Search

Background: Machine learning is a promising tool for biomarker-based diagnosis of Alzheimer’s disease (AD). Performing multimodal feature selection and studying the interaction between biological and clinical AD can help to improve the performance of the diagnosis models. Objective: This study aims to formulate a feature ranking metric based on the mutual information index to assess the relevance and redundancy of regional biomarkers and improve the AD classification accuracy. Methods: From the Alzheimer’s Disease Neuroimaging Initiative (ADNI), 722 participants with three modalities, including florbetapir-PET, flortaucipir-PET, and MRI, were studied. The multivariate mutual information metric was utilized to capture the redundancy and complementarity of the predictors and develop a feature ranking approach. This was followed by evaluating the capability of single-modal and multimodal biomarkers in predicting the cognitive stage. Results: Although amyloid-β deposition is an earlier event in the disease trajectory, tau PET with feature selection yielded a higher early-stage classification F1-score (65.4%) compared to amyloid-β PET (63.3%) and MRI (63.2%). The SVC multimodal scenario with feature selection improved the F1-score to 70.0% and 71.8% for the early and late-stage, respectively. When age and risk factors were included, the scores improved by 2 to 4%. The Amyloid-Tau-Neurodegeneration [AT(N)] framework helped to interpret the classification results for different biomarker categories. Conclusion: The results underscore the utility of a novel feature selection approach to reduce the dimensionality of multimodal datasets and enhance model performance. The AT(N) biomarker framework can help to explore the misclassified cases by revealing the relationship between neuropathological biomarkers and cognition.

Objective : This study demonstrates how functional connectivity (FC) patterns are affected in direct relation to the lobe that is mostly affected by seizures. Methods : The novel idea of penalized FC (pFC) maps is compared against standard FC maps in the four fundamental EEG frequency sub-bands. The FC measure between any two specific electrodes is scaled depending on the probability of true FC between them, and their power content with respect to the two electrodes of maximum power within each frequency sub-band. The algorithm is automated and introduces adaptive power penalization based on the power distribution of the different sub-bands. Results : The pFC maps were found to be more effective at suppressing the local connectivity in the lobes that are less affected by the interictal epileptiform discharges (IEDs). More precisely, given the least amount of power penalization, pFC maps of the theta sub-band reveal statistical significance in terms of increased local connectivity margin of the affected region as compared to the standard FC maps. However, they cannot be solely relied upon as other sub-bands could alternatively show high local connectivity across different patients within the region of interest. Conclusion : penalized functional connectivity maps intrinsically provide more information regarding the whole brain network in context to regions of interest where the active lobe is determined by the neurologists to contain the focal source. Significance : Findings suggest that (1) the significant sub-band varies from patient to patient while remaining relatively consistent within the IED segments of a same patient, and (2) the pFC maps have an advanced capability in terms of pinpointing to a region of interest of the active lobe, and as such can play a critical role in providing insight as to a region of interest where the 3D source might be located when solving the ill-posed inverse problem.

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.

Objective: Connectivity patterns of interictal epileptiform discharges are all subtle indicators of where the three-dimensional (3D) source of a seizure could be located. These specific patterns are explored in the recorded electroencephalogram (EEG) signals of 20 individuals diagnosed with focal epilepsy to assess how their functional brain maps could be affected by the 3D onset of a seizure. Methods: Functional connectivity maps, estimated by phase synchrony among EEG electrodes, were obtained by applying a data-driven recurrence-based method. This is augmented through a novel approach for selecting optimal parameters that produce connectivity matrices that are deemed significant for assessing epileptiform activity in context to the 3D source localization of seizure onset. These functional connectivity matrices were evaluated in different brain areas to gauge the regional effects of the 3D epileptic source. Results: Empirical evaluations indicate high synchronization in the temporal and frontal areas of the effected epileptic hemisphere, whereas strong links connect the irritated area to frontal and temporal lobes of the opposite hemisphere. Conclusion: Epileptic activity originating in the temporal or frontal areas is seen to affect these areas in both hemispheres. Significance: The results obtained express the dynamics of focal epilepsy in context to both the epileptogenic zone and the affected distant areas of the brain.

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.

With the advances in machine learning for the diagnosis of Alzheimer’s disease (AD), most studies have focused on either identifying the subject’s status through classification algorithms or on predicting their cognitive scores through regression methods, neglecting the potential association between these two tasks. Motivated by the need to enhance the prospects for early diagnosis along with the ability to predict future disease states, this study proposes a deep neural network based on modality fusion, kernelization, and tensorization that perform multiclass classification and longitudinal regression simultaneously within a unified multitask framework. This relationship between multiclass classification and longitudinal regression is found to boost the efficacy of the final model in dealing with both tasks. Different multimodality scenarios are investigated, and complementary aspects of the multimodal features are exploited to simultaneously delineate the subject’s label and predict related cognitive scores at future timepoints using baseline data. The main intent in this multitask framework is to consolidate the highest accuracy possible in terms of precision, sensitivity, F1 score, and area under the curve (AUC) in the multiclass classification task while maintaining the highest similarity in the MMSE score as measured through the correlation coefficient and the RMSE for all time points under the prediction task, with both tasks, run simultaneously under the same set of hyperparameters. The overall accuracy for multiclass classification of the proposed KTMnet method is 66.85 ± 3.77. The prediction results show an average RMSE of 2.32 ± 0.52 and a correlation of 0.71 ± 5.98 for predicting MMSE throughout the time points. These results are compared to state-of-the-art techniques reported in the literature. A discovery from the multitasking of this consolidated machine learning framework is that a set of hyperparameters that optimize the prediction results may not necessarily be the same as those that would optimize the multiclass classification. In other words, there is a breakpoint beyond which enhancing further the results of one process could lead to the downgrading in accuracy for the other.

Introduction Culturally fair cognitive assessments sensitive to detecting changes associated with prodromal Alzheimer's disease are needed. Methods Performance of Hispanic and non-Hispanic older adults on the Loewenstein-Acevedo Scale of Semantic Interference and Learning (LASSI-L) was examined in persons with amnestic mild cognitive impairment (aMCI) or normal cognition. The association between a novel cognitive marker, the failure to recover from proactive semantic interference (frPSI), and cortical thinning was explored. Results English-speaking aMCI participants scored lower than cognitively normal participants on all LASSI-L indices, while Spanish-speaking aMCI participants scored lower in learning, frPSI, and delayed recall. Healthy controls obtained equivalent scores on all indices except retroactive semantic interference. English-speaking and Spanish-speaking aMCI participants had equivalent scores except English speaker's greater vulnerability to frPSI. Across aMCI groups, frPSI was associated with cortical thinning of the entorhinal cortex and precuneus (r = −0.45 to r = 0.52; P, Highlights • Culturally fair outcome measures sensitive to detecting prodromal Alzheimer's disease are needed. • The Loewenstein-Acevedo Scale of Semantic Interference and Learning differentiates amnestic mild cognitive impairment from cognitively normal Hispanic elderly, a growing minority group. • A sensitive marker, failure to recover from proactive semantic interference, was implicated in amnestic mild cognitive impairment, regardless of culture/language. • The failure to recover from proactive semantic interference was associated with cortical thinning in Alzheimer's disease–prone regions.

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.

Background Functional magnetic resonance imaging (fMRI) is an MRI-based neuroimaging technique that measures brain activity on the basis of blood oxygenation level. This study reviews the main fMRI methods reported in the literature and their related applications in clinical and preclinical studies, focusing on relating functional brain networks in the prodromal stages of Alzheimer’s disease (AD), with a focus on the transition phases from cognitively normal (CN) to mild cognitive impairment (MCI) and from MCI to AD. New method The purpose of this study is to present and compare different approaches of supervised and unsupervised fMRI analyses and to highlight the different applications of fMRI in the diagnosis of MCI and AD. Results Survey article asserts that brain network disruptions of a given dysfunction or in relation to disease prone areas of the brain in neurodegenerative dementias could be extremely useful in ascertaining the extent of cognitive deficits at the different stages of the disease. Identifying the earliest changes in these activity patterns is essential for the early planning of treatment and therapeutic protocols. Comparison with existing methods Analysis methods such as independent component analysis (ICA) and graph theory-based approaches are strong analytical techniques most suitable for functional connectivity investigations. However, graph theory-based approaches have received more attention due to the higher performance they achieve in both functional and effective connectivity studies. Conclusion This article shows that the disruption of brain connectivity patterns of MCI and AD could be associated with cognitive decline, an interesting finding that could augment the prospects for early diagnosis. More importantly, results reveal that changes in functional connectivity as obtained through fMRI precede detection of cortical thinning in structural MRI and amyloid deposition in positron emission tomography (PET). However, a major challenge in using fMRI as a single imaging modality, like all other imaging modalities used in isolation, is in relating a particular disruption in functional connectivity in relation to a specific disease. This is a challenge that requires more thorough investigation, and one that could perhaps be overcome through multimodal neuroimaging by consolidating the strengths of these individual imaging modalities.

This review article provides a comprehensive survey on state-of-the-art impulse and Gaussian denoising filters applied to images and summarizes the progress that has been made over the years in all applications involving image processing. The random noise model in this survey is assumed to be comprised of impulse (salt and pepper) and Gaussian noise. Different noise models are addressed, and different types of denoising filters are studied in terms of their performance on digital images and in their various practical implications and domains of application. A comprehensive comparison is performed to cover all the denoising methods in details and the results they yield. With this extensive review, researchers in image processing will be able to ascertain which of these denoising methods will be best applicable to their research needs and the application domain where such methods are contemplated for implementation.

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.

Using electroencephalography (EEG) data from epileptic patients1, we investigated and compared functional connectivity networks of three various types of epileptiform discharges (ED; single, complex & repetitive spikes) in 4 regions of the brain. Our results showed different connectivity patterns among three ED types within-and between-brain regions. The one-way ANOVA test indicated significant differences between the mean of the average connectivity matrices (ACMs) of the single spike, which characterize focal epilepsy, and the other two ED types (complex & repetitive) which characterize generalized epilepsy. The interictal EEG segments, through the connectivity patterns they yield, could be considered as one of the key indicators for the diagnosis of focal or generalized epilepsy.

This paper introduces a robust edge detection method that relies on an integrated process for denoising images in the presence of high impulse noise. This process is shown to be resilient to impulse (or salt and pepper) noise even under high intensity levels. The proposed switching adaptive median and fixed weighted mean filter (SAMFWMF) is shown to yield optimal edge detection and edge detail preservation, an outcome we validate through high correlation, structural similarity index, and peak signal-to-noise ratio measures. For comparative purposes, a comprehensive analysis of other denoising filters is provided based on these various validation metrics. The non-maximum suppression method and new edge following maximum-sequence are the two techniques used to track the edges and overcome edge discontinuities and noisy pixels, especially in the presence of high-intensity noise levels. After applying predefined thresholds to the grayscale image, and thus obtaining a binary image, several morphological operations are used to remove the unwanted edges and noisy pixels and perform edge thinning to ultimately provide the desired edge connectivity, which results in an optimal edge detection method. The obtained results are compared with other existing state-of-the-art denoising filters and other edge detection methods in support of our assertion that the proposed method is resilient to impulse noise even under high-intensity levels.

This study introduces an image denoising method in the presence of combined speckle and Gaussian noise. The dual-tree complex wavelet transform is applied to the image in order to obtain specific coefficients characterising these types of noise. Then, these extracted coefficients are removed by thresholding and an inverse wavelet transform is applied in order to obtain the reconstructed image. A comparison between the dual-tree and standard wavelet-based denoising filters is provided on the basis of different structural metrics. Finally, in order to remove any remaining noise, a spatial denoising filter is applied to the image. The results obtained on medical ultrasound images corrupted by this noise combination support the authors' assertion on the method's resilience to the combined effects of speckle and Gaussian noise, and are compared to well-known and most effective speckle-Gaussian 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.