共查询到20条相似文献，搜索用时 31 毫秒
1.
Aim
To elucidate the hemodynamics of the uterine artery myomas by use of Doppler ultrasound and biomagnetic measurements.Method
Twenty-four women were included in the study. Sixteen of them were characterised with large myomas whereas 8 of them with small ones. Biomagnetic signals of uterine arteries myomas were recorded and analyzed with Fourier analysis. The biomagnetic signals were distributed according to spectral amplitudes as high (140–300 ft/√Hz), low (50–110 ft/√Hz) and borderline (111–139 ft/√Hz). Uterine artery waveform measurements were evaluated by use of Pulsatility Index (PI) (normal value PI < 1.45).Results
There was a statistically significant difference between large and small myomas concerning the waveform amplitudes (P < 0.0005) and the PI index (P < 0.0005). Specifically, we noticed high biomagnetic amplitudes in most large myomas (93.75 %) and low biomagnetic amplitudes in most small ones (87.5 %).Conclusion
It is suggested that the biomagnetic recordings of uterine artery myomas could be a valuable modality in the estimation of the circulation of blood cells justifying the findings of Doppler velocimetry examination.2.
Background
Identification of phosphorylation sites by computational methods is becoming increasingly important because it reduces labor-intensive and costly experiments and can improve our understanding of the common properties and underlying mechanisms of protein phosphorylation.Methods
A multitask learning framework for learning four kinase families simultaneously, instead of studying each kinase family of phosphorylation sites separately, is presented in the study. The framework includes two multitask classification methods: the Multi-Task Least Squares Support Vector Machines (MTLS-SVMs) and the Multi-Task Feature Selection (MT-Feat3).Results
Using the multitask learning framework, we successfully identify 18 common features shared by four kinase families of phosphorylation sites. The reliability of selected features is demonstrated by the consistent performance in two multi-task learning methods.Conclusions
The selected features can be used to build efficient multitask classifiers with good performance, suggesting they are important to protein phosphorylation across 4 kinase families.3.
Background
Extracting features from the colonoscopic images is essential for getting the features, which characterizes the properties of the colon. The features are employed in the computer-assisted diagnosis of colonoscopic images to assist the physician in detecting the colon status.Methods
Endoscopic images contain rich texture and color information. Novel schemes are developed to extract new texture features from the texture spectra in the chromatic and achromatic domains, and color features for a selected region of interest from each color component histogram of the colonoscopic images. These features are reduced in size using Principal Component Analysis (PCA) and are evaluated using Backpropagation Neural Network (BPNN).Results
Features extracted from endoscopic images were tested to classify the colon status as either normal or abnormal. The classification results obtained show the features' capability for classifying the colon's status. The average classification accuracy, which is using hybrid of the texture and color features with PCA (τ = 1%), is 97.72%. It is higher than the average classification accuracy using only texture (96.96%, τ = 1%) or color (90.52%, τ = 1%) features.Conclusion
In conclusion, novel methods for extracting new texture- and color-based features from the colonoscopic images to classify the colon status have been proposed. A new approach using PCA in conjunction with BPNN for evaluating the features has also been proposed. The preliminary test results support the feasibility of the proposed method.4.
P. J. P. M. Cuijpers G. Bookelman W. Kicken W. de Vries A. P. M. Gorgels 《Netherlands heart journal》2016,24(7-8):456-461
Background
Integrating cardiopulmonary resuscitation (CPR) training in secondary schools will increase the number of potential CPR providers. However, currently too few certified instructors are available for this purpose. Training medical students and physical education student teachers to become CPR instructors could decrease this shortage.Aim
Examine whether medical students and physical education student teachers can provide CPR training for secondary school pupils as well as (i.?e., non-inferior to) registered nurses.Methods
A total of 144 secondary school pupils were randomly assigned to CPR training by a registered nurse (n = 12), a medical student (n = 17) or a physical education student teacher (n = 15). CPR performance was assessed after training and after eight weeks in a simulated cardiac arrest scenario on a resuscitation manikin, using manikin software and video recordings.Results
No significant differences were found between the groups on the overall Cardiff Test scores and the correctness of the CPR techniques during the post-training and retention test. All pupils showed sufficient CPR competence, even after eight weeks.Conclusion
Training by medical students or physical education student teachers is non-inferior to training by a registered nurse, suggesting that school teachers, student teachers and medical students can be recruited for CPR training in secondary schools.5.
Background
The purpose of this study is to explore the potential of phase contrast imaging to detect fibrotic progress in its early stage; to investigate the feasibility of texture features for quantified diagnosis of liver fibrosis; and to evaluate the performance of back propagation (BP) neural net classifier for characterization and classification of liver fibrosis.Methods
Fibrous mouse liver samples were imaged by X-ray phase contrast imaging, nine texture measures based on gray-level co-occurrence matrix were calculated and the feasibility of texture features in the characterization and discrimination of liver fibrosis at early stages was investigated. Furthermore, 36 or 18 features were applied to the input of BP classifier; the classification performance was evaluated using receiver operating characteristic curve.Results
The phase contrast images displayed a vary degree of texture pattern from normal to severe fibrosis stages. The BP classifier could distinguish liver fibrosis among normal, mild, moderate and severe stages; the average accuracy was 95.1% for 36 features, and 91.1% for 18 features.Conclusion
The study shows that early stages of liver fibrosis can be discriminated by the morphological features on the phase contrast images. BP network model based on combination of texture features is demonstrated effective for staging liver fibrosis.6.
Andreas Mueller Gian Candrian Juri D Kropotov Valery A Ponomarev Gian-Marco Baschera 《Nonlinear biomedical physics》2010,4(Z1):S1
Background
In the context of sensory and cognitive-processing deficits in ADHD patients, there is considerable evidence of altered event related potentials (ERP). Most of the studies, however, were done on ADHD children. Using the independent component analysis (ICA) method, ERPs can be decomposed into functionally different components. Using the classification method of support vector machine, this study investigated whether features of independent ERP components can be used for discrimination of ADHD adults from healthy subjects.Methods
Two groups of age- and sex-matched adults (74 ADHD, 74 controls) performed a visual two stimulus GO/NOGO task. ERP responses were decomposed into independent components by means of ICA. A feature selection algorithm defined a set of independent component features which was entered into a support vector machine.Results
The feature set consisted of five latency measures in specific time windows, which were collected from four different independent components. The independent components involved were a novelty component, a sensory related and two executive function related components. Using a 10-fold cross-validation approach, classification accuracy was 92%.Conclusions
This study was a first attempt to classify ADHD adults by means of support vector machine which indicates that classification by means of non-linear methods is feasible in the context of clinical groups. Further, independent ERP components have been shown to provide features that can be used for characterizing clinical populations.7.
Marie Krogh Nielsen Sven Magnus Hector Kelly Allen Yousif Subhi Torben Lykke Sørensen 《Immunity & ageing : I & A》2017,14(1):18
Background
Neutrophil dysfunction plays a key role in the development of diseases characterized by inflammation and angiogenesis. Here, we studied the systemic expression of neutrophil markers reflecting activation, adhesion, and resolution of inflammation in patients with neovascular age-related macular degeneration (AMD).Results
This was a prospective case-control study of patients with neovascular AMD and age-matched healthy control individuals. Patients were recruited from an outpatient program, and control individuals were recruited amongst patients’ relatives. Current smokers and individuals with either active immune-disease or ongoing cancer were not included, as these factors are known to affect neutrophil function. Fresh-drawn venous blood was processed for flow cytometric analysis of neutrophil markers. We determined percentages of positive cells and compared expression levels using fluorescence intensity measures. We found conditional differences on marker expression between patients with neovascular AMD (n = 29) and controls (n = 28): no differences were found when looking broadly, but several differences emerged when focusing on non-smokers. Here, patients with neovascular AMD had increased expression of the activity marker cluster of differentiation (CD) 66b (P = 0.003; Mann-Whitney U test), decreased expression of adhesion marker CD162 (P = 0.044; Mann-Whitney U test), and lower expression of the resolution of inflammation marker C-X-C chemokine receptor 2 (P = 0.044; Mann-Whitney U test).Conclusions
We present novel evidence suggesting that the activity of circulating neutrophils, sensitive to smoking, may differ in patients with neovascular AMD.8.
Gianluca Coppola Antonio Currà Cherubino Di Lorenzo Vincenzo Parisi Manuela Gorini Simona Liliana Sava Jean Schoenen Francesco Pierelli 《BMC neurology》2010,10(1):126
Background
Medication-overuse headache (MOH) is a frequent, disabling disorder. Despite a controversial pathophysiology convincing evidence attributes a pivotal role to central sensitization. Most patients with MOH initially have episodic migraine without aura (MOA) characterized interictally by an absent amplitude decrease in cortical evoked potentials to repetitive stimuli (habituation deficit), despite a normal initial amplitude (lack of sensitization). Whether central sensitization alters this electrophysiological profile is unknown. We therefore sought differences in somatosensory evoked potential (SEP) sensitization and habituation in patients with MOH and episodic MOA.Methods
We recorded median-nerve SEPs (3 blocks of 100 sweeps) in 29 patients with MOH, 64 with MOA and 42 controls. Episodic migraineurs were studied during and between attacks. We measured N20-P25 amplitudes from 3 blocks of 100 sweeps, and assessed sensitization from block 1 amplitude, and habituation from amplitude changes between the 3 sequential blocks.Results
In episodic migraineurs, interictal SEP amplitudes were normal in block 1, but thereafter failed to habituate. Ictal SEP amplitudes increased in block 1, then habituated normally. Patients with MOH had larger-amplitude block 1 SEPs than controls, and also lacked SEP habituation. SEP amplitudes were smaller in triptan overusers than in patients overusing nonsteroidal anti-inflammatory drugs (NSAIDs) or both medications combined, lowest in patients with the longest migraine history, and highest in those with the longest-lasting headache chronification.Conclusions
In patients with MOH, especially those overusing NSAIDs, the somatosensory cortex becomes increasingly sensitized. Sensory sensitization might add to the behavioral sensitization that favors compulsive drug intake, and may reflect drug-induced changes in central serotoninergic transmission.9.
Background
The Receiver Operator Characteristic (ROC) curve is well-known in evaluating classification performance in biomedical field. Owing to its superiority in dealing with imbalanced and cost-sensitive data, the ROC curve has been exploited as a popular metric to evaluate and find out disease-related genes (features). The existing ROC-based feature selection approaches are simple and effective in evaluating individual features. However, these approaches may fail to find real target feature subset due to their lack of effective means to reduce the redundancy between features, which is essential in machine learning.Results
In this paper, we propose to assess feature complementarity by a trick of measuring the distances between the misclassified instances and their nearest misses on the dimensions of pairwise features. If a misclassified instance and its nearest miss on one feature dimension are far apart on another feature dimension, the two features are regarded as complementary to each other. Subsequently, we propose a novel filter feature selection approach on the basis of the ROC analysis. The new approach employs an efficient heuristic search strategy to select optimal features with highest complementarities. The experimental results on a broad range of microarray data sets validate that the classifiers built on the feature subset selected by our approach can get the minimal balanced error rate with a small amount of significant features.Conclusions
Compared with other ROC-based feature selection approaches, our new approach can select fewer features and effectively improve the classification performance.10.
Background
To determine the correlation of cyclin-dependent kinase inhibitor 1B (p27) expression with clinicopathologic features in nasopharyngeal carcinoma (NPC), including patient prognosis.Methods
Real-time PCR and immunohistochemistry were used to examine the mRNA and protein expressions of p27 in NPC and nasopharyngeal tissues. The relationship of p27 expression levels with clinical features and prognosis of NPC patients was analyzed.Results
The expression level of p27 mRNA was markedly lower in NPC tissues than that in the nasopharyngeal tissues (P?=?0.0006). Specific p27 protein staining by immunohistochemistry was found in the nuclei and cytoplasm of nasopharyngeal and malignant epithelial cells but decreased expression was observed in NPC samples compared to normal epithelium samples (P?=?0.002). In addition, low levels of p27 protein were inversely correlated with the status of T classification (p?=?0.002) and clinical stage (p?=?0.019) of NPC patients. Patients with lower p27 expression had a significantly shorter overall survival time than did patients with high p27 expression. Multivariate analysis suggested that the level of p27 expression was not an independent prognostic indicator (p?=?0.682) for NPC survival.Conclusion
Low level of p27 expression is a potential unfavorable prognostic factor for patients with NPC.Virtual slides
The virtual slide (s) for this article can be found here: http://www.diagnosticpathology.diagnomx.eu/vs/1915282782109343.11.
Joshua M. Mitchell Robert M. Flight Qing Jun Wang Richard M. Higashi Teresa W.-M. Fan Andrew N. Lane Hunter N. B. Moseley 《Metabolomics : Official journal of the Metabolomic Society》2018,14(10):125
Introduction
Direct injection Fourier-transform mass spectrometry (FT-MS) allows for the high-throughput and high-resolution detection of thousands of metabolite-associated isotopologues. However, spectral artifacts can generate large numbers of spectral features (peaks) that do not correspond to known compounds. Misassignment of these artifactual features creates interpretive errors and limits our ability to discern the role of representative features within living systems.Objectives
Our goal is to develop rigorous methods that identify and handle spectral artifacts within the context of high-throughput FT-MS-based metabolomics studies.Results
We observed three types of artifacts unique to FT-MS that we named high peak density (HPD) sites: fuzzy sites, ringing and partial ringing. While ringing artifacts are well-known, fuzzy sites and partial ringing have not been previously well-characterized in the literature. We developed new computational methods based on comparisons of peak density within a spectrum to identify regions of spectra with fuzzy sites. We used these methods to identify and eliminate fuzzy site artifacts in an example dataset of paired cancer and non-cancer lung tissue samples and evaluated the impact of these artifacts on classification accuracy and robustness.Conclusion
Our methods robustly identified consistent fuzzy site artifacts in our FT-MS metabolomics spectral data. Without artifact identification and removal, 91.4% classification accuracy was achieved on an example lung cancer dataset; however, these classifiers rely heavily on artifactual features present in fuzzy sites. Proper removal of fuzzy site artifacts produces a more robust classifier based on non-artifactual features, with slightly improved accuracy of 92.4% in our example analysis.12.
Background
Microarray technology is often used to identify the genes that are differentially expressed between two biological conditions. On the other hand, since microarray datasets contain a small number of samples and a large number of genes, it is usually desirable to identify small gene subsets with distinct pattern between sample classes. Such gene subsets are highly discriminative in phenotype classification because of their tightly coupling features. Unfortunately, such identified classifiers usually tend to have poor generalization properties on the test samples due to overfitting problem.Results
We propose a novel approach combining both supervised learning with unsupervised learning techniques to generate increasingly discriminative gene clusters in an iterative manner. Our experiments on both simulated and real datasets show that our method can produce a series of robust gene clusters with good classification performance compared with existing approaches.Conclusion
This backward approach for refining a series of highly discriminative gene clusters for classification purpose proves to be very consistent and stable when applied to various types of training samples.13.
Elif Erdem Ibrahim Inan Harbiyeli Hazal Boral Macit Ilkit Meltem Yagmur Reha Ersoz 《Mycopathologia》2018,183(3):521-527
Purpose
To evaluate the efficiency of corneal collagen cross-linking (CXL) in addition to topical voriconazole in cases with mycotic keratitis.Design
Retrospective case series in a tertiary university hospital.Participants
CXL was performed on 13 patients with mycotic keratitis who presented poor or no response to topical voriconazole treatment.Methods
The clinical features, symptoms, treatment results and complications were recorded retrospectively. The corneal infection was graded according to the depth of infection into the stroma (from grade 1 to grade 3). The visual analogue scale was used to calculate the pain score before and 2 days after surgery.Main Outcome Measures
Grade of the corneal infection.Results
Mean age of 13 patients (6 female and 7 male) was 42.4 ± 17.7 years (20–74 years). Fungus was demonstrated in culture (eight patients) or cytological examination (five patients). Seven of the 13 patients (54%) were healed with topical voriconazole and CXL adjuvant treatment in 26 ± 10 days (15–40 days). The remaining six patients did not respond to CXL treatment; they initially presented with higher grade ulcers. Pre- and post-operative pain score values were 8 ± 0.8 and 3.5 ± 1, respectively (p < 0.05).Conclusions
The current study suggests that adjunctive CXL treatment is effective in patients with small and superficial mycotic ulcers. These observations require further research by large randomized clinical trials.14.
15.
Shirin Najdi Ali Abdollahi Gharbali José Manuel Fonseca 《Biomedical engineering online》2017,16(1):78
Background
Nowadays, sleep quality is one of the most important measures of healthy life, especially considering the huge number of sleep-related disorders. Identifying sleep stages using polysomnographic (PSG) signals is the traditional way of assessing sleep quality. However, the manual process of sleep stage classification is time-consuming, subjective and costly. Therefore, in order to improve the accuracy and efficiency of the sleep stage classification, researchers have been trying to develop automatic classification algorithms. Automatic sleep stage classification mainly consists of three steps: pre-processing, feature extraction and classification. Since classification accuracy is deeply affected by the extracted features, a poor feature vector will adversely affect the classifier and eventually lead to low classification accuracy. Therefore, special attention should be given to the feature extraction and selection process.Methods
In this paper the performance of seven feature selection methods, as well as two feature rank aggregation methods, were compared. Pz-Oz EEG, horizontal EOG and submental chin EMG recordings of 22 healthy males and females were used. A comprehensive feature set including 49 features was extracted from these recordings. The extracted features are among the most common and effective features used in sleep stage classification from temporal, spectral, entropy-based and nonlinear categories. The feature selection methods were evaluated and compared using three criteria: classification accuracy, stability, and similarity.Results
Simulation results show that MRMR-MID achieves the highest classification performance while Fisher method provides the most stable ranking. In our simulations, the performance of the aggregation methods was in the average level, although they are known to generate more stable results and better accuracy.Conclusions
The Borda and RRA rank aggregation methods could not outperform significantly the conventional feature ranking methods. Among conventional methods, some of them slightly performed better than others, although the choice of a suitable technique is dependent on the computational complexity and accuracy requirements of the user.16.
Objective
To determine if there is any non-linearity in the biomagnetic recordings of uterine myomas and to find any differences that may be present in the mechanisms underlying their signal dynamics.Methods
Twenty-four women were included in the study. Sixteen of them were characterised with large myomas and 8 with small ones. Uterine artery waveform measurements were evaluated by use of Pulsatility Index (PI) (normal value PI<1.45).Results
Applying nonlinear analysis to the biomagnetic signals of the uterine myomas, we observed a clear saturation value for the group of large ones (mean = 11.35 ± 1.49) and no saturation for the small ones.Conclusion
The comparison of the saturation values in the biomagnetic recordings of large and small myomas may be a valuable tool in the evaluation of functional changes in their dynamic behavior.17.
Soo-Jin?Cho Kyung-Ho?Yu Mi?Sun?Oh San?Jung Ju-Hun?Lee Im-Seok?Koh Hee-Joon?Bae Yeonwook?Kang Byung-Chul?Lee
Background
The American Stroke Association/American Heart Association recommended the criteria for diagnosis of vascular cognitive impairment and memory impairment (MI) is a feature in the classification of vascular mild cognitive impairment (VaMCI). VaMCI patients with MI may differ in terms of infarct location or demographic features, so we evaluated the clinical characteristics associated with MI in patients with VaMCI.Methods
A prospective multicenter study enrolled 353 acute ischemic stroke patients who underwent evaluation using the Korean Vascular Cognitive Impairment Harmonization Standard Neuropsychological Protocol at three months after onset. The association between MI and demographic features, stroke risk factors, and infarct location was assessed.Results
VaMCI was diagnosed in 141 patients, and 58 (41.1%) exhibited MI. Proportions of men and of left side infarcts were higher in VaMCI with MI than those without (75.9 vs. 57.8%, P?=?0.03, 66.7 vs. 47%, P?=?0.02). Multiple logistic analyses revealed that male sex (odds ratio [OR] 3.07, 95% confidence interval [95% CI] 1.12-8.42), left-side infarcts (OR 3.14, 95% CI 1.37-7.20), and basal ganglia/internal capsule infarcts (OR 4.53, 95% CI 1.55-13.22) were associated with MI after adjusting other demographic variables, vascular risk factors, and subtypes of stroke.Conclusions
MI is associated with sex and infarct location in VaMCI patients.18.
Introduction
Sudden cardiac arrest (SCA) in athletes is an unexpected life-threatening event, which is often not recognised early and cardiopulmonary resuscitation (CPR) is not always initiated immediately. We describe key features to rapidly recognise non-traumatic SCA in athletes during sports activity.Methods
We reviewed videos and images of athletes suffering from non-traumatic SCA during sports activity. We searched Google images, Google videos and YouTube.com using the keywords ‘sudden cardiac death athlete’ and ‘resuscitation athlete’. We analysed (1) the athlete’s performance before syncope, (2) the athlete’s performance at the start of syncope, (3) the position of the body, and (4) the athlete’s facial expressions before CPR. We analysed our data by describing these four features to answer our research question.Results
We analysed the sequence of events in six well-known soccer players in whom a camera-witnessed non-traumatic SCA occurred during their athletic activity. All six athletes showed no changes before syncope. Four became unstable while standing and unexpectedly collapsed falling on their back. Two suddenly ‘dropped dead’ and fell face down. All six had their eyes wide open with a fixed gaze and fixed pupils.Conclusions
Sudden unexpected loss of consciousness in an athlete in action and a fixed gaze eye position are key features of SCA. Immediate cardiac massage should follow. The described features to immediately recognise SCA in athletes during sports activity should be taught to everyone involved in athletic activity leading to earlier recognition of SCA followed by earlier CPR.19.