Towards a Corpus (and Language)-Independent Screening of Parkinson's Disease from Voice and Speech through Domain Adaptation.

End-to-end deep learning models have shown promising results for the automatic screening of Parkinson's disease by voice and speech. However, these models often suffer degradation in their performance when applied to scenarios involving multiple corpora. In addition, they also show corpus-dependent clusterings. These facts indicate a lack of generalisation or the presence of certain shortcuts in the decision, and also suggest the need for developing new corpus-independent models. In this respect, this work explores the use of domain adversarial training as a viable strategy to develop models that retain their discriminative capacity to detect Parkinson's disease across diverse datasets. The paper presents three deep learning architectures and their domain adversarial counterparts. The models were evaluated with sustained vowels and diadochokinetic recordings extracted from four corpora with different demographics, dialects or languages, and recording conditions. The results showed that the space distribution of the embedding features extracted by the domain adversarial networks exhibits a higher intra-class cohesion. This behaviour is supported by a decrease in the variability and inter-domain divergence computed within each class. The findings suggest that domain adversarial networks are able to learn the common characteristics present in Parkinsonian voice and speech, which are supposed to be corpus, and consequently, language independent. Overall, this effort provides evidence that domain adaptation techniques refine the existing end-to-end deep learning approaches for Parkinson's disease detection from voice and speech, achieving more generalizable models.

Automatic Identification of Lung Opacities Due to COVID-19 from Chest X-ray Images-Focussing Attention on the Lungs.

Due to the primary affection of the respiratory system, COVID-19 leaves traces that are visible in plain chest X-ray images. This is why this imaging technique is typically used in the clinic for an initial evaluation of the patient's degree of affection. However, individually studying every patient's radiograph is time-consuming and requires highly skilled personnel. This is why automatic decision support systems capable of identifying those lesions due to COVID-19 are of practical interest, not only for alleviating the workload in the clinic environment but also for potentially detecting non-evident lung lesions. This article proposes an alternative approach to identify lung lesions associated with COVID-19 from plain chest X-ray images using deep learning techniques. The novelty of the method is based on an alternative pre-processing of the images that focuses attention on a certain region of interest by cropping the original image to the area of the lungs. The process simplifies training by removing irrelevant information, improving model precision, and making the decision more understandable. Using the FISABIO-RSNA COVID-19 Detection open data set, results report that the opacities due to COVID-19 can be detected with a Mean Average Precision with an IoU > 0.5 (mAP@50) of 0.59 following a semi-supervised training procedure and an ensemble of two architectures: RetinaNet and Cascade R-CNN. The results also suggest that cropping to the rectangular area occupied by the lungs improves the detection of existing lesions. A main methodological conclusion is also presented, suggesting the need to resize the available bounding boxes used to delineate the opacities. This process removes inaccuracies during the labelling procedure, leading to more accurate results. This procedure can be easily performed automatically after the cropping stage.

Differential Profile of Systemic Extracellular Vesicles From Sporadic and Familial Alzheimer's Disease Leads to Neuroglial and Endothelial Cell Degeneration.

Evidence suggests that extracellular vesicles (EVs) act as mediators and biomarkers of neurodegenerative diseases. Two distinct forms of Alzheimer disease (AD) are known: a late-onset sporadic form (SAD) and an early-onset familial form (FAD). Recently, neurovascular dysfunction and altered systemic immunological components have been linked to AD neurodegeneration. Therefore, we characterized systemic-EVs from postmortem SAD and FAD patients and evaluated their effects on neuroglial and endothelial cells. We found increase CLN-5 spots with vesicular morphology in the abluminal portion of vessels from SAD patients. Both forms of AD were associated with larger and more numerous systemic EVs. Specifically, SAD patients showed an increase in endothelial- and leukocyte-derived EVs containing mitochondria; in contrast, FAD patients showed an increase in platelet-derived EVs. We detected a differential protein composition for SAD- and FAD-EVs associated with the coagulation cascade, inflammation, and lipid-carbohydrate metabolism. Using mono- and cocultures (endothelium-astrocytes-neurons) and human cortical organoids, we showed that AD-EVs induced cytotoxicity. Both forms of AD featured decreased neuronal branches area and astrocytic hyperreactivity, but SAD-EVs led to greater endothelial detrimental effects than FAD-EVs. In addition, FAD- and SAD-EVs affected calcium dynamics in a cortical organoid model. Our findings indicate that the phenotype of systemic AD-EVs is differentially defined by the etiopathology of the disease (SAD or FAD), which results in a differential alteration of the NVU cells implied in neurodegeneration.

Artificial Intelligence Applied to Chest X-Ray Images for the Automatic Detection of COVID-19. A Thoughtful Evaluation Approach.

Current standard protocols used in the clinic for diagnosing COVID-19 include molecular or antigen tests, generally complemented by a plain chest X-Ray. The combined analysis aims to reduce the significant number of false negatives of these tests and provide complementary evidence about the presence and severity of the disease. However, the procedure is not free of errors, and the interpretation of the chest X-Ray is only restricted to radiologists due to its complexity. With the long term goal to provide new evidence for the diagnosis, this paper presents an evaluation of different methods based on a deep neural network. These are the first steps to develop an automatic COVID-19 diagnosis tool using chest X-Ray images to differentiate between controls, pneumonia, or COVID-19 groups. The paper describes the process followed to train a Convolutional Neural Network with a dataset of more than 79, 500 X-Ray images compiled from different sources, including more than 8, 500 COVID-19 examples. Three different experiments following three preprocessing schemes are carried out to evaluate and compare the developed models. The aim is to evaluate how preprocessing the data affects the results and improves its explainability. Likewise, a critical analysis of different variability issues that might compromise the system and its effects is performed. With the employed methodology, a 91.5% classification accuracy is obtained, with an 87.4% average recall for the worst but most explainable experiment, which requires a previous automatic segmentation of the lung region.

Changes in the hippocampal and peripheral phospholipid profiles are associated with neurodegeneration hallmarks in a long-term global cerebral ischemia model: Attenuation by Linalool.

Phospholipid alterations in the brain are associated with progressive neurodegeneration and cognitive impairment after acute and chronic injuries. Various types of treatments have been evaluated for their abilities to block the progression of the impairment, but effective treatments targeting long-term post-stroke alterations are not available. In this study, we analyzed changes in the central and peripheral phospholipid profiles in ischemic rats and determined whether a protective monoterpene, Linalool, could modify them. We used an in vitro model of glutamate (125 µM) excitotoxicity and an in vivo global ischemia model in Wistar rats. Linalool (0.1 µM) protected neurons and astrocytes by reducing LDH release and restoring ATP levels. Linalool was administered orally at a dose of 25 mg/kg every 24 h for a month, behavioral tests were performed, and a lipidomic analysis was conducted using mass spectrometry. Animals treated with Linalool displayed faster neurological recovery than untreated ischemic animals, accompanied by better motor and cognitive performances. These results were confirmed by the significant reduction in astrogliosis, microgliosis and COX-2 marker, involving a decrease of 24:0 free fatty acid in the hippocampus. The altered profiles of phospholipids composed of mono and polyunsaturated fatty acids (PC 36:1; 42:1 (24:0/18:1)/LPC 22:6)/LPE 22:6) in the ischemic hippocampus and the upregulation of PI 36:2 and other LCFA (long chain fatty acids) in the serum of ischemic rats were prevented by the monoterpene. Based on these data, alterations in the central and peripheral phospholipid profiles after long-term was attenuated by oral Linalool, promoting a phospholipid homeostasis, related to the recovery of brain function.

BACE1 RNAi Restores the Composition of Phosphatidylethanolamine-Derivates Related to Memory Improvement in Aged 3xTg-AD Mice.

ß-amyloid (Aß) is produced by the ß-secretase 1 (BACE1)-mediated enzymatic cleavage of the amyloid precursor protein through the amyloidogenic pathway, making BACE1 a therapeutic target against Alzheimer's disease (AD). Alterations in lipid metabolism are a risk factor for AD by an unknown mechanism. The objective of this study was to determine the effect of RNA interference against BACE1 (shBACEmiR) on the phospholipid profile in hippocampal CA1 area in aged 3xTg-AD mice after 6 and 12 months of treatment compared to aged PS1KI mice. The shBACEmiR treatment induced cognitive function recovery and restored mainly the fatty acid composition of lysophosphatidylethanolamine and etherphosphatidylethanolamine, reduced the cPLA2's phosphorylation, down-regulated the levels of arachidonic acid and COX2 in the hippocampi of 3xTg-AD mice. Together, our findings suggest, for the first time, that BACE1 silencing restores phospholipids composition which could favor the recovery of cellular homeostasis and cognitive function in the hippocampus of triple transgenic AD mice.

Automatic detection of pathological voices using complexity measures, noise parameters, and mel-cepstral coefficients.

This paper proposes a new approach to improve the amount of information extracted from the speech aiming to increase the accuracy of a system developed for the automatic detection of pathological voices. The paper addresses the discrimination capabilities of 11 features extracted using nonlinear analysis of time series. Two of these features are based on conventional nonlinear statistics (largest Lyapunov exponent and correlation dimension), two are based on recurrence and fractal-scaling analysis, and the remaining are based on different estimations of the entropy. Moreover, this paper uses a strategy based on combining classifiers for fusing the nonlinear analysis with the information provided by classic parameterization approaches found in the literature (noise parameters and mel-frequency cepstral coefficients). The classification was carried out in two steps using, first, a generative and, later, a discriminative approach. Combining both classifiers, the best accuracy obtained is 98.23% ± 0.001.

Towards objective evaluation of perceived roughness and breathiness: an approach based on mel-frequency cepstral analysis.

Within this paper, the authors report on an experiment on automatic labelling of perceived voice roughness (R) and breathiness (B), according to the GRBAS scale. The main objective of the experiment has not been to correlate objective measures to perceived R and B, but to automatically evaluate R and B. For this purpose, a system has been trained that extracts the first mel-frequency cepstral coefficients (MFCC) of available sustained vowel phonations. Afterwards, a classifier has been trained to estimate the corresponding degrees of roughness and breathiness. The obtained results reveal a significant correlation between subjective and automatic labelling, hence indicating the feasibility of objective evaluation of voice quality by means of perceptually meaningful measures.

Complexity analysis of pathological voices by means of hidden Markov entropy measurements.

In this work an entropy based nonlinear analysis of pathological voices is presented. The complexity analysis is carried out by means of six different entropies, including three measures derived from the entropy rate of Markov chains. The aim is to characterize the divergence of the trajectories and theirs directions into the state space of Markov Chains. By employing these measures in conjunction with conventional entropy features, it is possible to improve the discrimination capabilities of the nonlinear analysis in the automatic detection of pathological voices.

Effects of audio compression in automatic detection of voice pathologies.

This paper investigates the performance of an automatic system for voice pathology detection when the voice samples have been compressed in MP3 format and different binary rates (160, 96, 64, 48, 24, and 8 kb/s). The detectors employ cepstral and noise measurements, along with their derivatives, to characterize the voice signals. The classification is performed using Gaussian mixtures models and support vector machines. The results between the different proposed detectors are compared by means of detector error tradeoff (DET) and receiver operating characteristic (ROC) curves, concluding that there are no significant differences in the performance of the detector when the binary rates of the compressed data are above 64 kb/s. This has useful applications in telemedicine, reducing the storage space of voice recordings or transmitting them over narrow-band communications channels.