REM Sleep Stage Identification with Raw Single-Channel EEG.

This paper focused on creating an interpretable model for automatic rapid eye movement (REM) and non-REM sleep stage scoring for a single-channel electroencephalogram (EEG). Many methods attempt to extract meaningful information to provide to a learning algorithm. This method attempts to let the model extract the meaningful interpretable information by providing a smaller number of time-invariant signal filters for five frequency ranges using five CNN algorithms.

Extracting default mode network based on graph neural network for resting state fMRI study.

Functional magnetic resonance imaging (fMRI)-based study of functional connections in the brain has been highlighted by numerous human and animal studies recently, which have provided significant information to explain a wide range of pathological conditions and behavioral characteristics. In this paper, we propose the use of a graph neural network, a deep learning technique called graphSAGE, to investigate resting state fMRI (rs-fMRI) and extract the default mode network (DMN). Comparing typical methods such as seed-based correlation, independent component analysis, and dictionary learning, real data experiment results showed that the graphSAGE is more robust, reliable, and defines a clearer region of interests.

Attention Deficit Hyperactivity Disorder Classification Based on Deep Learning.

Attention Deficit Hyperactivity Disorder (ADHD) is a type of mental health disorder that can be seen from children to adults and affects patients' normal life. Accurate diagnosis of ADHD as early as possible is very important for the treatment of patients in clinical applications. Some traditional classification methods, although having been shown powerful in many other classification tasks, are not as successful in the application of ADHD classification.

Elastic net-based framework for imaging mass spectrometry data biomarker selection and classification.

Imaging mass spectrometry (IMS) shows great potential for the rapid mapping of protein localization and for detecting of sizeable differences in protein expression. However, data processing remains challenging due to the difficulty of analyzing high dimensionality, the fact that the number of predictors is significantly larger than the number of observations, and the need to consider both spectral and spatial information in order to represent the advantage of IMS technology. Ideally one would like to efficiently analyze all acquired data to find trace features based on both spectral and spatial patterns.

A novel comprehensive wave-form MS data processing method.

Motivation: Mass spectrometry (MS) can generate high-throughput protein profiles for biomedical research to discover biologically related protein patterns/biomarkers. The noisy functional MS data collected by current technologies, however, require consistent, sensitive and robust data-processing techniques for successful biomedical application. Therefore, it is important to detect features precisely for each spectrum, quantify them well and assign a unique label to features from the same protein/peptide across spectra.

Lineage development in a patient without goblet, paneth, and enteroendocrine cells: a clue for intestinal epithelial differentiation.

We report a patient who presented with severe enterocolitis and apparent absence of Paneth, goblet, and enteroendocrine lineages from the small bowel and colon. The absorptive enterocyte seemed to be normal morphologically and functionally. Because normal enterocytes were present, we hypothesized that this patient had a developmental block in the differentiation of a common stem cell precursor for Paneth, goblet, and neuroendocrine lineages.