ABSTRACT
Conventionally, cerebrovascular reactivity (CVR) is estimated as the amplitude of the hemodynamic response to vascular stimuli, most commonly carbon dioxide (CO2). While the CVR amplitude has established clinical utility, the temporal characteristics of CVR (dCVR) have been increasingly explored and may yield even more pathology-sensitive parameters. This work is motivated by the current need to evaluate the feasibility of dCVR modeling in various experimental conditions. In this work, we present a comparison of several recently published/utilized model-based deconvolution (response estimation) approaches for estimating the CO2 response function h(t), including maximum a posteriori likelihood (MAP), inverse logit (IL), canonical correlation analysis (CCA), and basis expansion (using Gamma and Laguerre basis sets). To aid the comparison, we devised a novel simulation framework that incorporates a wide range of SNRs, ranging from 10 to -7 dB, representative of both task and resting-state CO2 changes. In addition, we built ground-truth h(t) into our simulation framework, overcoming the conventional limitation that the true h(t) is unknown. Moreover, to best represent realistic noise found in fMRI scans, we extracted noise from in-vivo resting-state scans. Furthermore, we introduce a simple optimization of the CCA method (CCAopt) and compare its performance to these existing methods. Our findings suggest that model-based methods can accurately estimate dCVR even amidst high noise (i.e. resting-state), and in a manner that is largely independent of the underlying model assumptions for each method. We also provide a quantitative basis for making methodological choices, based on the desired dCVR parameters, the estimation accuracy and computation time. The BEL method provided the highest accuracy and robustness, followed by the CCAopt and IL methods. Of the three, the CCAopt method has the lowest computational requirements. These findings lay the foundation for wider adoption of dCVR estimation in CVR mapping.
Subject(s)
Carbon Dioxide , Magnetic Resonance Imaging , Humans , Magnetic Resonance Imaging/methods , Brain/physiology , Hemodynamics , Computer Simulation , Cerebrovascular Circulation/physiologyABSTRACT
The Coronavirus has spread across the world and infected millions of people, causing devastating damage to the public health and global economies. To mitigate the impact of the coronavirus a reliable, fast, and accurate diagnostic system should be promptly implemented. In this study, we propose EpistoNet, a decision tree-based ensemble model using two mixtures of discriminative experts to classify COVID-19 lung infection from chest X-ray images. To optimize the architecture and hyper-parameters of the designed neural networks, we employed Epistocracy algorithm, a recently proposed hyper-heuristic evolutionary method. Using 2500 chest X-ray images consisting of 1250 COVID-19 and 1250 non-COVID-19 cases, we left out 500 images for testing and partitioned the remaining 2000 images into 5 different clusters using K-means clustering algorithm. We trained multiple deep convolutional neural networks on each cluster to help build a mixture of strong discriminative experts from the top-performing models supervised by a gating network. The final ensemble model obtained 95% accuracy on COVID-19 images and 93% accuracy on non-COVID-19. The experimental results show that EpistoNet can accurately, and reliably be used to detect COVID-19 infection in the chest X-ray images, and Epistocracy algorithm can be effectively used to optimize the hyper-parameters of the proposed models.
Subject(s)
COVID-19 , Deep Learning , Image Processing, Computer-Assisted , Radiography, ThoracicABSTRACT
The desire to enhance the sensitivity and specificity of resting-state (rs-fMRI) measures has prompted substantial recent research into removing noise components. Chief among contributions to noise in rs-fMRI are physiological processes, and the neuronal implications of respiratory-volume variability (RVT), a main rs-fMRI-relevant physiological process, is incompletely understood. The potential implications of RVT in modulating and being modulated by autonomic nervous regulation, has yet to be fully understood by the rs-fMRI community. In this work, we use high-density electroencephalography (EEG) along with simultaneously acquired RVT recordings to help address this question. We hypothesize that (1) there is a significant relationship between EEG and RVT in multiple EEG bands, and (2) that this relationship varies by brain region. Our results confirm our first hypothesis, although all brain regions are shown to be equally implicated in RVT-related EEG-signal fluctuations. The lag between RVT and EEG is consistent with previously reported values. However, an interesting finding is related to the polarity of the correlation between RVT and EEG. Our results reveal potentially two main regimes of EEG-RVT association, one in which EEG leads RVT with a positive association between the two, and one in which RVT leads EEG but with a negative association between the two. We propose that these two patterns can be interpreted differently in terms of the involvement of higher cognition. These results further suggest that treating RVT simply as noise is likely a questionable practice, and that more work is needed to avoid discarding cognitively relevant information when performing physiological correction rs-fMRI.
Subject(s)
Brain Waves/physiology , Brain/diagnostic imaging , Brain/physiology , Respiratory Mechanics/physiology , Rest/physiology , Electroencephalography/methods , Female , Humans , Magnetic Resonance Imaging/methods , Male , Tidal Volume/physiologyABSTRACT
BACKGROUND: Atopic dermatitis (AD) is a common, chronic, relapsing and inflammatory skin disease characterized by pruritus and xerosis (dry skin). Its prevalence is on the increase worldwide, particularly in children. As the pathogenesis of AD involves a complex interaction of genetic, environmental and immunological factors, its definitive treatment is difficult. OBJECTIVE: This clinical trial was designed as equivalence study to investigate the effect of aqueous extract of edible dried fig fruit on the severity of AD as measured with scoring atopic dermatitis (SCORAD), in comparison with Hydrocortisone 1.0% as the routine treatment of AD and base cream as a placebo. METHOD: Forty five children aged 4 months to 14 years with mild to moderate AD (SCORAD <50) were randomly assigned, in a double blind manner, to three treatment groups in order to perform a randomised, double blinded, placebo-controlled clinical trial. The patients were instructed to apply their allocated creams twice a day for two weeks. RESULTS: The randomised, placebo-controlled trial indicates that the new treatment had significantly increased efficacy in terms of reducing the SCORAD index, pruritus and intensity scores in comparison with Hydrocortisone 1.0% (p<0.05) and the placebo failed to ameliorate the symptoms. CONCLUSION: Safety, efficacy, tolerability, and symptom relief were considerable in fig fruit extract in comparison with hydrocortisone 1.0%. This clinical trial suggests that fig fruit extract can be used instead of low potent corticosteroid in mild to moderate cases of AD.
Subject(s)
Dermatitis, Atopic/drug therapy , Ficus , Phytotherapy , Plant Preparations/therapeutic use , Pruritus/drug therapy , Administration, Topical , Adolescent , Child , Child, Preschool , Dermatitis, Atopic/complications , Double-Blind Method , Female , Fruit , Humans , Hydrocortisone/therapeutic use , Infant , Male , Ointments , Plant Preparations/administration & dosage , Plant Preparations/pharmacology , Pruritus/etiology , Severity of Illness Index , Treatment OutcomeABSTRACT
To spatially cluster resting state-functional magnetic resonance imaging (rs-fMRI) data into potential networks, there are only a few general approaches that determine the number of networks/clusters, despite a wide variety of techniques proposed for clustering. For individual subjects, extraction of a large number of spatially disjoint clusters results in multiple small networks that are spatio-temporally homogeneous but irreproducible across subjects. Alternatively, extraction of a small number of clusters creates spatially large networks that are temporally heterogeneous but spatially reproducible across subjects. We propose a fully automatic, iterative reclustering framework in which a small number of spatially large, heterogeneous networks are initially extracted to maximize spatial reproducibility. Subsequently, the large networks are iteratively subdivided to create spatially reproducible subnetworks until the overall within-network homogeneity does not increase substantially. The proposed approach discovers a rich network hierarchy in the brain while simultaneously optimizing spatial reproducibility of networks across subjects and individual network homogeneity. We also propose a novel metric to measure the connectivity of brain regions, and in a simulation study show that our connectivity metric and framework perform well in the face of low signal to noise and initial segmentation errors. Experimental results generated using real fMRI data show that the proposed metric improves stability of network clusters across subjects, and generates a meaningful pattern for spatially hierarchical structure of the brain.
Subject(s)
Brain Mapping/methods , Brain/physiology , Magnetic Resonance Imaging/methods , Pattern Recognition, Automated/methods , Adult , Algorithms , Cluster Analysis , Computer Simulation , Datasets as Topic , Humans , Models, Neurological , Neural Pathways/physiology , Rest , Signal Processing, Computer-Assisted , Young AdultABSTRACT
Linear predictive models are applied to functional MRI (fMRI) data to estimate boundaries that predict experimental task states for scans. These boundaries are visualized as statistical parametric maps (SPMs) and range from low to high spatial reproducibility across subjects (e.g., Strother , 2004; LaConte , 2003). Such inter-subject pattern reproducibility is an essential characteristic of interpretable SPMs that generalize across subjects. Therefore, we introduce a flexible hybrid model that optimizes reproducibility by simultaneously enhancing the prediction power and reproducibility. This hybrid model is formed by a weighted summation of the optimization functions of a linear discriminate analysis (LDA) model and a generalized canonical correlation (gCCA) model (Afshin-Pour , 2012). LDA preserves the model's ability to discriminate the fMRI scans of multiple brain states while gCCA finds a linear combination for each subject's scans such that the estimated boundary map is reproducible. The hybrid model is implemented in a split-half resampling framework (Strother , 2010) which provides reproducibility (r) and prediction (p) quality metrics. Then the model was compared with LDA, and Gaussian Naive Bayes (GNB). For simulated fMRI data, the hybrid model outperforms the other two techniques in terms of receiver operating characteristic (ROC) curves, particularly for detecting less predictable but spatially reproducible networks. These techniques were applied to real fMRI data to estimate the maps for two task contrasts. Our results indicate that compared to LDA and GNB, the hybrid model can provide maps with large increases in reproducibility for small reductions in prediction, which are jointly closer to the ideal performance point of (p=1, r=1).