基于深度学习并行网络模型的心律失常分类方法

目的 提出一种并行神经网络分类方法,以提高对正常搏动、室上性异位搏动、心室异位搏动、融合搏动4种心律失常的分类性能。方法 首先进行心电信号去噪、小尺度心拍和大尺度心拍的分割、数据增强等预处理;然后基于深度学习理论,应用密集连接卷积神经网络改善人工提取波形特征的局限性,并结合双向长短时记忆网络和高效通道注意力网络,以增强提取波形时序特征和重要特征的功能;接着采用并行网络结构,同时输入小尺度心拍和大尺度心拍的的波形特征,以提高心律失常分类的准确性;最后使用Softmax函数实现对心律失常的4分类任务。结果 利用MIT-BIH心律失常数据库和3组实验验证所提方法。多种并行网络模型分类性能对比实验和不同心拍输入方式下,各分类模型性能对比实验得出所提分类模型的总体准确率、平均灵敏度和平均特异性分别达到99.36%、96.08%、99.41%;并行网络分类模型收敛性能分析实验得出分类模型每次训练时间为41 s。结论 并行多网络分类方法在保持较高总体准确率的同时,平均灵敏度、平均特异性以及训练时间均有改善,该方法有望为心律失常临床诊断提供新的技术方案。     

Measuring Saliency of Features Using Signal-to-noise Ratios for Detection of Electrocardiographic Changes in Partial Epileptic Patients

Medical diagnostic accuracies can be improved when the pattern is simplified through representation by important features. The feature vector, which is comprised of the set of all features used to describe a pattern, is a reduced-dimensional representation of that pattern. By identifying a set of salient features, the noise in a classification model can be reduced, resulting in more accurate classification. In this study, a signal-to-noise ratio (SNR) saliency measure was employed to determine saliency of input features of probabilistic neural networks (PNNs) used in classification of two types of electrocardiogram (ECG) beats (normal and partial epilepsy). In order to extract features representing the ECG signals, discrete wavelet transform was used. The PNNs used in the ECG signals classification were trained for the SNR screening method. The application results of the SNR screening method to the ECG signals demonstrated that classification accuracies of the PNNs with salient input features are higher than that of the PNNs with salient and non-salient input features.     

A New Approach to Detection of ECG Arrhythmias: Complex Discrete Wavelet Transform Based Complex Valued Artificial Neural Network

This paper presents the new automated detection method for electrocardiogram (ECG) arrhythmias. The detection system is implemented with integration of complex valued feature extraction and classification parts. In feature extraction phase of proposed method, the feature values for each arrhythmia are extracted using complex discrete wavelet transform (CWT). The aim of using CWT is to compress data and to reduce training time of network without decreasing accuracy rate. Obtained complex valued features are used as input to the complex valued artificial neural network (CVANN) for classification of ECG arrhythmias. Ten types of the ECG arrhythmias used in this study were selected from MIT-BIH ECG Arrhythmias Database. Two different classification tasks were performed by the proposed method. In first classification task (CT-1), whether CWT-CVANN can distinguish ECG arrhythmia from normal sinus rhythm was examined one by one. For this purpose, nine classifiers were improved and executed in CT-1. Second classification task (CT-2) was to recognize ten different ECG arrhythmias by one complex valued classifier with ten outputs. Training and test sets were formed by mixing the arrhythmias in a certain order. Accuracy rates were obtained as 99.8% (averaged) and 99.2% for the first and second classification tasks, respectively. All arrhythmias in training and test phases were classified correctly for both of the classification tasks.     

Symptomatic vs. Asymptomatic Plaque Classification in Carotid Ultrasound

Quantitative characterization of carotid atherosclerosis and classification into symptomatic or asymptomatic type is crucial in both diagnosis and treatment planning. This paper describes a computer-aided diagnosis (CAD) system which analyzes ultrasound images and classifies them into symptomatic and asymptomatic based on the textural features. The proposed CAD system consists of three modules. The first module is preprocessing, which conditions the images for the subsequent feature extraction. The feature extraction stage uses image texture analysis to calculate Standard deviation, Entropy, Symmetry, and Run Percentage. Finally, classification is performed using AdaBoost and Support Vector Machine for automated decision making. For Adaboost, we compared the performance of five distinct configurations (Least Squares, Maximum- Likelihood, Normal Density Discriminant Function, Pocket, and Stumps) of this algorithm. For Support Vector Machine, we compared the performance using five different configurations (linear kernel, polynomial kernel configurations of different orders and radial basis function kernels). SVM with radial basis function kernel for support vector machine presented the best classification result: classification accuracy of 82.4%, sensitivity of 82.9%, and specificity of 82.1%. We feel that texture features coupled with the Support Vector Machine classifier can be used to identify the plaque tissue type. An Integrated Index, called symptomatic asymptomatic carotid index (SACI), is proposed using texture features to discriminate symptomatic and asymptomatic carotid ultrasound images using just one index or number. We hope this SACI can be used as an adjunct tool by the vascular surgeons for daily screening.     

影像组学在鉴别伴结石肾积水是否伴发肾细胞癌中的应用

目的利用有监督的机器学习方法探讨影像组学分析在鉴别伴结石肾积水是否伴发肾细胞癌中的应用。方法回顾性分 析经病理确诊的66例伴结石肾积水患者的腹部CT扫描,其中31例伴发肾细胞癌。对每位患者的三维肿瘤区域提取18个非纹 理特征和344个纹理特征,并应用无限特征选择技术（InfFS）结合支持向量机分类器的方法（SVM）进行特征选择。最后将最佳 特征子集训练SVM分类器并对伴结石肾积水是否伴发肾细胞癌进行预测。结果12个纹理特征入选最佳特征子集,且SVMInfFS 对伴结石肾积水是否伴发肾肿瘤的预测结果如下：感受曲线下面积、准确率、敏感性、特异性、假阳性和假阴性分别为 0.907、81.0%、70.0%、90.9%、9.1%和30.0%。临床医生以分类结果作为辅助信息进行诊断的结果如下：准确率、敏感性、特异 性、假阳性和假阴性分别为90.5%、80.0%、100%、0.00%、20.0%。结论基于有监督机器学习的计算机辅助分类模型,可有效提 取的辅助诊断信息,提高伴结石肾积水是否伴发肾细胞癌的诊断率。     

基于心拍的端到端心律失常分类

目的提出一种端到端的心律失常分类方法，以提高计算机对室上性异位心搏（SVEB）和室性异位心搏（VEB）的分类性 能。方法首先对心电信号进行心拍分割、校正等预处理；然后通过卷积神经网络构建心律失常分类网络，最后结合新的损失函 数训练分类器模型。结果利用MIT-BIH心律失常数据集验证本文分类方法的性能，其中在SVEB和VEB上的AUC分别达到 了0.77和0.98。在引入前5 min片段作为局部数据的情况下，SVEB和VEB的灵敏度分别达到了78.28%和98.88%；而在引入0、 50、100、150个样本作为局部数据时，SVEB和VEB的灵敏度最高分别达到82.25%和93.23%。结论本文提出的方法与现有的 方法相比，有效改善了样本类别不平衡带来的消极影响，SVEB和VEB灵敏度均有一定程度的提升，为心律失常的自动分类提 供了新的技术方案。     

支持向量机在CT鉴别诊断肾脏上皮样血管平滑肌脂肪瘤与肾透明细胞癌中的应用

目的探讨支持向量机在CT鉴别诊断肾脏上皮样血管平滑肌脂肪瘤(epithelioid angiomyolipoma,EAML)的CT与肾透明细胞癌(clear cell renal cell carcinoma,cc RCC)中的应用价值。方法搜集70例经病理证实的肾脏肿瘤(EAML、cc RCC病变各35例),采用支持向量机法综合分析其CT特征表现,判定其所属类型。结果支持向量机法(support vector machine,SVM)对EAML病变的诊断正确率为100%;对cc RCC病变的诊断正确率为94.59%;总体平均判别正确率为97.14%;训练集诊断正确率为97.30%;测试集诊断正确率为96.97%;与bagging和adaboost分类算法诊断符合率相接近。结论支持向量机法有助于CT鉴别诊断EAML和cc RCC,可用于辅助日常阅片工作,尤其是年轻医师或基层医院医师的工作。     

Three-Category Classification of Magnetic Resonance Hearing Loss Images Based on Deep Autoencoder

Hearing loss, a partial or total inability to hear, is known as hearing impairment. Untreated hearing loss can have a bad effect on normal social communication, and it can cause psychological problems in patients. Therefore, we design a three-category classification system to detect the specific category of hearing loss, which is beneficial to be treated in time for patients. Before the training and test stages, we use the technology of data augmentation to produce a balanced dataset. Then we use deep autoencoder neural network to classify the magnetic resonance brain images. In the stage of deep autoencoder, we use stacked sparse autoencoder to generate visual features, and softmax layer to classify the different brain images into three categories of hearing loss. Our method can obtain good experimental results. The overall accuracy of our method is 99.5%, and the time consuming is 0.078 s per brain image. Our proposed method based on stacked sparse autoencoder works well in classification of hearing loss images. The overall accuracy of our method is 4% higher than the best of state-of-the-art approaches.     

Towards Automatic Recognition of Scientifically Rigorous Clinical Research Evidence

The growing numbers of topically relevant biomedical publications readily available due to advances in document retrieval methods pose a challenge to clinicians practicing evidence-based medicine. It is increasingly time consuming to acquire and critically appraise the available evidence. This problem could be addressed in part if methods were available to automatically recognize rigorous studies immediately applicable in a specific clinical situation. We approach the problem of recognizing studies containing useable clinical advice from retrieved topically relevant articles as a binary classification problem. The gold standard used in the development of PubMed clinical query filters forms the basis of our approach. We identify scientifically rigorous studies using supervised machine learning techniques (Naïve Bayes, support vector machine (SVM), and boosting) trained on high-level semantic features. We combine these methods using an ensemble learning method (stacking). The performance of learning methods is evaluated using precision, recall and F₁ score, in addition to area under the receiver operating characteristic (ROC) curve (AUC). Using a training set of 10,000 manually annotated MEDLINE citations, and a test set of an additional 2,000 citations, we achieve 73.7% precision and 61.5% recall in identifying rigorous, clinically relevant studies, with stacking over five feature-classifier combinations and 82.5% precision and 84.3% recall in recognizing rigorous studies with treatment focus using stacking over word + metadata feature vector. Our results demonstrate that a high quality gold standard and advanced classification methods can help clinicians acquire best evidence from the medical literature.     

A New QRS Detection Method Using Wavelets and Artificial Neural Networks

We present a new method for detection and classification of QRS complexes in ECG signals using continuous wavelets and neural networks. Our wavelet method consists of four wavelet basis functions that are suitable in detection of QRS complexes within different QRS morphologies in the signal and thresholding technique for denoising and feature extraction. The results demonstrate that the proposed method is not only efficient for normal ECG signal analysis but also for various types of arrhythmic cardiac signals embedded in noise. For the classification stage, a feedforward neural network was trained with standard backpropagation algorithm. The classifier input features consisted of compact wavelet coefficients of QRS complexes that resulted in higher classification rates. We demonstrate the efficiency of our method with the average accuracy 97.2% in classification of normal and abnormal QRS complexes.     

A sequence labeling approach to link medications and their attributes in clinical notes and clinical trial announcements for information extraction

Objective

The goal of this work was to evaluate machine learning methods, binary classification and sequence labeling, for medication–attribute linkage detection in two clinical corpora.

Data and methods

We double annotated 3000 clinical trial announcements (CTA) and 1655 clinical notes (CN) for medication named entities and their attributes. A binary support vector machine (SVM) classification method with parsimonious feature sets, and a conditional random fields (CRF)-based multi-layered sequence labeling (MLSL) model were proposed to identify the linkages between the entities and their corresponding attributes. We evaluated the system''s performance against the human-generated gold standard.

Results

The experiments showed that the two machine learning approaches performed statistically significantly better than the baseline rule-based approach. The binary SVM classification achieved 0.94 F-measure with individual tokens as features. The SVM model trained on a parsimonious feature set achieved 0.81 F-measure for CN and 0.87 for CTA. The CRF MLSL method achieved 0.80 F-measure on both corpora.

Discussion and conclusions

We compared the novel MLSL method with a binary classification and a rule-based method. The MLSL method performed statistically significantly better than the rule-based method. However, the SVM-based binary classification method was statistically significantly better than the MLSL method for both the CTA and CN corpora. Using parsimonious feature sets both the SVM-based binary classification and CRF-based MLSL methods achieved high performance in detecting medication name and attribute linkages in CTA and CN.     

Highly Sensitive Computer Aided Diagnosis System for Breast Tumor Based on Color Doppler Flow Images

A computer-aided diagnosis (CAD) system for breast tumor based on color Doppler flow images is proposed. Our system consists of automatic segmentation, feature extraction, and classification of breast tumors. First, the B-mode grayscale image containing anatomical information was separated from a color Doppler flow image (CDFI). Second, the boundary of the breast tumor was automatically defined in the B-mode image and then morphologic and gray features were extracted. Third, an optimal feature vector was created using K-means cluster algorithm. Then a back-propagation (BP) artificial neural network (ANN) was used to classify breast tumors as benign, malignant or uncertain. Finally, the blood flow feature was extracted selectively from the CDFI, and was used to classify the uncertain tumor as benign or malignant. Experiments on 500 cases show that the proposed system yields an accuracy of 100% for the malignant and 80.8% for the benign classification. Comparing with other systems, the advantage of our system is that it has a much lower percentage of malignant tumor misdiagnosis.     

Accelerometer and Camera-Based Strategy for Improved Human Fall Detection

In this paper, we address the problem of detecting human falls using anomaly detection. Detection and classification of falls are based on accelerometric data and variations in human silhouette shape. First, we use the exponentially weighted moving average (EWMA) monitoring scheme to detect a potential fall in the accelerometric data. We used an EWMA to identify features that correspond with a particular type of fall allowing us to classify falls. Only features corresponding with detected falls were used in the classification phase. A benefit of using a subset of the original data to design classification models minimizes training time and simplifies models. Based on features corresponding to detected falls, we used the support vector machine (SVM) algorithm to distinguish between true falls and fall-like events. We apply this strategy to the publicly available fall detection databases from the university of Rzeszow’s. Results indicated that our strategy accurately detected and classified fall events, suggesting its potential application to early alert mechanisms in the event of fall situations and its capability for classification of detected falls. Comparison of the classification results using the EWMA-based SVM classifier method with those achieved using three commonly used machine learning classifiers, neural network, K-nearest neighbor and naïve Bayes, proved our model superior.     

基于普美显增强磁共振的影像组学鉴别肝细胞癌与肝血管瘤

目的基于普美显增强磁共振图像,评估影像组学方法在鉴别肝细胞癌（HCC）与肝血管瘤（HHE）的可行性。方法收集 HCC病人与HHE病人的普美显增强磁共振数据（总共135个病灶）,在肝特异期图像勾画病灶,利用影像组学方法提取每个病 灶的纹理特征。单特征分析：用两样本t检验或Mann Whitney U检验、ROC分析评估每个特征对HCC和HHE的区分程度及分 类性能;多特征分析：首先比较3种特征选择算法（最小冗余-最大相关、近邻成分分析、序列前向选择）的性能,根据最优的特征 选择算法确定最优特征子集,最后将特征选择的结果在3种分类器算法（支持向量机、线性判别分析、逻辑回归）上进行训练与测 试,整个分析过程均采用重复5次10折交叉验证实验。结果对于单特征分析,超过50%的特征具有较强的区分能力,其中灰度 共生矩阵特征S（3,-3）SumEntrp的分类性能：AUC为0.72（P<0.01）,敏感性为0.83,特异性为0.57;对于多特征分析,特征选择算 法比较的结果为序列前向搜索算法更优;最终基于该算法选择15个特征,其中支持向量机分类器上得到的平均分类性能：测试 准确率：0.82±0.09,AUC为0.86±0.12,敏感性为0.88±0.11,特异性为0.76±0.18。结论基于普美显增强磁共振图像,使用影像 组学方法能够很好地鉴别肝细胞癌与肝血管瘤,为临床辅助诊断提供有利的手段。     

不同病理类型及组织特点对肾活检后出血的影响

目的 评估不同病理类型及穿刺组织特点对超声引导下经皮肾穿刺活检后出血的影响。方法 以西安交通大学第二附属医院肾病内科2019年1月至2021年12月接受肾活检的患者为研究对象,比较不同病理类型的患者肾活检后的出血比率;分析活检组织的髓皮比、弓状动脉个数、肾小球硬化率及肾间质纤维化评分与肾活检后出血的关系以及在各种病理类型间的差异。结果 1 026例患者中超声下可探及出血343例,平均出血率33.4%,其中需治疗的大出血5例,占比0.49%。其中出血率较高的4种病理类型由高到低依次为干燥综合征肾损害(100%)、急性/亚急性肾小管损伤(66.7%)、结节硬化性肾炎(50.0%)和膜增生性/毛细血管内增生性肾炎(50.0%)。出血率较低的3种病理类型由低到高依次为微小病变肾病(25.3%)、膜性/非典型肾病(26.3%)、糖尿病性肾病(27.9%)。与非出血组比较,急性/亚急性肾小管损伤(P=0.032)、IgA肾病(P=0.043)出血率较高,膜性肾病/非典型肾病(P=0.003)出血率较低。活检组织中出血组的髓皮比、弓状动脉个数、肾小球硬化率、肾间质纤维化程度均高于未出血组,而仅髓皮比(P=0.032)、弓状动脉个数(P=0.037)差异有统计学意义。不同病理类型间的活检组织特点差异无统计学意义,而常见病理类型的部分临床资料差异有统计学意义。结论 不同病理类型对超声引导下肾活检后出血率有影响,肾脏活检组织的髓皮比及弓状动脉个数影响了活检后的出血程度。     

基于机器学习的椎弓根螺钉钉道超声图像评估方法

目的 探讨基于支持向量机（SVM）构建的人工智能辅助诊断模型对椎弓根螺钉钉道完整性进行超声鉴别与验证的方法研究。 方法 本文提出了一种基于超声图像智能分析的椎弓根钉道完整性评估方法。数据采自4个新鲜人体胸腰椎标本。预建立钉道50个，共800张超声图像（其中钉道完整与破损的样本各400个），采用五折交叉验证的方法对样本进行训练集与测试集的划分，对人工智能辅助诊断模型进行训练及测试。首先对超声图像进行裁剪，并采用亮度映射方法进行图像增强得到易于计算机判断识别且排除无效信息干扰的超声图像；然后通过灰度共生矩阵算法进行纹理特征提取，并采用支持向量机模型对正常和严重破损样本的初始分类模型进行搭建；其次，使用灰度分布得到用于区分前景和背景的阈值，并通过设计的损失函数得到得到钉道同心圆的半径；最后将同心圆外部图像的熵、方差、对比度、能量、平均绝对偏差作为第二类特征，最后进行轻微破损样本和未破损样本的二次分类模型搭建。 结果 初始分类的准确率为74.75%，特异性为71.81%，灵敏度为81.5%，F1值为76.35%，假正率为32%，假负率为18.5%。二次分类的准确率为93.75%，特异性为91.55%，灵敏度为97.5%，F1值为94.43%，假正率为9%，假负率为2.5%。二次类准确率与初始分类相比较，准确率提升19%。 结论 本文提出的基于SVM机器学习模型的方法可较为准确地检测椎弓根钉道的破损情况，且准确率较高，可用于术中实时判断椎弓根钉道的状态。     

谷氨酸脱羧酶抗体和胰岛细胞抗体对1型糖尿病的诊断价值

目的 探讨谷氨酸脱羧酶抗体(GAD-Ab)、胰岛细胞抗体(ICA)对1型糖尿病诊断的敏感度和特异度。方法 应用酶联免疫方法检测45例l型糖尿病患者和50例健康人血清GAD-Ab与ICA。结果 测量GAD-Ab的敏感度是48．9％，特异度94％；测量ICA的敏感度是26．7％，特异度96％；而GAD-Ab与ICA平行试验的敏感度62．5％。结论 GAD-Ab与ICA联合检测对1型糖尿病的诊断更敏感。     

Automated Diagnosis of Alzheimer Disease using the Scale-Invariant Feature Transforms in Magnetic Resonance Images

In this paper we present an automated method for diagnosing Alzheimer disease (AD) from brain MR images. The approach uses the scale-invariant feature transforms (SIFT) extracted from different slices in MR images for both healthy subjects and subjects with Alzheimer disease. These features are then clustered in a group of features which they can be used to transform a full 3-dimensional image from a subject to a histogram of these features. A feature selection strategy was used to select those bins from these histograms that contribute most in classifying the two groups. This was done by ranking the features using the Fisher’s discriminant ratio and a feature subset selection strategy using the genetic algorithm. These selected bins of the histograms are then used for the classification of healthy/patient subjects from MR images. Support vector machines with different kernels were applied to the data for the discrimination of the two groups, namely healthy subjects and patients diagnosed by AD. The results indicate that the proposed method can be used for diagnose of AD from MR images with the accuracy of %86 for the subjects aged from 60 to 80 years old and with mild AD.     

Myasthenia gravis in pediatric and elderly patients

Objective To determine whether the clinical and pathologic characteristics and prognoses of myasthenia gravis (MG) patients below 15 years differ from those patients over 50 years after thymectomy. Methods We reviewed the registry material of 30 pediatric and 32 elderly MG patients after thymectomy, including their age, sex, clinical classification, pathological types, and prognoses. The Chi-square test or Wilcoxon’s rank-sum test was used to determine the statistical differences between the children and elderly groups.Results No significant difference was seen in sex distribution between the two groups (Chi-square test, P=0.625), but there were differences in clinical classification: more type Ⅰ was observed in the pediatric group than in the elderly group, but more type Ⅱor Ⅲ was seen in the elderly group (Wilcoxon’s rank-sum test, P&lt;0.001). As to pathological types, the pediatric group was also significantly different from the elderly group (Chi-square test, P&lt;0.01). All of the patients (100%) in the pediatric group had thymus hyperplasia, but in the elderly group more than half (56.26%) were found to have thymoma (benign or malignant). The prognoses after thymectomy were better in the pediatric group than in the elderly group (Wilcoxon’s rank-sum test, P&lt;0.001). Conclusions Because the prognoses are generally better than those of the elderly patients, we should be careful when operating on pediatric patients of ocular type. The elderly patients tend to receive more aggressive treatment because of more severe generalized types often associated with thymoma and poor prognoses. Both pediatric and elderly patients are seldom associated with other autoimmune disease.     

应用磁共振4D flow成像对正常颅内前循环动脉血流动力学参数定量评估的可重复性研究

目的 探讨应用磁共振4D flow成像对正常颅内前循环动脉的血流动力学状态进行定量评估的可重复性。方法 收集正常志愿者4例,对每名志愿者的颅内Willis环区域分别进行两次4D flow成像,应用4D flow图像后处理软件测量计算正常志愿者双侧颈内动脉（internal carotid artery,ICA）入颅段、虹吸段、末端、双侧大脑中动脉（middle cerebral artery,MCA）起始部及近段、大脑前动脉（anterior cerebral artery,ACA）起始部（每例取双侧共12个位置）的血流动力学参数,比较两次扫描的平均血管面积、平均及最大血流速度、平均及最大瞬时血流量。生成血流矢量图、流线图及粒子追踪图显示颅内前循环大动脉的血流动力学状态。结果 4名正常志愿者两次颅内Willis环血流参数比较显示,ICA虹吸段左侧最大血流速度及右侧各项血流动力学参数两次扫描之间的差异有统计学意义;ICA入颅段、MCA及ACA起始部双侧及MCA近段右侧最大血流速度之间的差异有统计学意义;MCA近段双侧平均血管面积、ACA起始部左侧平均血管面积及平均血流速度之间的差异有统计学意义。其中一名志愿者的心率两次之间有较大变化,两次的最大血流速度之间存在明显区别。另外,在针对不同部位的分析中发现,颈动脉虹吸段位置两次测量的最大血流速度之间存在较明显区别。结论 应用磁共振4D flow成像对颅内动脉血流速度的评估的可重复性较好,对于不同心率状态下以及血流状态复杂部位的血流动力学评估,4D flow成像测量的可重复性可能还需要进一步验证。