A Review of Hidden Markov Models and Recurrent Neural Networks for Event Detection and Localization in Biomedical Signals

Biomedical signals carry signature rhythms of complex physiological processes that control our daily bodily activity. The properties of these rhythms indicate the nature of interaction dynamics among physiological processes that maintain a homeostasis. Abnormalities associated with diseases or disorders usually appear as disruptions in the structure of the rhythms which makes isolating these rhythms and the ability to differentiate between them, indispensable. Computer aided diagnosis systems are ubiquitous nowadays in almost every medical facility and more closely in wearable technology, and rhythm or event detection is the first of many intelligent steps that they perform. How these rhythms are isolated? How to develop a model that can describe the transition between processes in time? Many methods exist in the literature that address these questions and perform the decoding of biomedical signals into separate rhythms. In here, we demystify the most effective methods that are used for detection and isolation of rhythms or events in time series and highlight the way in which they were applied to different biomedical signals and how they contribute to information fusion. The key strengths and limitations of these methods are also discussed as well as the challenges encountered with application in biomedical signals.

Upper Esophageal Sphincter Opening Segmentation with Convolutional Recurrent Neural Networks in High Resolution Cervical Auscultation

Upper esophageal sphincter is an important anatomical landmark of the swallowing process commonly observed through the kinematic analysis of radiographic examinations that are vulnerable to subjectivity and clinical feasibility issues. Acting as the doorway of esophagus, upper esophageal sphincter allows the transition of ingested materials from pharyngeal into esophageal stages of swallowing and a reduced duration of opening can lead to penetration/aspiration and/or pharyngeal residue. Therefore, in this study we consider a non-invasive high resolution cervical auscultation-based screening tool to approximate the human ratings of upper esophageal sphincter opening and closure. Swallows were collected from 116 patients and a deep neural network was trained to produce a mask that demarcates the duration of upper esophageal sphincter opening. The proposed method achieved more than 90\% accuracy and similar values of sensitivity and specificity when compared to human ratings even when tested over swallows from an independent clinical experiment. Moreover, the predicted opening and closure moments surprisingly fell within an inter-human comparable error of their human rated counterparts which demonstrates the clinical significance of high resolution cervical auscultation in replacing ionizing radiation-based evaluation of swallowing kinematics.

Single neuron-based neural networks are as efficient as dense deep neural networks in binary and multi-class recognition problems

Recent advances in neuroscience have revealed many principles about neural processing. In particular, many biological systems were found to reconfigure/recruit single neurons to generate multiple kinds of decisions. Such findings have the potential to advance our understanding of the design and optimization process of artificial neural networks. Previous work demonstrated that dense neural networks are needed to shape complex decision surfaces required for AI-level recognition tasks. We investigate the ability to model high dimensional recognition problems using single or several neurons networks that are relatively easier to train. By employing three datasets, we test the use of a population of single neuron networks in performing multi-class recognition tasks. Surprisingly, we find that sparse networks can be as efficient as dense networks in both binary and multi-class tasks. Moreover, single neuron networks demonstrate superior performance in binary classification scheme and competing results when combined for multi-class recognition.