基于特征提取的脑部MRI肿瘤自动分割

对脑部磁共振图像中肿瘤的自动分割,有助于了解疾病特征和制定手术方案,评价治疗效果。该文通过提取基于灰度统计、对称性、纹理等的特征,结合AdaBoost方法,利用计算机进行自动脑肿瘤分割。该方法综合利用了磁共振(MR)各加权图像的信息和大脑解剖结构的知识,以及AdaBoost算法的特征选择能力。在20帧带有肿瘤的MR图像上进行实验,得到了96.82%的分类准确率。     

Segmentation of psoriasis vulgaris images using multiresolution-based orthogonal subspace techniques.

In this paper, a method is proposed for the segmentation of color images using a multiresolution-based signature subspace classifier (MSSC) with application to psoriasis images. The essential techniques consist of feature extraction and image segmentation (classification) methods. In this approach, the fuzzy texture spectrum and the two-dimensional fuzzy color histogram in the hue-saturation space are first adopted as the feature vector to locate homogeneous regions in the image. Then these regions are used to compute the signature matrices for the orthogonal subspace classifier to obtain a more accurate segmentation. To reduce the computational requirement, the MSSC has been developed. In the experiments, the method is quantitatively evaluated by using a similarity function and compared with the well-known LS-SVM method. The results show that the proposed algorithm can effectively segment psoriasis images. The proposed approach can also be applied to general color texture segmentation applications.     

Dimensionality reduction using genetic algorithms

Pattern recognition generally requires that objects be described in terms of a set of measurable features. The selection and quality of the features representing each pattern affect the success of subsequent classification. Feature extraction is the process of deriving new features from original features to reduce the cost of feature measurement, increase classifier efficiency, and allow higher accuracy. Many feature extraction techniques involve linear transformations of the original pattern vectors to new vectors of lower dimensionality. While this is useful for data visualization and classification efficiency, it does not necessarily reduce the number of features to be measured since each new feature may be a linear combination of all of the features in the original pattern vector. Here, we present a new approach to feature extraction in which feature selection and extraction and classifier training are performed simultaneously using a genetic algorithm. The genetic algorithm optimizes a feature weight vector used to scale the individual features in the original pattern vectors. A masking vector is also employed for simultaneous selection of a feature subset. We employ this technique in combination with the k nearest neighbor classification rule, and compare the results with classical feature selection and extraction techniques, including sequential floating forward feature selection, and linear discriminant analysis. We also present results for the identification of favorable water-binding sites on protein surfaces     

Hybridized approach of image segmentation in classification of fruit mango using BPNN and discriminant analyzer

In machine learning, image classification accuracy generally depends on image segmentation and feature extraction methods with the extracted features and its qualities. The main focus of this paper is to determine the defected area of mangoes using image segmentation algorithm for improving the classification accuracy. The Enhanced Fuzzy based K-means clustering algorithm is designed for increasing the efficiency of segmentation. Proposed segmentation method is compared with K-means and Fuzzy C-means clustering methods. The geometric, texture and colour based features are used in the feature extraction. Process of feature selection is done by Maximally Correlated Principal Component Analysis (MCPCA). Finally, in the classification step, severe portions of the affected area are analyzed by Backpropagation Based Discriminant Classifier (BBDC). Proposed classifier is compared with BPNN and Naive Bayes classifiers. The images are classified into three classes in final output like Class A –good quality mango, Class B-average quality mango, and Class C-poor quality mango. Finally, the evaluated results of the proposed model examine various defected and healthy mango images and prove that the proposed method has the highest accuracy when compared with existing methods.

     

Feature encoding for unsupervised segmentation of color images

In this paper, an unsupervised segmentation method using clustering is presented for color images. We propose to use a neural network based approach to automatic feature selection to achieve adaptive segmentation of color images. With a self-organizing feature map (SOFM), multiple color features can be analyzed, and the useful feature sequence (feature vector) can then be determined. The encoded feature vector is used in the final segmentation using fuzzy clustering. The proposed method has been applied in segmenting different types of color images, and the experimental results show that it outperforms the classical clustering method. Our study shows that the feature encoding approach offers great promise in automating and optimizing the segmentation of color images.     

Glioma grade classification using wavelet transform-local binary pattern based statistical texture features and geometric measures extracted from MRI

The objective of this study is to perform brain glioma grade classification by identifying an optimal quantitative feature set from conventional magnetic resonance images. In this work, a hybrid feature set comprising of statistical texture and geometric features is computed over entire segmented tumor volume. Discrete wavelet transform (DWT) and local binary pattern (LBP) techniques are combined to extract texture information from segmented tumour volume at multiple resolutions. Statistical texture features comprising of skewness, kurtosis and entropy are then computed from DWT-LBP transformed images. Geometric features are calculated from (i) fractal dimension (FD) of three dimensional (3D) volumes of tumour region, tumour border and tumour skeleton, and (ii) convexity parameters over complete segmented tumour volume. Statistical analysis revealed that extracted texture features are significantly different between high grade (HG) and low grade (LG) glioma patients (p < 0.05). FD-based geometric parameters are significantly higher for HG glioma patients in comparison to LG glioma patients. Our results reflect that HG glioma has more structural complexity than LG glioma. The optimised feature set comprising of DWT-LBP-based texture features and FD-based measures extracted from segmented tumour volume achieved 96% accuracy, 97% sensitivity and 95% specificity for glioma classification with Naive Bayes classifier.     

基于分形维数的纹理图像分割

纹理图发割过程一般分为特征抽取和特征划分,文中提出一种新的基于分形维数的纹理图像分割方法,在特征抽取上,以分形作为纹理特征,运用图像变换的思想,结合差分盒计数和基于分形布朗自相似模型的分形估计方法。     

核磁共振图像脑组织自动提取方法

核磁共振图像的脑组织提取是神经图像处理研究中的一个重要步骤。将传统的几何活动轮廓模型与二值水平集函数相结合,提出了一种新型的二值水平集活动轮廓模型,并基于该模型提出了一种能够自动、准确实现MRI脑组织提取的方法。该方法在脑组织内部自动设定最优初始轮廓曲线,将该演化曲线隐含地表示成一个高维函数的零水平集,零水平集在基于区域的图像力驱动下不断演化并达到待分割脑部图像的边缘。将基于该方法的脑组织提取结果与作为金标准的专家手动分割结果和其他流行算法相比较,结果表明提出的脑组织提取方法能够自动、准确和快速地提取MRI脑组织,是一种鲁棒性较好的MRI脑组织提取方法。     

基于U-Net改进模型的直肠肿瘤分割方法

诊断直肠癌时,如果能够从CT图像中自动准确分割出直肠肿瘤区域,将有助于医生进行更准确和快速的诊断。针对直肠肿瘤分割问题,提出基于U-Net改进模型的直肠肿瘤自动分割方法。首先在U-Net模型的每级编码器中嵌入子编码模块提升模型特征提取能力;其次通过对比不同优化器的优化性能,获得最适合的优化器用于训练模型;最后对训练集进行数据扩充使模型得到更充分的训练,从而提高分割性能。与U-Net、Y-Net和FocusNetAlpha三种网络模型进行的对比实验表明：所提改进模型得到的分割区域与真实肿瘤区域更接近,对小目标的分割性能更突出,该模型的查准率、查全率和Dice系数三个评价指标都优于对比的模型,能有效分割直肠肿瘤区域。     

基于树形聚类匹配的脑肿瘤自动分割方法

提出一种基于树形聚类匹配的脑肿瘤自动分割方法.为了去除非脑组织对于脑肿瘤定位的影响,首先提出一种新的脑组织提取算法,这种算法无需完整的序列影像,可直接对三维影像数据进行分割.其次对分割后的脑组织影像进行中心定位,建立树形索引匹配结构,采用一种节点匹配算法完成粗分割,最后根据粗分割结果,采用形变模型完成精确分割.算法的特点是无需数据集的训练,能够较为准确的完成脑肿瘤的自动分割,实验结果验证了算法的实用性及可行性.     

Computer-aided diagnosis of human brain tumor through MRI: A survey and a new algorithm

Computer-aided detection/diagnosis (CAD) systems can enhance the diagnostic capabilities of physicians and reduce the time required for accurate diagnosis. The objective of this paper is to review the recent published segmentation and classification techniques and their state-of-the-art for the human brain magnetic resonance images (MRI). The review reveals the CAD systems of human brain MRI images are still an open problem. In the light of this review we proposed a hybrid intelligent machine learning technique for computer-aided detection system for automatic detection of brain tumor through magnetic resonance images. The proposed technique is based on the following computational methods; the feedback pulse-coupled neural network for image segmentation, the discrete wavelet transform for features extraction, the principal component analysis for reducing the dimensionality of the wavelet coefficients, and the feed forward back-propagation neural network to classify inputs into normal or abnormal. The experiments were carried out on 101 images consisting of 14 normal and 87 abnormal (malignant and benign tumors) from a real human brain MRI dataset. The classification accuracy on both training and test images is 99% which was significantly good. Moreover, the proposed technique demonstrates its effectiveness compared with the other machine learning recently published techniques. The results revealed that the proposed hybrid approach is accurate and fast and robust. Finally, possible future directions are suggested.     

Automatic clinical image segmentation using pathological modeling,PCA and SVM

Due to the presence of complicated topological and residual features, the segmentation of medical imagery is a difficult problem. In this paper, an automated approach to clinical image segmentation is presented. The processing of these images in our approach is divided into learning and segmentation stages to facilitate the application of principal component analysis with a support vector machine (SVM) classifier. During the initial learning stage, representative images are chosen to represent typical input images. These images are segmented using a variational level set method driven by a modeled energy functional designed to delineate the pathological characteristics of the images. Then a window-based feature extraction is applied to these segmented images. Principal component analysis is applied to these extracted features and the results are used to train an SVM classifier. After training the SVM, any time a clinical image needs to be segmented, it is simply classified with the trained SVM. By the proposed method, we take the strengths of both machine learning and the variational level set method while limiting their weaknesses to achieve automatic and fast clinical segmentation. To test the proposed system, both chest (thoracic) computed tomography (CT) scans (2D and 3D) and dental X-rays are used. Promising results are demonstrated and analyzed. The proposed method can be used during pre-processing for automatic computer-aided diagnosis.     

A learning-based colour image segmentation with extended and compact structural tensor feature representation

In this paper a novel Tensor-Based Image Segmentation Algorithm (TBISA) is presented, which is dedicated for segmentation of colour images. A purpose of TBISA is to distinguish specific objects based on their characteristics, i.e. shape, colour, texture, or a mixture of these features. All of those information are available in colour channel data. Nonetheless, performing image analysis on the pixel level using RGB values, does not allow to access information on texture which is hidden in relation between neighbouring pixels. Therefore, to take full advantage of all available information, we propose to incorporate the Structural Tensors as a feature extraction method. It forms enriched feature set which, apart from colour and intensity, conveys also information of texture. This set is next processed by different classification algorithms for image segmentation. Quality of TBISA is evaluated in a series of experiments carried on benchmark images. Obtained results prove that the proposed method allows accurate and fast image segmentation.     

回转窑烧成带状态混合智能识别方法

针对氧化铝回转窑过程复杂、长期依赖人工看火操作而造成的生产过程不稳定、 产品质量一致性差、能源消耗大等问题,提出了基于烧成带火焰图像特征与关键过程数据融合的烧成带状态自动识别方法, 该方法由烧成带火焰图像的分割、特征提取、 关键过程数据的融合以及二叉树支持向量机分类器模型组成.工业实验表明, 该方法能够较准确地识别烧成带状态,为基于产品质量指标优化的窑温控制器提供决策依据.     

基于特征选择与残差融合的肝肿瘤分割模型

目的 高效的肝肿瘤计算机断层扫描（computed tomography,CT）图像自动分割方法是临床实践的迫切需求,但由于肝肿瘤边界不清晰、体积相对较小且位置无规律,要求分割模型能够细致准确地发掘类间差异。对此,本文提出一种基于特征选择与残差融合的2D肝肿瘤分割模型,提高了2D模型在肝肿瘤分割任务中的表现。方法 该模型通过注意力机制对U-Net瓶颈特征及跳跃链接进行优化,为符合肝肿瘤分割任务特点优化传统注意力模块进,提出以全局特征压缩操作（global feature squeeze,GFS）为基础的瓶颈特征选择模块,即全局特征选择模块（feature selection module,FS）和邻近特征选择模块（neighbor feature selection module,NFS）。跳跃链接先通过空间注意力模块（spatial attention module,SAM）进行特征重标定,再通过空间特征残差融合（spatial feature residual fusion module,SFRF）模块解决前后空间特征的语义不匹配问题,在保持低复杂度的同时使特征高效表达。结果 在LiTS （liver tumor segmentation）公开数据集上进行组件消融测试并与当前方法进行对比测试,在肝脏及肝肿瘤分割任务中的平均Dice得分分别为96.2%和68.4%,与部分2.5D和3D模型的效果相当,比当前最佳的2D肝肿瘤分割模型平均Dice得分高0.8%。结论 提出的FSF-U-Net （feature selection and residual fusion U-Net）模型通过改进的注意力机制与优化U-Net模型结构的方法,使2D肝肿瘤分割的结果更加准确。     

改进FCM和LFP相结合的白细胞图像分类

研究白细胞图像分类识别中有效的图像分割与特征提取方法,以提高白细胞图像的正确识别率.由于某些白细胞(粒细胞)中颗粒的存在,严重影响细胞核与细胞质区域的正确分割,通过将空间信息与核函数融入模糊C-均值聚类(FCM)算法,提出一种改进的FCM算法.应用该算法对白细胞图像进行分割,并采用数学形态学方法对分割后的图像进行处理,获得了很好的分割效果,解决了粒细胞的质核分割难题.对于细胞的纹理特征提取,通过对局部二值模式(LBP)中阈值参数的模糊化,建立了基于局部模糊模式(LFP)的纹理特征提取算法.运用本文方法进行图像分割和纹理提取,以支持向量机作为分类器,对CellAtlas的100幅白细胞图像进行了分类识别的实验,结果表明白细胞的正确识别率达到93％.     

Feature selection for multi-label naive Bayes classification

In multi-label learning, the training set is made up of instances each associated with a set of labels, and the task is to predict the label sets of unseen instances. In this paper, this learning problem is addressed by using a method called Mlnb which adapts the traditional naive Bayes classifiers to deal with multi-label instances. Feature selection mechanisms are incorporated into Mlnb to improve its performance. Firstly, feature extraction techniques based on principal component analysis are applied to remove irrelevant and redundant features. After that, feature subset selection techniques based on genetic algorithms are used to choose the most appropriate subset of features for prediction. Experiments on synthetic and real-world data show that Mlnb achieves comparable performance to other well-established multi-label learning algorithms.     

基于CHI值特征选取和覆盖的文本分类方法

利用CHI值特征选取和前向神经网络的覆盖算法,通过对文本进行分词的预处理后,实现文本的自动分类。该方法利用CHI值进行特征选取即特征降维,应用覆盖算法进行文本分类。该方法将CHI值特征选取和覆盖算法充分结合,在提高了分类速度的同时还保证了分类的准确度。应用该方法对标准数据集中的文本进行实验,并在不同的维数上与SVM算法、朴素贝叶斯方法的实验结果进行了比较。结果表明,与SVM算法和朴素贝叶斯方法相比较,覆盖算法在准确度上更好。并且,维数的选择对分类的精确度影响很大。     

脑机接口中脑电信号的特征提取和模式分类

从智能处理与不确定性的角度, 探讨了脑机接口中的核心问题-EEG模式特征的识别和分类. 针对EEG模式分类中所存在的不确定性问题, 从EEG的特征提取和分类模型构建两个方面进行了分析, 并提出了解决问题的方法和对策. 以P300成分为例, 从导联选择、滤波处理和时间窗处理三方面进行特征提取, 采用贝叶斯线性判别分析的方法进行模式分类. 最后以第三届脑机接口竞赛P300字符输入的数据为实验, 分别采用3种不同的方法进行数据分析, 通过分类准确率和不同重复次数下性能的比较, 实验结果表明了本文特征提取和模式分类方法的有效性.     

基于随机森林特征选择算法的鼻咽肿瘤分割

针对医学图像中存在的灰度对比度低、器官组织边界模糊等问题，提出一种新的随机森林（RF）特征选择算法用于鼻咽肿瘤MR图像的分割。首先，充分提取图像的灰度、纹理、几何等特征信息用于构建一个初始的随机森林分类器；随后，结合随机森林特征重要性度量，将改进的特征选择方法应用于原始手工特征集；最终，以得到的最优特征子集构建新的随机森林分类器对测试图像进行分割。实验结果表明，该算法对鼻咽肿瘤的分割精度为：Dice系数79.197%，Acc准确率97.702%，Sen敏感度72.191%，Sp特异性99.502%。通过与基于传统随机森林和基于深度卷积神经网络（DCNN）的分割算法对比可知，所提特征选择算法能有效提取鼻咽肿瘤MR图像中的有用信息，并较大程度地提升小样本情况下鼻咽肿瘤的分割精度。