Explore the vast range of titles available.

Modern machine learning algorithms are increasingly being used in neuroimaging studies, such as the prediction of Alzheimer's disease (AD) from structural MRI. However, finding a good representation for multivariate brain MRI features in which their essential structure is revealed and easily extractable has been difficult. We report a successful application of a machine learning framework that significantly improved the use of brain MRI for predictions. Specifically, we used the unsupervised learning algorithm of local linear embedding (LLE) to transform multivariate MRI data of regional brain volume and cortical thickness to a locally linear space with fewer dimensions, while also utilizing the global nonlinear data structure. The embedded brain features were then used to train a classifier for predicting future conversion to AD based on a baseline MRI. We tested the approach on 413 individuals from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had baseline MRI scans and complete clinical follow-ups over 3years with the following diagnoses: cognitive normal (CN; n=137), stable mild cognitive impairment (s-MCI; n=93), MCI converters to AD (c-MCI, n=97), and AD (n=86). We found that classifications using embedded MRI features generally outperformed (p<0.05) classifications using the original features directly. Moreover, the improvement from LLE was not limited to a particular classifier but worked equally well for regularized logistic regressions, support vector machines, and linear discriminant analysis. Most strikingly, using LLE significantly improved (p=0.007) predictions of MCI subjects who converted to AD and those who remained stable (accuracy/sensitivity/specificity: =0.68/0.80/0.56). In contrast, predictions using the original features performed not better than by chance (accuracy/sensitivity/specificity: =0.56/0.65/0.46). In conclusion, LLE is a very effective tool for classification studies of AD using multivariate MRI data. The improvement in predicting conversion to AD in MCI could have important implications for health management and for powering therapeutic trials by targeting non-demented subjects who later convert to AD. •Locally linear embedding (LLE) is an unsupervised learning algorithm.•It was used to extract characteristic MR features of brain alternations.•It was used to classify normal aging subjects, MCI and AD patients from ADNI data.•The performance of predicting AD in MCIs was significantly improved by using LLE.•LLE benefitted various classifiers, such as SVM, LDA and regularized regressions.

In the current decade, advances in health care are attracting widespread interest due to their contributions to people longer surviving and fitter lives. Alzheimer’s disease (AD) is the commonest neurodegenerative and dementing disease. The monetary value of caring for Alzheimer’s disease patients is involved to rise dramatically. The necessity of having a computer-aided system for early and accurate AD classification becomes crucial. Deep-learning algorithms have notable advantages rather than machine learning methods. Many recent research studies that have used brain MRI scans and convolutional neural networks (CNN) achieved promising results for the diagnosis of Alzheimer’s disease. Accordingly, this study proposes a CNN based end-to-end framework for AD-classification. The proposed framework achieved 99.6%, 99.8%, and 97.8% classification accuracies on Alzheimer’s disease Neuroimaging Initiative (ADNI) dataset for the binary classification of AD and Cognitively Normal (CN). In multi-classification experiments, the proposed framework achieved 97.5% classification accuracy on the ADNI dataset.

Recently, machine learning methods have gained lots of attention from researchers seeking to analyze brain images such as Resting-State Functional Magnetic Resonance Imaging (rs-fMRI) to obtain a deeper understanding of the brain and such related diseases, for example, Alzheimer's disease. Finding the common patterns caused by a brain disorder through analysis of the functional connectivity (FC) network along with discriminating brain diseases from normal controls have long been the two principal goals in studying rs-fMRI data. The majority of FC extraction methods calculate the FC matrix for each subject and then use simple techniques to combine them and obtain a general FC matrix. In addition, the state-of-the-art classification techniques for finding subjects with brain disorders also rely on calculating an FC for each subject, vectorizing, and feeding them to the classifier. Considering these problems and based on multi-dimensional nature of the data, we have come up with a novel tensor framework in which a general FC matrix is obtained without the need to construct an FC matrix for each sample. This framework also allows us to reduce the dimensionality and create a novel discriminant function that rather than using FCs works directly with each sample, avoids vectorization in any step, and uses the test data in the training process without forcing any prior knowledge of its label into the classifier. Extensive experiments using the ADNI dataset demonstrate that our proposed framework effectively boosts the fMRI classification performance and reveals novel connectivity patterns in Alzheimer's disease at its early stages.

Here we summarize recent progress in machine learning model for diagnosis of Autism Spectrum Disorder (ASD) and Attention-deficit/Hyperactivity Disorder (ADHD). We outline and describe the machine-learning, especially deep-learning, techniques that are suitable for addressing research questions in this domain, pitfalls of the available methods, as well as future directions for the field. We envision a future where the diagnosis of ASD, ADHD, and other mental disorders is accomplished, and quantified using imaging techniques, such as MRI, and machine-learning models.

It has been of great interest in the neuroimaging community to model spatiotemporal brain function and related disorders based on resting state functional magnetic resonance imaging (rfMRI). Although a variety of deep learning models have been proposed for modeling rfMRI, the dominant models are limited in capturing the long-distance dependency (LDD) due to their sequential nature. In this work, we propose a spatiotemporal attention auto-encoder (STAAE) to discover global features that address LDDs in volumetric rfMRI. The unsupervised STAAE framework can spatiotemporally model the rfMRI sequence and decompose the rfMRI into spatial and temporal patterns. The spatial patterns have been extensively explored and are also known as resting state networks (RSNs), yet the temporal patterns are underestimated in last decades. To further explore the application of temporal patterns, we developed a resting state temporal template (RSTT)-based classification framework using the STAAE model and tested it with attention-deficit hyperactivity disorder (ADHD) classification. Five datasets from ADHD-200 were used to evaluate the performance of our method. The results showed that the proposed STAAE outperformed three recent methods in deriving ten well-known RSNs. For ADHD classification, the proposed RSTT-based classification framework outperformed methods in recent studies by achieving a high accuracy of 72.5%. Besides, we found that the RSTTs derived from NYU dataset still work on the other four datasets, but the accuracy on different test datasets decreased with the increase in the age gap to NYU dataset, which likely supports the idea of that there exist age differences of brain activity among ADHD patients.

Early diagnosis of attention deficit and hyperactivity disorder (ADHD) by experts is difficult. Some solutions using electroencephalography (EEG) signals have been presented in the literature to solve this problem. However, few studies have aimed to determine which recording statuses and which channels are effective for the diagnosis of ADHD. In this study, the effects of photic stimuli at different frequencies and on different channels on ADHD diagnosis were analysed. The main purpose of this study is to reveal the most effective channel and the most effective recording status for ADHD diagnosis. In this way, EEG data can be obtained from effective channels and recording statuses, and ADHD classification can be performed with fewer channels and higher accuracy. This can reduce the amount of data to be processed and the numbers of recording procedures. The dataset used in the experiments of this study was obtained using power spectral densities and spectral entropy values. These values were obtained from individuals with and without ADHD. When these data were applied to long short-term memory (LSTM), support vector machine (SVM), and artificial neural network classifiers, the highest accuracy was obtained with LSTM. The accuracy of LSTM was calculated as 88.88% on the “Fp1,F7” channel and 92.15% in the eyes-closed resting state. Spectral entropy was found to contribute positively to the accuracy. As a result, the potential difference between “Fp1,F7” electrodes in the eyes-closed resting state proved to be effective in diagnosing ADHD.

Habitualmente las leyes administrativas cuando tipifican infracciones se encargan también de clasificarlas en función de su gravedad. Pero no siempre es así. No son pocas, de hecho, las leyes que confían esa operación de clasificación al desarrollo reglamentario o, como es más común que suceda, a la propia Administración sancionadora. Este artículo analiza esta forma de tipificación de las infracciones y alerta sobre las principales debilidades de la tesis hoy dominante que niega su constitucionalidad.

To evaluate the incidence, severity, and factors related to drug-induced keratoepitheliopathy in eyes using antiglaucoma eye drops. In a cross-sectional study, 749 eyes from 427 patients who had used one or more antiglaucoma eye drops were examined at Niigata University Medical and Dental Hospital or related facilities. The incidence and severity of superficial punctate keratitis (SPK), patient gender and age, type of glaucoma, and type of eye drops were recorded. SPK was graded according to the AD (A, area; D, density) classification. The severity score (SS) was calculated from A x D. SPK was observed in 382 (51.0%) of 749 eyes that had received any type of antiglaucoma eye drops. While 254 eyes (33.9%) were classified as A1D1 (SS 1), 34 eyes (4.6%) had severe SPK with SS 4 or more. The number of eye drops and the total dosing frequency per day were significantly greater in SPK-positive eyes than in eyes without SPK. The number of eye drops was proportional to the frequency and severity of SPK. Among eyes that were treated with three or more eye drops, SPK was more severe and more frequent in older patients (>/=71 years). In addition, a considerable difference was detected for each type of glaucoma. Drug-induced keratoepitheliopathy is often observed in eyes that have received recent antiglaucoma eye drops. The number of eye drops, the total dose frequency per day, patient age, and type of glaucoma may affect this condition. We have to consider not only the effects on intraocular pressure but also the incidence and severity of drug-induced keratoepitheliopathy as a frequent side effect of glaucoma medications.

Since its first edition, the Diagnostic and Statistical manual of Mental disorders (DSM) has had a great impact on the scientific community and the public opinion as well. In 2013, the American Psychiatric Association released the fifth edition of the manual and – as for the previous versions – several criticisms raised. In particular, the persistence of the categorical approach to mental disorders represents one of the main debated topics, as well as the introduction of new diagnostic syndromes, which are not based on an adequate evidences. Moreover, the threshold of diagnostic criteria for many mental disorders has been lowered, with the consequence that the boundaries between “normality” and “pathology” is not so clear. In this paper, we will: 1) report the historical development of the DSM from the publication of its first edition; 2) describe the main changes introduced in the DSM-5; 3) discuss critical elements in the DSM-5. The current debate regarding the validity of diagnostic manuals and its criteria is threatening the psychiatric discipline, but a possible solution should be represented by the integration of diagnostic criteria with the in-depth description of patient’s psychopathological experiences.

In questo saggio propongo un’analisi della classificazione delle scienze sviluppata da Bonaventura nel De reductione artium ad theologiam. La prima parte introduce i temi fondamentali della questione enciclopedica, mostrandone l’importanza teorica e socioculturale. Nella seconda parte considero il problema specifico della riduzione nel saggio di Bonaventura. Il principio guida di quest’analisi è la convinzione che i classici siano tali non tanto perché appartengono a un passato più o meno lontano, ma perché ci possono dire qualcosa del presente e ci possono insegnare qualcosa per il futuro. In questo senso l’opera di Bonaventura, analizzata nell’ottica della questione enciclopedica, apparirà come un vero e proprio inno all’enciclopedia del sapere. In this paper I propose an analysis of the classification of the sciences developed by S. Bonaventure in the De reductione artium ad theologiam. The first part introduces the basic topics of the encyclopaedic issue, showing its theoretical and sociocultural importance. In the second part I focus on the specific reduction problem in the Bonaventure’s essay. The guiding principle of this analysis is the belief that the classics are classics not because they belong to a more or less distant past but because they can tell us something about the present and they can teach us something for the future. In this respect, with the view to the encyclopaedic issue, the Bonaventure’s work will prove to be a real hymn to the human encyclopaedia.