Fully automatic and segmentation-robust classification of breast tumors based on local texture analysis of ultrasound images

Region of interest (ROI) is a region used to extract features. In breast ultrasound (BUS) image, the ROI is a breast tumor region. Because of poor image quality (low SNR (signal/noise ratio), low contrast, blurry boundaries, etc.), it is difficult to segment the BUS image accurately and produce a ROI which precisely covers the tumor region. Due to the requirement of accurate ROI for feature extraction, fully automatic classification of BUS images becomes a difficult task. In this paper, a novel fully automatic classification method for BUS images is proposed which can be divided into two steps: “ROI generation step” and “ROI classification step”. The ROI generation step focuses on finding a credible ROI instead of finding the precise tumor location. The ROI classification step employs a novel feature extraction and classification strategy. First, some points in the ROI are selected as the “classification checkpoints” which are evenly distributed in the ROI, and the local texture features around each classification checkpoint are extracted. For each ROI, all the classification checkpoints are classified. Finally, the class of the BUS image is determined by analyzing every classification checkpoint in the corresponding ROI. Both steps were implemented by utilizing a supervised texture classification approach. The experiments demonstrate that the proposed method is very robust to the segmentation of BUS images, and very effective and useful for classifying breast tumors.     

乳腺超声图像中易混淆困难样本的分类方法

目的 超声诊断常作为乳腺肿瘤首选的影像学检查和术前评估方法,但存在良恶性结节的图像表现重叠、诊断严重依赖医生经验,以及需要较多人机交互等问题。为减少误诊和不必要的穿刺活检率,以及提高诊断自动化程度,本文提出一种端到端的模型,实现结节区域自动提取及良恶性鉴别。方法 就超声图像散斑噪声问题使用基于边缘增强的各向异性扩散去噪模型（edge enhanced anisotropic diffusion,EEAD）实现数据预处理,之后针对结节良恶性特征提出一个改进的损失函数以增强鉴别性能,通过形状描述符组合挖掘因形状与其他类别相似从而易导致错判的困难样本,为使该部分困难样本具有更好的区分性,应用改进的损失函数,并在此基础上构建困难样本形状约束损失项,用来调整形状相似但类别不同样本间的特征映射。结果 为验证算法的有效性,构建了一个包含1 805幅图像的乳腺超声数据集,在该数据集上具有5年资历医生的平均判断准确率为85.3%,而本文方法在该数据集上分类正确率为92.58%,敏感性为90.44%,特异性为93.72%,AUC （area under curve）为0.946,均优于对比算法;相对传统Softmax损失函数,各评价指标提高了5% 12%。结论 本文提出了一个端到端的乳腺超声图像分类方法,实用性强;通过将医学知识融合到优化模型,增加的困难样本形状约束损失项可提高乳腺肿瘤良恶性诊断的准确性和鲁棒性,各项评价指标均高于超声科医生,具有临床应用价值。     

Computer-aided detection and classification of microcalcifications in mammograms: a survey

Breast cancer continues to be a significant public health problem in the world. Approximately, 182,000 new cases of breast cancer are diagnosed and 46,000 women die of breast cancer each year in the United States. Even more disturbing is the fact that one out of eight women in US will develop breast cancer at some point during her lifetime. Primary prevention seems impossible since the causes of this disease still remain unknown. Early detection is the key to improving breast cancer prognosis. Mammography is one of the reliable methods for early detection of breast carcinomas. There are some limitations of human observers, and it is difficult for radiologists to provide both accurate and uniform evaluation for the enormous number of mammograms generated in widespread screening. The presence of microcalcification clusters (MCCs) is an important sign for the detection of early breast carcinoma. An early sign of 30–50% of breast cancer detected mammographically is the appearance of clusters of fine, granular microcalcification, and 60–80% of breast carcinomas reveal MCCs upon histological examinations. The high correlation between the appearance of the microcalcification clusters and the diseases show that the CAD (computer aided diagnosis) systems for automated detection/classification of MCCs will be very useful and helpful for breast cancer control. In this survey paper, we summarize and compare the methods used in various stages of the computer-aided detection systems (CAD). In particular, the enhancement and segmentation algorithms, mammographic features, classifiers and their performances are studied and compared. Remaining challenges and future research directions are also discussed.     

Computer‐aided classification of breast masses in mammogram images based on spherical wavelet transform and support vector machines

Breast cancer can be effectively detected and diagnosed using the technology of digital mammography. However, although this technology has been rapidly developing recently, suspicious regions cannot be detected in some cases by radiologists, because of the noise or inappropriate mammogram contrast. This study presents a classification of segmented region of interests (ROIs) as either benign or malignant to serve as a second eye of the radiologists. Our study consists of three steps. In the first step, spherical wavelet transform (SWT) is applied to the original ROIs. In the second step, shape, boundary and grey level based features of wavelet (detail) and scaling (approximation) coefficients are extracted. Finally, in the third step, malignant/benign classification of the masses is implemented by giving the feature matrices to a support vector machine system. The proposed system achieves 91.4% and 90.1% classification accuracy using the dataset acquired from the hospital of Istanbul University in Turkey and the free Mammographic Image Analysis Society, respectively. Furthermore, discrete wavelet transform, which produces 83.3% classification accuracy, is applied to the coefficients to make a comparison with the SWT method.     

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。     

Fully automatic segmentation of breast ultrasound images based on breast characteristics in space and frequency domains

Due to the complicated structure of breast and poor quality of ultrasound images, accurately and automatically locating regions of interest (ROIs) and segmenting tumors are challenging problems for breast ultrasound (BUS) computer-aided diagnosis systems. In this paper, we propose a fully automatic BUS image segmentation approach for performing accurate and robust ROI generation, and tumor segmentation. In the ROI generation step, the proposed adaptive reference point (RP) generation algorithm can produce the RPs automatically based on the breast anatomy; and the multipath search algorithm generates the seeds accurately and fast. In the tumor segmentation step, we propose a segmentation framework in which the cost function is defined in terms of tumor?s boundary and region information in both frequency and space domains. First, the frequency constraint is built based on the newly proposed edge detector which is invariant to contrast and brightness; and then the tumor pose, position and intensity distribution are modeled to constrain the segmentation in the spatial domain. The well-designed cost function is graph-representable and its global optimum can be found. The proposed fully automatic segmentation method is applied to a BUS database with 184 cases (93 benign and 91 malignant), and the performance is evaluated by the area and boundary error metrics. Compared with the newly published fully automatic method, the proposed method is more accurate and robust in segmenting BUS images.     

先验权重共享码本下内窥镜图像大肠病变分类

目的 大肠息肉和溃疡性结肠炎（ulcerative colitis,UC）是常见的大肠疾病,发病率高,检测需求大,且容易在临床中被漏诊和误诊。因此研究用于内窥镜大肠病变图像分类的计算机辅助诊断（computer-aided diagnosis,CAD）系统十分重要。局域约束线性编码（locality constrained linear coding,LLC）在图像分类领域展现了优异的性能,能够完成对内窥镜中病变图像的分类。但是由于肠胃内窥镜图像中存在的一些微小息肉等病理征状与肠壁十分相似,LLC在这一场景下的性能有待提高。方法 由于码本的设计对细微差别检测能力影响大,本文通过改进LLC中的码本来实现更精确的大肠病变分类,其中原始码本被改进为带有先验权重影响的共享码本。主要思想是尝试尽可能多地使用代表私有部分的码本。本文方法重新排列了码本的列,将较少使用的原子排列在码本的后面,成为共享码本。并利用原子使用的频率计算权重,通过在线字典学习的方法,获得具有先验权重的共享码本。利用这一新码本对特征进行编码能实现更为高效精确的图像分类。结果 为避免过拟合,将部分Kvasir数据集与部分医院合作数据集合并使用。实验在2 600幅内窥镜图像上进行正常、息肉和UC图像的三分类实验,与压缩感知空间金字塔池化（compressed sensing spatial pyramid pooling,CSSPP）方法、私有共享字典学习算法（category-specific dictionary and shared dictionary learning,CSDL）、环形空间金字塔模型方法（circular inner ring partitioning,CIRP）、显著性和自适应局部约束线性编码（saliency and adaptive locality constrained linear coding,SALLC）和AlexNet迁移学习的网络比较,本文方法的总体分类准确率为93.82%,较对比方法分别高了2.33%、2.21%、1.91%、0.8%、0.07%。结论 本文所提出的先验权重共享码本,综合了词汇袋模型和共享字典的思想,使得对内窥镜图像中相似图片的分类更加精确。     

Cancer classification by gradient LDA technique using microarray gene expression data

Cancer classification is one of the major applications of the microarray technology. When standard machine learning techniques are applied for cancer classification, they face the small sample size (SSS) problem of gene expression data. The SSS problem is inherited from large dimensionality of the feature space (due to large number of genes) compared to the small number of samples available. In order to overcome the SSS problem, the dimensionality of the feature space is reduced either through feature selection or through feature extraction. Linear discriminant analysis (LDA) is a well-known technique for feature extraction-based dimensionality reduction. However, this technique cannot be applied for cancer classification because of the singularity of the within-class scatter matrix due to the SSS problem. In this paper, we use Gradient LDA technique which avoids the singularity problem associated with the within-class scatter matrix and shown its usefulness for cancer classification. The technique is applied on three gene expression datasets; namely, acute leukemia, small round blue-cell tumour (SRBCT) and lung adenocarcinoma. This technique achieves lower misclassification error as compared to several other previous techniques.     

深度学习在医学影像中的应用综述

深度学习能自动从大样本数据中学习获得优良的特征表达,有效提升各种机器学习任务的性能,已广泛应用于信号处理、计算机视觉和自然语言处理等诸多领域。基于深度学习的医学影像智能计算是目前智慧医疗领域的研究热点,其中深度学习方法已经应用于医学影像处理、分析的全流程。由于医学影像内在的特殊性、复杂性,特别是考虑到医学影像领域普遍存在的小样本问题,相关学习任务和应用场景对深度学习方法提出了新要求。本文以临床常用的X射线、超声、计算机断层扫描和磁共振等4种影像为例,对深度学习在医学影像中的应用现状进行综述,特别面向图像重建、病灶检测、图像分割、图像配准和计算机辅助诊断这5大任务的主要深度学习方法的进展进行介绍,并对发展趋势进行展望。     

Thermography based breast cancer analysis using statistical features and fuzzy classification

Medical thermography has proved to be useful in various medical applications including the detection of breast cancer where it is able to identify the local temperature increase caused by the high metabolic activity of cancer cells. It has been shown to be particularly well suited for picking up tumours in their early stages or tumours in dense tissue and outperforms other modalities such as mammography for these cases. In this paper we perform breast cancer analysis based on thermography, using a series of statistical features extracted from the thermograms quantifying the bilateral differences between left and right breast areas, coupled with a fuzzy rule-based classification system for diagnosis. Experimental results on a large dataset of nearly 150 cases confirm the efficacy of our approach that provides a classification accuracy of about 80%.     

深度学习在口腔医学影像中的应用与挑战

口腔医学影像是进行临床口腔疾病检测、筛查、诊断和治疗评估的重要工具,对口腔影像进行准确分析对于后续治疗计划的制定至关重要。常规的口腔医学影像分析依赖于医师的水平和经验,存在阅片效率低、可重复性低以及定量分析欠缺的问题。深度学习可以从大样本数据中自动学习并获取优良的特征表达,提升各类机器学习任务的效率和性能,目前已广泛应用于医学影像分析处理的各类任务之中。基于深度学习的口腔医学影像处理是目前的研究热点,但由于口腔医学领域内在的特殊性和复杂性,以及口腔医学影像数据样本量通常较小的问题,给深度学习方法在相关学习任务和场景的应用带来了新的挑战。本文从口腔医学影像领域常用的二维X射线影像、三维点云/网格影像和锥形束计算机断层扫描影像3种影像出发,介绍深度学习技术在口腔医学影像处理及分析领域应用的思路和现状,分析了各算法的优缺点及该领域所面临的问题和挑战,并对未来的研究方向和可能开展的临床应用进行展望,以助力智慧口腔建设。     

行人行为的奇异性检测和正常行为分类

提出了一种固定场景视频序列异常检测和正常行为分类的方法。该方法定义行人正常的走路和跑动为正常行为,最大的特点在于时空联合特征的选择。首先选用区域特征,通过分析正常行为找到特征的在时间上的统计规律,视频序列中行人不符合规律的行为被判定为异常。然后选用具有时空联合分布特点的目标轮廓特征,通过支持向量机（Support Vector Machine,SVM）进行训练,在训练的基础上判断目标行为是走路还是跑动。该方法在一定样本基础上进行了实验,实验结果表明,该方法能够较好进行行为检测和分类,性能比其他方法也有提高。     

Intensity-based statistical features for classification of lungs CT scan nodules using artificial intelligence techniques

A computer-aided diagnostic (CAD) system for effective and accurate pulmonary nodule detection is required to detect the nodules at early stage. This paper proposed a novel technique to detect and classify pulmonary nodules based on statistical features for intensity values using support vector machine (SVM). The significance of the proposed technique is, it uses the nodules features in 2D & 3D and also SVM for the classification that is good to classify the nodules extracted from the image. The lung volume is extracted from Lung CT using thresholding, background removal, hole-filling and contour correction of lung lobe. The candidate nodules are extracted and pruned using the rules based on ground truth of nodules. The statistical features for intensity values are extracted from candidate nodules. The nodule data are up-samples to reduce the biasness. The classifier SVM is trained using data samples. The efficiency of proposed CAD system is tested and evaluated using Lung Image Consortium Database (LIDC) that is standard data-set used in CAD Systems for Lungs Nodule classification. The results obtained from proposed CAD system are good as compare to previous CAD systems. The sensitivity of 96.31% is achieved in the proposed CAD system.     

融合空间和通道特征的高精度乳腺癌分类方法

组织病理学图像是鉴别乳腺癌的黄金标准,所以对乳腺癌组织病理学图像的自动、精确的分类具有重要的临床应用价值。为了提高乳腺组织病理图像的分类准确率,从而满足临床应用的需求,提出了一种融合空间和通道特征的高精度乳腺癌分类方法。该方法使用颜色归一化来处理病理图像并使用数据增强扩充数据集,基于卷积神经网络（CNN）模型DenseNet和压缩和激励网络（SENet）融合病理图像的空间特征信息和通道特征信息,并根据压缩-激励（SE）模块的插入位置和数量,设计了三种不同的BCSCNet模型,分别为BCSCNetⅠ、BCSCNetⅡ、BCSCNetⅢ。在乳腺癌癌组织病理图像数据集（BreaKHis）上展开实验。通过实验对比,先是验证了对图像进行颜色归一化和数据增强能提高乳腺的分类准确率,然后发现所设计的三种乳腺癌分类模型中精度最高为BCSCNetⅢ。实验结果表明,BCSCNetⅢ的二分类准确率在99.05%~99.89%,比乳腺癌组织病理学图像分类网络（BHCNet）提升了0.42个百分点;其多分类的准确率在93.06%~95.72%,比BHCNet提升了2.41个百分点。证明了BCSCNet能准确地对乳腺癌组织病理图像进行分类,同时也为计算机辅助乳腺癌诊断提供了可靠的理论支撑。     

A novel method for pulmonary embolism detection in CTA images

In this paper, we propose a new computer-aided detection (CAD) – based method to detect pulmonary embolism (PE) in computed tomography angiography images (CTAI). Since lung vessel segmentation is the main objective to provide high sensitivity in PE detection, this method performs accurate lung vessel segmentation. To concatenate clogged vessels due to PEs, the starting region of PEs and some reference points (RPs) are determined. These RPs are detected according to the fixed anatomical structures. After lung vessel tree is segmented, the region, intensity, and size of PEs are used to distinguish them. We used the data sets that have heart disease or abnormal tissues because of lung disease except PE in this work. According to the results, 428 of 450 PEs, labeled by the radiologists from 33 patients, have been detected. The sensitivity of the developed system is 95.1% at 14.4 false positive per data set (FP/ds). With this performance, the proposed CAD system is found quite useful to use as a second reader by the radiologists.     

Road intersection detection and classification using hierarchical SVM classifier

In this paper, a hierarchical multi-classification approach using support vector machines (SVM) has been proposed for road intersection detection and classification. Our method has two main steps. The first involves the road detection. For this purpose, an edge-based approach has been developed using the bird’s eye view image which is mapped from the perspective view of the road scene. Then, the concept of vertical spoke has been introduced for road boundary form extraction. The second step deals with the problem of road intersection detection and classification. It consists on building a hierarchical SVM classifier of the extracted road forms using the unbalanced decision tree architecture. Many measures are incorporated for good evaluation of the proposed solution. The obtained results are compared to those of Choi et al. (2007).     

Plant-wide detection and diagnosis using correspondence analysis

This paper presents an approach based on the correspondence analysis (CA) for the task of fault detection and diagnosis. Unlike other data-based monitoring tools, such as principal components analysis/dynamic PCA (PCA/DPCA), the CA algorithm has been shown to use a different metric to represent the information content in the data matrix X. Decomposition of the information represented in the metric is shown here to yield superior performance from the viewpoints of data compression, discrimination and classification, as well as early detection and diagnosis of faults. Metrics similar to the contribution plots and threshold statistics that have been developed and used for PCA are also proposed in this paper for detection and diagnosis using the CA algorithm. Further, using the benchmark Tennessee Eastman problem as a case study, significant performance improvements are demonstrated in monitoring and diagnosis (in terms of shorter detection delays, smaller false alarm rates, reduced missed detection rates and clearer diagnosis) using the CA algorithm over those achievable using the PCA and DPCA algorithms.     

Microwave tomography for breast cancer detection on Cell broadband engine processors

Microwave tomography (MT) is a safe screening modality that can be used for breast cancer detection. The technique uses the dielectric property contrasts between different breast tissues at microwave frequencies to determine the existence of abnormalities. Our proposed MT approach is an iterative process that involves two algorithms: Finite-Difference Time-Domain (FDTD) and Genetic Algorithm (GA). It is a compute intensive problem: (i) the number of iterations can be quite large to detect small tumors; (ii) many fine-grained computations and discretizations of the object under screening are required for accuracy. In our earlier work, we developed a parallel algorithm for microwave tomography on CPU-based homogeneous, multi-core, distributed memory machines. The performance improvement was limited due to communication and synchronization latencies inherent in the algorithm. In this paper, we exploit the parallelism of microwave tomography on the Cell BE processor. Since FDTD is a numerical technique with regular memory accesses, intensive floating point operations and SIMD type operations, the algorithm can be efficiently mapped on the Cell processor achieving significant performance. The initial implementation of FDTD on Cell BE with 8 SPEs is 2.9 times faster than an eight node shared memory machine and 1.45 times faster than an eight node distributed memory machine. In this work, we modify the FDTD algorithm by overlapping computations with communications during asynchronous DMA transfers. The modified algorithm also orchestrates the computations to fully use data between DMA transfers to increase the computation-to-communication ratio. We see 54% improvement on 8 SPEs (27.9% on 1 SPE) for the modified FDTD in comparison to our original FDTD algorithm on Cell BE. We further reduce the synchronization latency between GA and FDTD by using mechanisms such as double buffering. We also propose a performance prediction model based on DMA transfers, number of instructions and operations, the processor frequency and DMA bandwidth. We show that the execution time from our prediction model is comparable (within 0.5 s difference) with the execution time of the experimental results on one SPE.     

Unsupervised feature selection using swarm intelligence and consensus clustering for automatic fault detection and diagnosis in Heating Ventilation and Air Conditioning systems

Various sensory and control signals in a Heating Ventilation and Air Conditioning (HVAC) system are closely interrelated which give rise to severe redundancies between original signals. These redundancies may cripple the generalization capability of an automatic fault detection and diagnosis (AFDD) algorithm. This paper proposes an unsupervised feature selection approach and its application to AFDD in a HVAC system. Using Ensemble Rapid Centroid Estimation (ERCE), the important features are automatically selected from original measurements based on the relative entropy between the low- and high-frequency features. The materials used is the experimental HVAC fault data from the ASHRAE-1312-RP datasets containing a total of 49 days of various types of faults and corresponding severity. The features selected using ERCE (Median normalized mutual information (NMI) = 0.019) achieved the least redundancies compared to those selected using manual selection (Median NMI = 0.0199) Complete Linkage (Median NMI = 0.1305), Evidence Accumulation K-means (Median NMI = 0.04) and Weighted Evidence Accumulation K-means (Median NMI = 0.048). The effectiveness of the feature selection method is further investigated using two well-established time-sequence classification algorithms: (a) Nonlinear Auto-Regressive Neural Network with eXogenous inputs and distributed time delays (NARX-TDNN); and (b) Hidden Markov Models (HMM); where weighted average sensitivity and specificity of: (a) higher than 99% and 96% for NARX-TDNN; and (b) higher than 98% and 86% for HMM is observed. The proposed feature selection algorithm could potentially be applied to other model-based systems to improve the fault detection performance.     

基于属性约简和支持向量机集成的乳腺癌诊断决策

针对遗传算法(GA)与支持向量机(SVM)集成相结合的疾病诊断方法存在属性冗余的问题,提出了一种改进的约简和诊断乳腺癌决策方法。该方法将最小化约简属性个数、最大化区分矩阵可区别属性的个数以及最大化约简属性对决策属性的依赖度这三种目标函数相结合作为GA的适应度函数。在约简属性后取多个子集,以便利用SVM集成学习。在UCI数据库中乳腺癌数据集的实验表明,与原始的SVM算法相比,该方法在分类诊断的准确度以及敏感性方面有一定的提高,其中分类准确度至少提高了2%。