量机的分类性能和效率优于以往提出的光滑模型。     

基于分歧的半监督学习

传统监督学习通常需使用大量有标记的数据样本作为训练例,而在很多现实问题中,人们虽能容易地获得大批数据样本,但为数据 提供标记却需耗费很多人力物力.那么,在仅有少量有标记数据时,可否通过对大量未标记数据进行利用来提升学习性能呢？为此,半监督学习 成为近十多年来机器学习的一大研究热点.基于分歧的半监督学习是该领域的主流范型之一,它通过使用多个学习器来对未标记数据进行利用, 而学习器间的"分歧"对学习成效至关重要.本文将综述简介这方面的一些研究进展.