改进Xception模型的乳腺钼靶图像识别研究

乳腺X线摄影技术是早期发现乳腺癌的主要方法,但其结果很大程度上受放射科医师临床诊断经验的限制;基于卷积神经网络对乳腺钼靶图像自动分类的研究可以为放射科医师临床诊断提供意见,然而乳腺癌肿块边缘模糊且良恶性肿块特征差异较小,分类任务面临重重挑战;为了提高乳腺钼靶图像分类的准确率,提出一种基于Xception模型的改进优化算法,改进模型中的残差连接模块,并嵌入Squeeze-and-excitation（SE）注意力机制对模型进行优化;采用优化后的Xception模型并结合迁移学习算法进行乳腺钼靶图像特征提取,并优化全连接层网络进行图像分类,使用公开的乳腺癌图像数据库CBIS-DDSM进行实验,将乳腺钼靶图像自动分为良性和恶性;实验结果表明该方法可以有效提高模型的分类效果,准确率和AUC分别达到了97.46%和99.12%。     

基于视觉注意机制的大范围水体信息遥感智能提取

建立契合遥感数据内在特征的智能信息分析模型与方法,是解决遥感大数据时代信息智能提取的关键所在。从普适性的大范围水体信息遥感智能采集的需求出发,构建一种基于视觉选择性注意机制与AdaBoost算法的水体信息遥感智能提取方法。首先通过对遥感多特征指数的RGB配色方案的优化设计,实现水体信息图像特征的增强和可视化表达。然后在HSV颜色空间中,利用色差距离图像的关键节点信息构造分类特征集,并采用AdaBoost算法构建水体识别分类器,据此从图像色彩聚类结果中自动识别出水体所属类别,实现水体信息的智能提取。对比实验结果表明,该方法的水体信息提取结果在漏分率（LR）和复合分类精度（CCA）上都有明显提高;同时,该方法能有效减少对高质量训练样本的依赖性,对于丰水期泥沙含量较高水体以及洪灾导致的淹没区等临时性水域也具有较好的识别性能。     

基于多分类AdaBoost改进算法的TEE标准切面分类

针对超声图像样本冗余、不同标准切面因疾病导致的高度相似性、感兴趣区域定位不准确问题,提出一种结合特征袋（BOF）特征、主动学习方法和多分类AdaBoost改进算法的经食管超声心动图（TEE）标准切面分类方法。首先采用BOF方法对超声图像进行描述;然后采用主动学习方法选择对分类器最有价值的样本作为训练集;最后,在AdaBoost算法对弱分类器的迭代训练中,根据临时强分类器的分类情况调整样本更新规则,实现对多分类AdaBoost算法的改进和TEE标准切面的分类。在TEE数据集和三个UCI数据集上的实验表明,相比AdaBoost.SAMME算法、多分类支持向量机（SVM）算法、BP神经网络和AdaBoost.M2算法,所提算法在各个数据集上的G-mean指标、整体分类准确率和大多数类别分类准确率都有不同程度的提升,且比较难分的类别分类准确率提升最为显著。实验结果表明,在包含类间相似样本的数据集上,分类器的性能有显著提升。     

模糊AdaBoost算法在SAR图像目标识别中的应用

提出了一种AdaBoost算法的多类别推广方法,并将推广后的算法应用于合成孔径雷达图像目标识别中.针对AdaBoost基本算法只考虑两类分类的情况,对算法进行多类别推广,用"一对一"方法将多类别分类问题分解为多个两类分类问题,用模糊方法对多个两类AdaBoost分类器的输出进行决策判决,得到最终分类结果.将推广后的模糊AdaBoost算法应用于SAR图像目标识别,用MSTAR数据库中3个军事目标进行识别实验.实验结果表明,该算法可有效应用于SAR图像目标识别.与其他分类算法相比较,可获得较高的目标正确识别率.     

一种用于不平衡数据分类的改进AdaBoost算法

真实世界中存在大量的类别不平衡分类问题,传统的机器学习算法如AdaBoost算法,关注的是分类器的整体性能,而没有给予小类更多的关注。因此针对类别不平衡学习算法的研究是机器学习的一个重要方向。AsymBoost作为AdaBoost的一种改进算法,用于类别不平衡学习时,牺牲大类样本的识别精度来提高小类样本的分类性能。AsymBoost算法依然可能遭遇样本权重过大造成的过适应问题。据此提出了一种新型的AdaBoost改进算法。该方法通过对大类中分类困难样本的权重和标签进行处理,使分类器能够同时获得较好的查准率和查全率。实验结果表明,该方法可以有效提高在不平衡数据集上的分类性能。     

基于能量图像的目标识别方法

提出了一种基于AdaBoost算法,利用能量图像进行目标分类的算法.该算法通过灰度图像创建能量图像,并将能量图像作为样本进行机器的集中学习,实现对骑车人、行人和车辆目标的分类识别.根据待检测目标的能量分布,构建了能描述目标的典型特征,并以检测区域的能量差异作为其特征值.重点讨论了骑车人和行人的分类识别问题.实验结果表明,所提出方法对本课题中的特定目标具有较好的识别率,并具有较强的鲁棒性.     

一种快速嘴部检测方法在视听语音识别的应用

在改进噪音环境下的语音识别率中,来自于说话人嘴部的可视化语音信息有着显著的作用。介绍了在视听语音识别（AVSR）中的重要组成部分之一：可视化信息的前端设计;描述了一种用于快速处理图像并能达到较高识别率的人脸嘴部检测的机器学习方法,此方法引入了旋转Hart-like特征在积分图像中的应用,在基于AdaBoost学习算法上通过使用单值分类作为基础特征分类器,以级联的方式合并强分类器,最后划分检测区域用于嘴部定位。将上述方法应用于AVSR系统中,基本上达到了对人脸嘴部实时准确的检测效果。     

集成多尺度微调卷积神经网络下的甲状腺结节良恶性识别

针对由于训练图像样本较少与忽略多尺度的结构和纹理信息而导致分类性能不佳问题,为提升甲状腺结节良恶性诊断准确率,提出了集成多尺度微调卷积神经网络下的甲状腺结节超声图像识别算法.首先将图像转换成具有3种不同尺度信息作为输入数据,以便模型能够学习到图像不同尺度的特征信息,提高模型的特征提取能力;其次,通过优化3种预训练模型(AlexNet,VGG16和ResNet50)的全连接层结构和迁移学习与微调策略,构建了3种不同尺度的9个微调模型,让模型能够更好地学习源域(ImageNet)和目标域(甲状腺超声图像)上的特征差异;最后选择最优的微调模型组合并通过对模型输出类别概率的加权融合方法得到最终的集成模型,利用模型的多样性进一步提升分类性能.文中算法在真实采集的数据集上和其他算法进行对比实验,得到甲状腺结节良恶性识别的准确率为96.00％,敏感度为94.10％,特异度为97.70％,AUC为98.00％ 实验结果表明,该算法在这些指标上均优于传统机器学习算法和当前甲状腺结节良恶性识别领域中的其他算法,能够有效地提取出互补的视觉特征信息,具有令人满意的分类性能.     

基于PCA特征提取和距离哈希K近邻分类的人脸表情识别

使用PCA降维,提取人脸表情特征,并结合基于距离的哈希K近邻分类算法进行人脸表情识别。首先使用类Haar特征和AdaBoost算法进行人脸检测,并对人脸图像进行预处理;接着使用PCA提取人脸表情特征,并将特征加入到哈希表;最后使用K近邻分类算法进行人脸表情的识别。将特征库重构为哈希表后,很大地提高了识别效率。     

基于钙化点信息的乳腺病灶类型识别算法

为了有效地对乳腺恶性病变做出早期诊断,提出一种基于钙化点信息的乳腺病灶类型识别算法.算法以钙化点的形状信息、纹理信息、空间分布信息为特征量,以支持向量机为工具对钙化点进行恶性与良性分类.对开放乳腺图像数据库MIAS的仿真实验表明,算法的检出率超过86%,错检率不足4%,达到理想的识别效果.     

Toward a combined tool to assist dermatologists in melanoma detection from dermoscopic images of pigmented skin lesions

In this paper we propose a machine learning approach to classify melanocytic lesions as malignant or benign, using dermoscopic images. The lesion features used in the classification framework are inspired on border, texture, color and structures used in popular dermoscopy algorithms performed by clinicians by visual inspection. The main weakness of dermoscopy algorithms is the selection of a set of weights and thresholds, that appear not to be robust or independent of population. The use of machine learning techniques allows to overcome this issue. The proposed method is designed and tested on an image database composed of 655 images of melanocytic lesions: 544 benign lesions and 111 malignant melanoma. After an image pre-processing stage that includes hair removal filtering, each image is automatically segmented using well known image segmentation algorithms. Then, each lesion is characterized by a feature vector that contains shape, color and texture information, as well as local and global parameters. The detection of particular dermoscopic patterns associated with melanoma is also addressed, and its inclusion in the classification framework is discussed. The learning and classification stage is performed using AdaBoost with C4.5 decision trees. For the automatically segmented database, classification delivered a specificity of 77% for a sensitivity of 90%. The same classification procedure applied to images manually segmented by an experienced dermatologist yielded a specificity of 85% for a sensitivity of 90%.     

Microcalcification diagnosis in digital mammography using extreme learning machine based on hidden Markov tree model of dual-tree complex wavelet transform

Diagnosis of benign and malignant microcalcifications in digital mammography using Computer-aided Diagnosis (CAD) system is critical for the early diagnosis of breast cancer. Wavelet transform based diagnosis methods are effective to accomplish this task, but limited by representing the correlation within each wavelet scale, these methods neglect the correlation between wavelet scales. In this paper, we apply the hidden Markov tree model of dual-tree complex wavelet transform (DTCWT-HMT) for microcalcification diagnosis in digital mammography. DTCWT-HMT can effectively capture the correlation between different wavelet coefficients and model the statistical dependencies and non-Gaussian statistics of real signals, is used to characterize microcalcifications for the diagnosis of benign and malignant cases. The combined features which consist of the DTCWT-HMT features and the DTCWT features are optimized by genetic algorithm (GA). Extreme learning machine (ELM), an efficient learning theory is employed as the classifier to diagnose the benign and malignant microcalcifications. The validity of the proposed method is evaluated on the Nijmegen, MIAS and DDSM datasets using area under curve (AUC) of receiver operating characteristic (ROC). The AUC values of 0.9856, 0.9941 and 0.9168 of the proposed method are achieved on Nijmegen, MIAS and DDSM, respectively. We compare the proposed method with state-of-the-art diagnosis methods, and the experimental results show the effectiveness of the proposed method for the diagnosis of the benign and malignant microcalcifications in mammograms in terms of the accuracy and stability.     

基于混合受限玻尔兹曼机的肺结节良恶性诊断

针对传统计算机辅助诊断中肺结节的特征提取方法依靠人工设计、操作复杂、识别率低等问题,提出了一种基于混合受限玻尔兹曼机的肺结节良恶性诊断方法。首先采用多层无监督卷积受限玻尔兹曼机自动对肺结节图像进行特征学习,然后利用分类受限玻尔兹曼机对获得的特征进行良恶性分类。为避免分类受限玻尔兹曼机在训练中出现的特征同质化问题,引入了交叉熵稀疏惩罚对其进行优化。实验结果表明,该方法有效避免了手动特征提取的复杂性,在肺结节良恶性分类的准确率、敏感性、特异性、ROC曲线下面积值上均优于传统诊断方法。     

基于一种改进的LBP算法和超限学习机的肝硬化识别

肝硬化的计算机辅助诊断对肝脏疾病的早期治疗和诊断具有重要意义。针对B超图像中肝硬化病变区域边缘模糊和回声不均匀、尺度因素影响等问题,提出了改进的LBP算法并提取了相应的SLBP特征。该特征较传统的纹理特征更准确地描述了B超图像中肝硬化病变的特征,结合二维Gabor变换,解决了上述难题。鉴于传统的机器学习方法的训练时间较长,采用基于超限学习机的训练方法,并首次将其应用于肝硬化识别。实验结果表明,所提方法对测试集的分类准确率达到95.4%,在时间效率上较传统方法有很大提高。ROC曲线表明,提出的分类方法在准确率和泛化能力上均优于传统方法,有助于肝硬化的临床诊断。     

ThyroScreen system: high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform

Using right equipment and well trained personnel, ultrasound of the neck can detect a large number of non-palpable thyroid nodules. However, this technique often suffers from subjective interpretations and poor accuracy in the differential diagnosis of malignant and benign thyroid lesions. Therefore, we developed an automated identification system based on knowledge representation techniques for characterizing the intra-nodular vascularization of thyroid lesions. Twenty nodules (10 benign and 10 malignant), taken from 3-D high resolution ultrasound (HRUS) images were used for this work. Malignancy was confirmed using fine needle aspiration biopsy and subsequent histological studies. A combination of discrete wavelet transformation (DWT) and texture algorithms were used to extract relevant features from the thyroid images. These features were fed to different configurations of AdaBoost classifier. The performance of these configurations was compared using receiver operating characteristic (ROC) curves. Our results show that the combination of texture features and DWT features presented an accuracy value higher than that reported in the literature. Among the different classifier setups, the perceptron based AdaBoost yielded very good result and the area under the ROC curve was 1 and classification accuracy, sensitivity and specificity were 100%. Finally, we have composed an Integrated Index called thyroid malignancy index (TMI) made up of these DWT and texture features, to facilitate distinguishing and diagnosing benign or malignant nodules using just one index or number. This index would help the clinicians in more quantitative assessment of the thyroid nodules.     

Performance Analysis of Breast Cancer Detection Method Using ANFIS Classification Approach

Breast cancer is one of the deadly diseases prevailing in women. Earlier detection and diagnosis might prevent the death rate. Effective diagnosis of breast cancer remains a significant challenge, and early diagnosis is essential to avoid the most severe manifestations of the disease. The existing systems have computational complexity and classification accuracy problems over various breast cancer databases. In order to overcome the above-mentioned issues, this work introduces an efficient classification and segmentation process. Hence, there is a requirement for developing a fully automatic methodology for screening the cancer regions. This paper develops a fully automated method for breast cancer detection and segmentation utilizing Adaptive Neuro Fuzzy Inference System (ANFIS) classification technique. This proposed technique comprises preprocessing, feature extraction, classifications, and segmentation stages. Here, the wavelet-based enhancement method has been employed as the preprocessing method. The texture and statistical features have been extracted from the enhanced image. Then, the ANFIS classification algorithm is used to classify the mammogram image into normal, benign, and malignant cases. Then, morphological processing is performed on malignant mammogram images to segment cancer regions. Performance analysis and comparisons are made with conventional methods. The experimental result proves that the proposed ANFIS algorithm provides better classification performance in terms of higher accuracy than the existing algorithms.     

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.     

A computer-aided diagnosis system for malignant melanomas

The aim of this study is to provide an efficient way to segment the malignant melanoma images. This method first eliminates extra hair and scales using edge detection; afterward, it deduces a color image into an intensity image and approximately segments the image by intensity thresholding. Some morphological operations are used to focus on an image area where a melanoma boundary potentially exists and then used to localize the boundary in that area. The distributions of texture and a new feature known as AIBQ features in the next step provide a good discrimination of skin lesions to feature extraction. Finally, we rely on quantitative image analysis to measure a series of candidate attributes hoped to contain enough information to differentiate malignant from benign melanomas. The selected features are applied to a support vector machine to classify the melanomas as malignant or benign. By our approach, we obtained 95 % correct classification of malignant or benign melanoma on real melanoma images.     

Pedestrian detection for intelligent transportation systems combining AdaBoost algorithm and support vector machine

Pedestrians are the vulnerable participants in transportation system when crashes happen. It is important to detect pedestrian efficiently and accurately in many computer vision applications, such as intelligent transportation systems (ITSs) and safety driving assistant systems (SDASs). This paper proposes a two-stage pedestrian detection method based on machine vision. In the first stage, AdaBoost algorithm and cascading method are adopted to segment pedestrian candidates from image. To confirm whether each candidate is pedestrian or not, a second stage is needed to eliminate some false positives. In this stage, a pedestrian recognizing classifier is trained with support vector machine (SVM). The input features used for SVM training are extracted from both the sample gray images and edge images. Finally, the performance of the proposed pedestrian detection method is tested with real-world data. Results show that the performance is better than conventional single-stage classifier, such as AdaBoost based or SVM based classifier.