Noninvasive diagnosis of coronary artery disease using a neural network algorithm

This study examines the utility of neural networks for detecting coronary artery disease noninvasively by using the clinical examination variables and extracting useful information from the diastolic heart sounds associated with coronary occlusions. It has been widely reported that coronary stenoses produce sounds due to the turbulent blood flow in these vessels. These complex and highly attenuated signals taken from recordings made in both soundproof and noisy rooms were detected and analyzed to provide feature set based on the poles and power spectral density function (PSD) of the Autoregressive (AR) method after Adaptive Line Enhancement (ALE) method. In addition, some physical examination variables such as sex, age, body weight, smoking condition, diastolic pressure, systolic pressure and derivation from them were included in the feature vector. This feature vector was used as the input pattern to the neural network. The analysis was studied on one hundred recordings (63 abnormal, 37 normals). The network correctly identified 84% of the subjects with coronary artery disease and 89% of the normal subjects.     

Sentence alignment using feed forward neural network

Parallel corpora have become an essential resource for work in multi lingual natural language processing. However, sentence aligned parallel corpora are more efficient than non-aligned parallel corpora for cross language information retrieval and machine translation applications. In this paper, we present a new approach to align sentences in bilingual parallel corpora based on feed forward neural network classifier. A feature parameter vector is extracted from the text pair under consideration. This vector contains text features such as length, punctuate score, and cognate score values. A set of manually prepared training data has been assigned to train the feed forward neural network. Another set of data was used for testing. Using this new approach, we could achieve an error reduction of 60% over length based approach when applied on English-Arabic parallel documents. Moreover this new approach is valid for any language pair and it is quite flexible approach since the feature parameter vector may contain more/less or different features than that we used in our system such as lexical match feature.     

A Slantlet transform based intelligent system for magnetic resonance brain image classification

The present paper proposes the development of a new approach for automated diagnosis, based on classification of magnetic resonance (MR) human brain images. Wavelet transform based methods are a well-known tool for extracting frequency space information from non-stationary signals. In this paper, the proposed method employs an improved version of orthogonal discrete wavelet transform (DWT) for feature extraction, called Slantlet transform, which can especially be useful to provide improved time localization with simultaneous achievement of shorter supports for the filters. For each two-dimensional MR image, we have computed its intensity histogram and Slantlet transform has been applied on this histogram signal. Then a feature vector, for each image, is created by considering the magnitudes of Slantlet transform outputs corresponding to six spatial positions, chosen according to a specific logic. The features hence derived are used to train a neural network based binary classifier, which can automatically infer whether the image is that of a normal brain or a pathological brain, suffering from Alzheimer's disease. An excellent classification ratio of 100% could be achieved for a set of benchmark MR brain images, which was significantly better than the results reported in a very recent research work employing wavelet transform, neural networks and support vector machines.     

冠状动脉造影大致正常的胸痛患者临床分析

摘要 目的：探讨有胸痛症状的冠状动脉造影大致正常的患者的临床特点及病因。方法：回顾性分析2019年1月至2021年5月我院收治的有胸痛症状疑诊为冠状动脉粥样硬化性心脏病并行冠状动脉造影的1283例患者,纳入其中冠状动脉造影提示冠状动脉大致正常的患者,比较冠状动脉造影结果大致正常者与冠状动脉造影存在异常的患者的人口学资料、危险因素等,并统计冠状动脉造影结果大致正常者的确定诊断并进行分析。结果：最终纳入91例疑诊为冠心病的冠状动脉造影大致正常的患者。与冠状动脉造影存在异常的1192例患者的相比,冠脉造影大致正常组中无危险因素者占20.1%,单一高危因素者占50.5%,显著高于冠脉造影异常组,而多重高危因素者占28.6%,显著低于冠脉造影异常组（P＜0.05）。91例疑诊为冠心病的冠状动脉造影大致正常的患者中心脏神经官能症及心律失常分别占45例（49.5％）及12例(13.2％)。结论：临床上很多疑诊为冠心病的胸痛患者的冠状动脉造影大致正常,这部分患者与冠状动脉异常的患者相比冠心病的危险因素更少,胸痛由其他原因引起,所以对这部分患者应强调应用无创的检查手段。     

Identification of butterfly species with a single neural network system

Growing interest in conservation and biodiversity increased the demand for accurate and consistent identification of biological objects, such as insects, at the level of individual or species. Among the identification issues, butterfly identification at the species level has been strongly addressed because it is directly connected to the crop plants for human food and animal feed products. However, so far, the widely-used reliable methods were not suggested due to the complicated butterfly shape. In the present study, we propose a novel approach based on a back-propagation neural network to identify butterfly species. The neural network system was designed as a multi-class pattern classifier to identify seven different species. We used branch length similarity (BLS) entropies calculated from the boundary pixels of a butterfly shape as the input feature to the neural network. We verified the accuracy and efficiency of our method by comparing its performance to that of another single neural network system in which the binary values (0 or 1) of all pixels on an image shape are used as a feature vector. Experimental results showed that our method outperforms the binary image network in both accuracy and efficiency.     

Evolutionary optimization of classifiers and features for single-trial EEG Discrimination

Background  

State-of-the-art signal processing methods are known to detect information in single-trial event-related EEG data, a crucial aspect in development of real-time applications such as brain computer interfaces. This paper investigates one such novel approach, evaluating how individual classifier and feature subset tailoring affects classification of single-trial EEG finger movements. The discrete wavelet transform was used to extract signal features that were classified using linear regression and non-linear neural network models, which were trained and architecturally optimized with evolutionary algorithms. The input feature subsets were also allowed to evolve, thus performing feature selection in a wrapper fashion. Filter approaches were implemented as well by limiting the degree of optimization.     

End-to-end neural system identification with neural information flow

Neural information flow (NIF) provides a novel approach for system identification in neuroscience. It models the neural computations in multiple brain regions and can be trained end-to-end via stochastic gradient descent from noninvasive data. NIF models represent neural information processing via a network of coupled tensors, each encoding the representation of the sensory input contained in a brain region. The elements of these tensors can be interpreted as cortical columns whose activity encodes the presence of a specific feature in a spatiotemporal location. Each tensor is coupled to the measured data specific to a brain region via low-rank observation models that can be decomposed into the spatial, temporal and feature receptive fields of a localized neuronal population. Both these observation models and the convolutional weights defining the information processing within regions are learned end-to-end by predicting the neural signal during sensory stimulation. We trained a NIF model on the activity of early visual areas using a large-scale fMRI dataset recorded in a single participant. We show that we can recover plausible visual representations and population receptive fields that are consistent with empirical findings.     

Diagnosis of Coronary Heart Diseases Using Gene Expression Profiling; Stable Coronary Artery Disease,Cardiac Ischemia with and without Myocardial Necrosis

Cardiovascular disease (including coronary artery disease and myocardial infarction) is one of the leading causes of death in Europe, and is influenced by both environmental and genetic factors. With the recent advances in genomic tools and technologies there is potential to predict and diagnose heart disease using molecular data from analysis of blood cells. We analyzed gene expression data from blood samples taken from normal people (n = 21), non-significant coronary artery disease (n = 93), patients with unstable angina (n = 16), stable coronary artery disease (n = 14) and myocardial infarction (MI; n = 207). We used a feature selection approach to identify a set of gene expression variables which successfully differentiate different cardiovascular diseases. The initial features were discovered by fitting a linear model for each probe set across all arrays of normal individuals and patients with myocardial infarction. Three different feature optimisation algorithms were devised which identified two discriminating sets of genes, one using MI and normal controls (total genes = 6) and another one using MI and unstable angina patients (total genes = 7). In all our classification approaches we used a non-parametric k-nearest neighbour (KNN) classification method (k = 3). The results proved the diagnostic robustness of the final feature sets in discriminating patients with myocardial infarction from healthy controls. Interestingly it also showed efficacy in discriminating myocardial infarction patients from patients with clinical symptoms of cardiac ischemia but no myocardial necrosis or stable coronary artery disease, despite the influence of batch effects and different microarray gene chips and platforms.     

An automatic diagnostic system of coronary artery lesions in Kawasaki disease using intravascular optical coherence tomography imaging

Intravascular optical coherence tomography (IV‐OCT) is a light‐based imaging modality with high resolution, which employs near‐infrared light to provide tomographic intracoronary images. Morbidity caused by coronary heart disease is a substantial cause of acute coronary syndrome and sudden cardiac death. The most common intracoronay complications caused by coronary artery disease are intimal hyperplasia, calcification, fibrosis, neovascularization and macrophage accumulation, which require efficient prevention strategies. OCT can provide discriminative information of the intracoronary tissues, which can be used to train a robust fully automatic tissue characterization model based on deep learning. In this study, we aimed to design a diagnostic model of coronary artery lesions. Particularly, we trained a random forest using convolutional neural network features to distinguish between normal and diseased arterial wall structure. Then, based on the arterial wall structure, fully convolutional network is designed to extract the tissue layers in normal cases, and pathological tissues regardless of lesion type in pathological cases. Then, the type of the lesions can be characterized with high precision using our previous model. The results demonstrate the robustness of the model with the approximate overall accuracy up to 90%.      

LogitBoost classifier for discriminating thermophilic and mesophilic proteins

A novel classifier, the so-called LogitBoost classifier, was introduced to discriminate the thermophilic and mesophilic proteins according to their primary structures. When the 20-amino acid composition was chosen as the feature vector, the overall accuracy of the self-consistency check and a five-fold cross-validation procedure was 97.0% and 86.6%, respectively. To test if the method was also applicable to a wide range of biological targets, an independent testing dataset was also used. The method based on LogitBoost algorithm has achieved an overall classification accuracy of 88.9%. According to the three different validation check approaches, it was demonstrated that LogitBoost outperformed AdaBoost and performed comparably with RBF neural network and support vector machine. The influence of protein size on discrimination was addressed.     

改进GA-SVM在冠状动脉疾病诊断中的应用

改进的遗传算法（GA）自动优化支持向量机（SVM）参数,同步决策最优特征子集。新颖的分组多基因交叉技术保留了基因小组中的信息,而且允许后代继承更多的来自染色体的遗传信息。该算法促进可行解集中的高质量染色体信息交换,提高了解空间的搜索能力。实验结果说明：改进GA-SVM不仅可决策出与疾病相关的重要特征变量、优化SVM参数,而且可提升分类性能。与前馈BP神经网络及自适应模糊推理系统两种学习算法的比较表明,改进GA-SVM具有更好地表现。     

基于人工神经网络的叶脉信息提取--植物活体机器识别研究I

叶片的识别是识别植物的重要组成部分,特别在野外识别植物活体尤其重要.叶脉的脉序是植物的内在特征,包含有重要的遗传信息.但由于叶脉本身的多样性,利用单一特征的图像处理方法难以有效地提取叶脉.为了充分利用图像的信息,本文提出了一种基于人工神经网络的叶脉提取方法.该方法利用边缘梯度、局部对比度和邻域统计特征等10个参数来描述像素的邻域特征,并将其作为神经网络的输入层.实验结果表明,与传统方法相比,经过训练的神经网络能够更准确地提取叶脉图像,为进一步的叶片识别打下了良好的基础.     

基于人工神经网络的叶脉信息提取——植物活体机器识别研究Ⅰ

叶片的识别是识别植物的重要组成部分,特别在野外识别植物活体尤其重要。叶脉的脉序是植物的内在特征,包含有重要的遗传信息。但由于叶脉本身的多样性,利用单一特征的图像处理方法难以有效地提取叶脉。为了充分利用图像的信息,本文提出了一种基于人工神经网络的叶脉提取方法。该方法利用边缘梯度、局部对比度和邻域统计特征等10个参数来描述像素的邻域特征,并将其作为神经网络的输入层。实验结果表明,与传统方法相比,经过训练的神经网络能够更准确地提取叶脉图像,为进一步的叶片识别打下了良好的基础。     

Computerized morphometric discrimination between normal and tumoral cells in oral smears

The oral exfoliative cytology allows a quick and fairly accurate assessment of suspicious lesions of the oral cavity. Within this context, our paper proposes a quantitative approach, focusing on the construction of a classifier for detecting the presence of the tumoral cells on oral smears. The design of the classifier relies on a detailed computerized analysis of the individual morphometric features exhibited by two large known populations of normal and tumoral cells, respectively; the digital image processing was performed in the Zeiss KS400 environment. The classifier was implemented as a neural network with step activation function, whose parameters were obtained from an adequate training, based on the nuclear and cytoplasmic areas of the cells belonging to the two populations. Our procedure based on this classifier was meant to operate by identifying the tumoral or normal nature of any cell randomly selected from a smear. To identify the nature of an arbitrary cell, its nuclear and cytoplasmic areas are presented at the input of the classifier. The classification procedure was tested on several smears, and the results coincided with the pathological diagnosis in all the considered cases. The performances of our approach are discussed in comparison with other analytical methods previously reported in oral exfoliative cytology. These discussions emphasize the role of numerical information exploited for the classifier design, concluding that the individual morphometric features are more meaningful than the global characterization of smears by mean values.     

不同糖代谢冠心病患者的糖化血红蛋白水平与冠状动脉病变的关系

目的：研究不同糖代谢冠心病患者的糖化血红蛋白（HbA1c）水平与和冠状动脉病变的关系。方法：选取2013 年5 月到2014 年5 月我院收治的冠心病患者100 例,分为糖代谢正常组、异常组和糖尿病组。分析三组患者的HbA1c 水平、冠状动脉狭窄程度 及冠状动脉病变指数之间的关系和冠状动脉病变的危险因素。结果：三组患者的冠状动脉狭窄程度、冠状动脉病变支数、空腹血 糖（FPG）、餐后2 小时血糖（2hPG）、HbA1c 和三酰甘油（TG）水平比较,差异具有统计学意义（P<0.05）;HbA1c 水平与冠状动脉狭 窄程度呈正相关（P<0.05）;Logistic 结果显示年龄、性别、高血压、HbA1c、FPG、总胆固醇（TG）和高密度脂蛋白胆固醇（HDL-C）是 冠状动脉病变的危险因素（P<0.05）。结论：HbA1c 水平和冠状动脉病变具有相关性,是影响冠状动脉病变的重要危险因素。     

Thallium 201 Scintigraphy

The radioactive isotope thallium 201 behaves physiologically as a potassium analog, and when injected intravenously accumulates rapidly within the cells of many organs. Uptake of the isotope reflects both regional perfusion and sodium-potassium pump activity. The radionuclide emits 80 keV x-rays which are suitable for scintillation camera imaging.The main clinical application of ²⁰¹TI scintigraphy has been in myocardial imaging. Abnormal uptake of the isotope results in a cold spot on the myocardial image. In patients with coronary artery disease, the differentiation of ischemic and infarcted myocardium is made by comparing images obtained after injecting the radionuclide at the peak of a maximal exercise test with those obtained after injection at rest. Abnormalities due to ischemia usually are seen only on the stress image whereas fixed defects in both rest and stress studies usually indicate areas of infarction or scarring. Some investigators believe that redistribution images obtained four to six hours after stress injection (without administering further ²⁰¹TI) give the same information as a separate rest study. The sensitivity of stress imaging for detecting significant coronary disease is of the order of 80 percent to 95 percent, though computer processing of the images may be necessary to achieve the higher figure. The prediction of the extent of coronary disease from ²⁰¹TI images is less reliable. An abnormal ²⁰¹TI image is not entirely specific for coronary artery disease and the likelihood of an abnormal image being due to this diagnosis varies according to the clinical circumstances.The main clinical value of ²⁰¹TI myocardial imaging is likely to be in the noninvasive screening of patients with atypical chest pain or with ambiguous findings on stress electrocardiographic tests. It has also proved useful in studying patients with variant angina or following a coronary bypass operation. It is doubtful whether the technique is clinically helpful in most patients with suspected or established acute myocardial infarction.Imaging of organs other than the heart with ²⁰¹TI has received much less attention but has been reported in patients with peripheral vascular disease and various primary and secondary neoplasms.     

Using a neural network to identify potential HLA-DR1 binding sites within proteins

The presentation by antigen-presenting cells of immunodominant peptide segments in association with major histocompatibility complex (MHC) encoded proteins is fundamental to the efficacy of a specific immune response. One approach used to identify immunodominant segments within proteins has involved the development of predictive algorithms which utilize amino acid sequence data to identify structural characteristics or motifs associated with in vivo antigenicity. The parallel-computing technique termed ‘neural networking’ has recently been shown to be remarkably efficient at addressing the problem of pattern recognition and can be applied to predict protein secondary structure attributes directly from amino acid sequence data. In order to examine the potential of a neural network to generalize peptide structural feature related to binding within class II MHC-encoded proteins, we have trained a neural network to determine whether or not any given amino acid of a protein is part of a peptide segment capable of binding to HLA-DR1. We report that a neural network trained on a data base consisting of peptide segments known to bind to HLA-DR1 is able to generalize features relating to HLA-DR1-binding capacity (r = 0.17 and p = 0.0001).     

Chest pain in women: clinical,investigative, and prognostic features.

OBJECTIVE--To characterise clinical, investigative, and prognostic features of women referred with chest pain who subsequently underwent coronary angiography. DESIGN--Analysis of all women with angina referred to one consultant during 1987-91 who subsequently underwent coronary angiography, with follow up to present day. SETTING--Cardiothoracic centre. SUBJECTS--Women with normal coronary arteries; women with coronary artery disease shown on angiography; men with coronary artery disease matched for age; men referred with chest pain during the same period subsequently found to have normal coronary arteries. MAIN OUTCOME MEASURES--Risk factor analysis; results of exercise testing and coronary angiography; intervention; morbidity and mortality. RESULTS--Women comprised 23% (202/886) of patients referred with chest pain who subsequently underwent angiography. 83/202 women had normal coronary angiograms compared with 55/684 men (41% v 8%, P < 0.01). Diabetes mellitus was the only risk factor more frequently encountered in women with coronary artery disease (P = 0.001). The specificity and positive predictive value of exercise testing before angiography were significantly lower in women than men (71% v 93%, P < 0.001 and 76% v 95%, P < 0.001, respectively). Revascularisation procedures were as common in women with coronary artery disease as in men (81 (68%) v 70 (59%)), and there was no difference in event rate during follow up. Many patients with normal coronary arteries, irrespective of sex, had symptoms during follow up (61 (73%) women, 36 (65%) men) and continued to take antianginal drugs (27 (33%) women, 14 (28%) men); 14 (17%) women and six (11%) men required hospital readmission for severe symptoms. CONCLUSIONS--In this series, although women comprised the minority of patients referred with chest pain, a diagnosis of normal coronary arteries was five times more common in women than men. Risk factor analysis and exercise testing were of limited value in predicting coronary artery disease in women. There was no sex bias regarding revascularisation procedures, and outcome was similar. A diagnosis of non-cardiac chest pain in patients with normal coronary arteries was of little benefit to the patient with regard to morbidity.     

A convolutional neural network to recognize Chagas disease vectors using mobile phone images

There are several identification tools that can assist researchers, technicians and the community in the recognition of Chagas vector insects (triatomines), from other insects with similar morphologies. They involve using dichotomous keys, field guides, expert knowledge or, in more recent approaches, through the classification by a neural network of high quality photographs taken in standardized conditions. The aim of this research was to develop a deep neural network to recognize triatomines (insects associated with vectorial transmission of Chagas disease) directly from photos taken with any commonly available mobile device, without any other specialized equipment. To overcome the shortcomings of taking images using specific instruments and a controlled environment an innovative machine-learning approach was used: Fastai with Pytorch, a combination of open-source software for deep learning. The Convolutional Neural Network (CNN) was trained with triatomine photos, reaching a correct identification in 94.3% of the cases. Results were validated using photos sent by citizen scientists from the GeoVin project, resulting in 91.4% of correct identification of triatomines. The CNN provides a lightweight, robust method that even works with blurred images, poor lighting and even with the presence of other subjects and objects in the same frame. Future steps include the inclusion of the CNN into the framework of the GeoVin science project, which will also allow to further train the network using the photos sent by the citizen scientists. This would allow the participation of the community in the identification and monitoring of the vector insects, particularly in regions where government-led monitoring programmes are not frequent due to their low accessibility and high costs.     

Discriminating lysosomal membrane protein types using dynamic neural network

This work presents a dynamic artificial neural network methodology, which classifies the proteins into their classes from their sequences alone: the lysosomal membrane protein classes and the various other membranes protein classes. In this paper, neural networks-based lysosomal-associated membrane protein type prediction system is proposed. Different protein sequence representations are fused to extract the features of a protein sequence, which includes seven feature sets; amino acid (AA) composition, sequence length, hydrophobic group, electronic group, sum of hydrophobicity, R-group, and dipeptide composition. To reduce the dimensionality of the large feature vector, we applied the principal component analysis. The probabilistic neural network, generalized regression neural network, and Elman regression neural network (RNN) are used as classifiers and compared with layer recurrent network (LRN), a dynamic network. The dynamic networks have memory, i.e. its output depends not only on the input but the previous outputs also. Thus, the accuracy of LRN classifier among all other artificial neural networks comes out to be the highest. The overall accuracy of jackknife cross-validation is 93.2% for the data-set. These predicted results suggest that the method can be effectively applied to discriminate lysosomal associated membrane proteins from other membrane proteins (Type-I, Outer membrane proteins, GPI-Anchored) and Globular proteins, and it also indicates that the protein sequence representation can better reflect the core feature of membrane proteins than the classical AA composition.