Search

This study presents a comprehensive survey on mixed impulse and Gaussian denoising filters which are applied to an image in order to gauge the effects of this type of noise combination and to then determine optimal ways that can overcome such effects. The random noise model considered in this survey is the combined effect of impulse (salt and pepper) and Gaussian noise. After describing the noise models, the denoising filters which are applied to the images are classified and explained according to their design structure, the type of filters they use, the noise level they could overcome, and the limitations they face. This survey covers all related denoising methods and provides an assessment of the strengths and practical limitations of the different classes of denoising filters.

This study aims to determine whether newly introduced biomarkers Visinin-like protein-1 (VILIP-1), chitinase-3-like protein 1 (YKL-40), synaptosomal-associated protein 25 (SNAP-25), and neurogranin (NG) in cerebrospinal fluid are useful in evaluating the asymptomatic and early symptomatic stages of Alzheimer's disease (AD). It further aims to shed new insight into the differences between stable subjects and those who progress to AD by associating cerebrospinal fluid (CSF) biomarkers and specific magnetic resonance imaging (MRI) regions with disease progression, more deeply exploring how such biomarkers relate to AD pathology.We examined baseline and longitudinal changes over a 7-year span and the longitudinal interactions between CSF and MRI biomarkers for subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). We stratified all CSF (140) and MRI (525) cohort participants into five diagnostic groups (including converters) further dichotomized by CSF amyloid beta (Aβ) status. Linear mixed models were used to compare within-person rates of change across diagnostic groups and to evaluate the association of CSF biomarkers as predictors of magnetic resonance imaging (MRI) biomarkers. CSF biomarkers and disease-prone MRI regions are assessed for CSF proteins levels and brain structural changes.VILIP-1 and SNAP-25 displayed within-person increments in early symptomatic, amyloid-positive groups. CSF amyloid-positive (Aβ+) subjects showed elevated baseline levels of total tau (tTau), phospho-tau181 (pTau), VILIP-1, and NG. YKL-40, SNAP-25, and NG are positively intercorrelated. Aβ+ subjects showed negative MRI biomarker changes. YKL-40, tTau, pTau, and VILIP-1 are longitudinally associated with MRI biomarkers atrophy.Converters (CNc, MCIc) highlight the evolution of biomarkers during the disease progression. Results show that underlying amyloid pathology is associated with accelerated cognitive impairment. CSF levels of Aβ42, pTau, tTau, VILIP-1, and SNAP-25 show utility to discriminate between mild cognitive impairment (MCI) converter and control subjects (CN). Higher levels of YKL-40 in the Aβ+ group were longitudinally associated with declines in temporal pole and entorhinal thickness. Increased levels of tTau, pTau, and VILIP-1 in the Aβ+ groups were longitudinally associated with declines in hippocampal volume. These CSF biomarkers should be used in assessing the characterization of the AD progression.

Background Regional cortical thickness (rCTh) among cognitively normal (CN) adults (rCThCN) varies greatly between brain regions, as does the vulnerability to neurodegeneration. Objective The goal of this study was to: 1) rank order rCThCN for various brain regions, and 2) explore their vulnerability to neurodegeneration in Alzheimer's disease (AD) within these brain regions. Methods The relationship between rCTh among the CN group (rCThCN) and the percent difference in CTh (% CThDiff) in each region between the CN group and AD patients was examined. Pearson correlation analysis was performed accounting for amyloid-β (Aβ) protein and APOE genotype using 210 age, gender, and APOE matched CN (n = 105, age range: 56-90) and AD (n = 105, age range: 56-90) ADNI participants. Results Strong positive correlations were observed between rCThCN and % CThDiff accounting for Aβ deposition and APOE status. Regions, such as the entorhinal cortex, which had the greatest CTh in the CN state, were also the regions which had the greatest % CThDiff. Conclusions Regions with the greatest CTh at the CN stage are found to aggregate in disease prone regions of AD, namely in the medial temporal lobe, including the temporal pole, ERC, parahippocampal gyrus, fusiform and the middle and inferior temporal gyrus. Although rCTh has been found to vary considerably across the different regions of the brain, our results indicate that regions with the greatest CTh at the CN stage are actually regions which have been found to be most vulnerable to neurodegeneration in AD.

We propose a novel pipeline for the real-time detection of myocardial infarction from a single heartbeat of a 12-lead electrocardiograms. We do so by merging a real-time R-spike detection algorithm with a deep learning Long-Short Term Memory (LSTM) network-based classifier. A comparative assessment of the classification performance of the resulting system is performed and provided. The proposed algorithm achieves an inter-patient classification accuracy of 95.76% (with a 95% Confidence Interval (CI) of ±2.4%), a recall of 96.67% (±2.4% 95% CI), specificity of 93.64% (±5.7% 95% CI), and the average J-Score is 90.31% (±6.2% 95% CI). These state-of-the-art myocardial infarction detection metrics are extremely promising and could pave the wave for the early detection of myocardial infarctions. This high accuracy is achieved with a processing time of 40 milliseconds, which is most appropriate for online classification as the time between fast heartbeats is around 300 milliseconds.

This study introduces a new multimodal deep regression method to predict cognitive test score in a 5-year longitudinal study on Alzheimer’s disease (AD). The proposed model takes advantage of multimodal data that includes cerebrospinal fluid (CSF) levels of tau and beta-amyloid, structural measures from magnetic resonance imaging (MRI), functional and metabolic measures from positron emission tomography (PET), and cognitive scores from neuropsychological tests (Cog), all with the aim of achieving highly accurate predictions of future Mini-Mental State Examination (MMSE) test scores up to five years after baseline biomarker collection. A novel data augmentation technique is leveraged to increase the numbers of training samples without relying on synthetic data. With the proposed method, the best and most encompassing regressor is shown to achieve better than state-of-the-art correlations of 85.07%(SD=1.59) for 6 months in the future, 87.39% (SD =1.48) for 12 months, 84.78% (SD=2.66) for 18 months, 85.13% (SD=2.19) for 24 months, 81.15% (SD=5.48) for 30 months, 81.17% (SD=4.44) for 36 months, 79.25% (SD=5.85) for 42 months, 78.98% (SD=5.79) for 48 months, 78.93%(SD=5.76) for 54 months, and 74.96% (SD=7.54) for 60 months.

This paper introduces a new image smoothing filter based on a feed-forward convolutional neural network (CNN) in presence of impulse noise. This smoothing filter integrates a very deep architecture, a regularization method, and a batch normalization process. This fully integrated approach yields an effectively denoised and smoothed image yielding a high similarity measure with the original noise free image. Specific structural metrics are used to assess the denoising process and how effective was the removal of the impulse noise. This CNN model can also deal with other noise levels not seen during the training phase. The proposed CNN model is constructed through a 20-layer network using 400 images from the Berkeley Segmentation Dataset (BSD) in the training phase. Results are obtained using the standard testing set of 8 natural images not seen in the training phase. The merits of this proposed method are weighed in terms of high similarity measure and structural metrics that conform to the original image and compare favorably to the different results obtained using state-of-art denoising filters.

This study proposes a novel real-time frequency-independent myocardial infarction detector for Lead II electrocardiograms. The underlying Deep-LSTM network is trained using the PTB-XL database, the largest to date publicly available electrocardiography dataset, and is tested over the same and the older PTB database. By testing the model over distinct datasets, collected under different conditions and from different patients, a more realistic measure of the performance can be gauged from the deployed system. The detector is trained over 3589 myocardial infarction (MI) patients and 7115 healthy controls (HC) while it is evaluated on 1076 MIs and 1840 HCs. The proposed algorithm, achieved an accuracy of 77.12%, recall/sensitivity of 75.85%, and a specificity of 83.02% over the entire PTB database; 85.07%, 81.54%, 87.31% over the PTB-XL validation set (fold 9), and 84.17%, 78.37%, 87.55% over the PTB-XL test set (fold 10). The model also achieves stable performance metrics over the frequency range of 202 Hz to 2.8 kHz. The processing time is dependent on the sampling frequency, ranging from 130 ms at 202 Hz to 1.8 s at 2.8 kHz. Such outcome is within the time required for real-time processing (less than 300 ms for fast heartbeats), between 202 Hz and 500 Hz making the algorithm practically real-time. Therefore, the proposed MI detector could be readily deployed onto existing wearable and/or portable devices and test instruments; potentially having significant societal and clinical impact in the lives of patients at risk for myocardial infarction.

This study proposes a novel Long Short-Term Memory Neural Network (LSTM) architecture for the diagnosis of myocardial infarctions from individual heartbeats of single-lead electrocardiograms (ECGs). The proposed model is trained using an unbiased patient split approach and validated using 10-fold cross-validation over 148 myocardial infarction and 52 Healthy Control patients from the Physikalisch-Technische Bundesanstalt diagnostic ECG Database to generate an inter-patient classifier. We further demonstrate why special care must be taken when generating the training and testing datasets by exploring the effects of various data-split techniques that could mask the occurrence of overfitting and produce misleadingly high testing metrics of the model's performance. A thorough assessment of these results is provided using several standard metrics for different data split methods to show their tendency to overfitting, data leakage, and bias introduced from previously seen heart beats during the training phase. The design achieves near real-time diagnosis of 40 ms while providing an accuracy of 89.56% (with a 95% Confidence Interval (CI) of ± 2.79%), recall/sensitivity of 91.88% ( ± 3.13% 95%CI), and a specificity of 80.81% ( ± 9.62% 95%CI). The fast processing makes the model readily deployable on currently existing mobile devices and testing instruments. The achieved performance makes the proposed method a new research direction for attaining real-time and unbiased diagnosis. While, the modular architectural design of the LSTM network structure, which is amenable for the inclusion of other ECG leads, could serve as a platform for early detection of myocardial infarction and for the planning of early treatment(s).

Predicting future cognitive status from current and past scores on objective cognitive tests and imaging measures would be useful in diagnosing Alzheimer's disease (AD) and to assess the progression of the disease. We used stochastic gradient boosting of decision trees on over 1,141 individuals whose clinical and imaging studies were available from the Alzheimer's disease Neuroimaging Initiative (ADNI) database. The proposed method outperformed all the algorithms tested in all five cognitive scores (MMSE, CDRS, RAVLT, ADAS11 and ADAS13), outranking all other state-of-the-art algorithms in terms of both Pearson's correlation coefficient and root mean square error. All correlation measures between predicted and actual cognitive scores were higher than 0.9. Given the large number of subjects included in this study, all correlations were statistically significant. For the subset of MCI patients, we compared the proposed method with state of the art algorithms. Here, the proposed method outperformed all the algorithms tested in all five cognitive scores.

Electrocardiograms (EKGs) are the most common diagnosis tools used for the detection and diagnosis of cardiovascular diseases and abnormalities. In this paper, we proposed a method that uses independent component analysis (ICA) for the real-time detection of the most distinct component of the cardiac electrical signal, the R-peak. This approach will open the door to real-time analysis and decomposition of the complete cardiac signal and the online diagnosis of cardiac abnormalities. The potential benefits of such real-time implementation are far reaching, from the online diagnosis of diseases and abnormalities to its use in tracking heart functioning during the testing and development of cutting edge research and treatments, such as transcranial magnetic stimulation (TMS).

Nowadays, background model does not have any robust solution and constitutes one of the main problems in surveillance systems. Researchers are working in several approaches in order to get better background pixel models. This is a previous step to apply the background subtraction technique and results are not as good as expected. We concentrate our efforts on the second step for segmentation of moving objects and we propose background division to substitute background subtraction technique.This approach allows us to obtain clusters with lower intraclass variability and higher inter-class variability, this diminishes confusion between background and foreground, pixels. We compared results using our background division approach versus wallflowers algorithm as the baseline to compare.