Sourya Bhattacharyya

Feature Selection for Automatic Burst Detection in Neonatal Electroencephalogram

Monitoring neonatal electroencephalogram (EEG) signal is useful in identifying neonatal convulsions which might be clinically invisible. Presence of burst suppression pattern in neonate EEG is a clear indication of epilepsy. Visual identification of burst patterns from recorded continuous raw EEG data is time consuming. On the other hand, automatic burst detection techniques mentioned in the standard literature mostly rely on comparison with respect to predefined static voltage or energy thresholds, thus becoming too specific. Burst detection using ratio information of quantitative feature values between burst segment and neighborhood background EEG segment is proposed in this paper. Features like ratio of mean nonlinear energy, power spectral density, variance and absolute voltage, when applied as an input to a support vector machine (SVM) classifier, provides high degree of separability between burst and normal (nonburst) EEG segments. Exhaustive simulation using various literature specified features and proposed feature combinations shows that the proposed feature set provides best classification accuracy compared to other reported burst detection methods. The results documented in this paper can be used as a reference of optimum quantitative EEG feature sets for distinguishing between burst and normal (nonburst) EEG segments.

Detection of artifacts from high energy bursts in neonatal EEG

Detection of non-cerebral activities or artifacts, intermixed within the background EEG, is essential to discard them from subsequent pattern analysis. The problem is much harder in neonatal EEG, where the background EEG contains spikes, waves, and rapid fluctuations in amplitude and frequency. Existing artifact detection methods are mostly limited to detect only a subset of artifacts such as ocular, muscle or power line artifacts. Few methods integrate different modules, each for detection of one specific category of artifact. Furthermore, most of the reference approaches are implemented and tested on adult EEG recordings. Direct application of those methods on neonatal EEG causes performance deterioration, due to greater pattern variation and inherent complexity. A method for detection of a wide range of artifact categories in neonatal EEG is thus required. At the same time, the method should be specific enough to preserve the background EEG information. The current study describes a feature based classification approach to detect both repetitive (generated from ECG, EMG, pulse, respiration, etc.) and transient (generated from eye blinking, eye movement, patient movement, etc.) artifacts. It focuses on artifact detection within high energy burst patterns, instead of detecting artifacts within the complete background EEG with wide pattern variation. The objective is to find true burst patterns, which can later be used to identify the Burst-Suppression (BS) pattern, which is commonly observed during newborn seizure. Such selective artifact detection is proven to be more sensitive to artifacts and specific to bursts, compared to the existing artifact detection approaches applied on the complete background EEG. Several time domain, frequency domain, statistical features, and features generated by wavelet decomposition are analyzed to model the proposed bi-classification between burst and artifact segments. A feature selection method is also applied to select the feature subset producing highest classification accuracy. The suggested feature based classification method is executed using our recorded neonatal EEG dataset, consisting of burst and artifact segments. We obtain 78% sensitivity and 72% specificity as the accuracy measures. The accuracy obtained using the proposed method is found to be about 20% higher than that of the reference approaches. Joint use of the proposed method with our previous work on burst detection outperforms reference methods on simultaneous burst and artifact detection. As the proposed method supports detection of a wide range of artifact patterns, it can be improved to incorporate the detection of artifacts within other seizure patterns and background EEG information as well.

Summarization of Neonatal Video EEG for Seizure and Artifact Detection

Monitoring neonatal EEG signal is useful in identifying neonatal convulsions or seizures. For neonates, seizures can be electrographic, electro clinical, or both simultaneously. Electrographic seizure is identified via recorded EEG signal, while electro clinical seizures exhibit clinical manifestations. Sometimes neonates can exhibit silent seizures which may be clinically invisible but identifiable in recorded EEG, or vice versa. Thus, simultaneous monitoring of video and recorded EEG determines the correlation between the electrographic and electro clinical seizures. Furthermore, analyzing the movements of the neonates can identify movement artifacts easily, thus preventing false seizure detection. However, storage of high quality video recordings require large storage space. As neonates do not commonly exhibit movements, summarizing the video for storing only patient movements along with corresponding timestamps, can be useful. In this paper, a video summarization method is proposed for efficient browsing of video-EEG. Identification and analysis of the patterns of interest is possible via summarized information, thus reducing effective analysis time. In addition, quantitative demonstration of electrographic and electro clinical seizures is presented to analyze the utility of video-EEG.

Automated detection of newborn sleep apnea using video monitoring system

Automated detection of neonatal sleep apnea is essential for constrained environments with high patient to nurse ratio. Existing studies on apnea detection mostly target adults, and use invasive sensors. Few approaches detect apnea using video monitoring, by identifying absence of respiratory motion. They apply frame differencing and thresholding, not suitable for neonates due to their subtle respiratory motion intermixed with other body movements. Proposed method first applies motion magnification. Subsequently, it filters respiration motion using dynamic thresholding. The technique is benchmarked with simulated motion of varying respiration frequencies. When validated with neonatal video data, proposed method achieves both > 90% sensitivity and specificity.

Couplet supertree by equivalence partitioning of taxa set and DAG formation

From a given set of phylogenetic trees with overlapping taxa sets, a supertree describes evolutionary relationships among the union of their constituent taxa sets. Individual taxa subsets, however, can exhibit conflicting evolutionary relationships for different input trees. Strict consensus supertrees do not include any taxa subset exhibiting conflicts, thus can be non-plenary1. Plenary supertrees, on the other hand, aims to satisfy maximum agreement property, by resolving conflicts with the consensus (most frequent) relation (with respect to the input trees) between corresponding taxa subset. However, satisfying such property is NP hard. Existing studies propose various approximations based on matrix or graph representation, or using subtree level decomposition, for supertree construction. Most of these approaches involve high computational complexity. Further, accuracy of most of these methods need to be improved for application in large biological datasets. Current study presents a supertree construction method, named COSPEDTree, by analyzing couplet (taxa pair) relationships and their conflicts (contradictions) with respect to the source trees. To the best of our knowledge, such couplet based supertree construction is not proposed before. To prioritize the consensus relations for resolving individual taxa pairs, a greedy scoring method is suggested. Selected relations between individual taxa pairs are used to model a Directed Acyclic Graph (DAG), which subsequently generates the final supertree. Performance of COSPEDTree, in terms of lower values of branch dissimilarities between the derived supertree and the candidate source trees, are mostly better or comparable with existing methods. COSPEDTree involves worst case time and space complexities of cubic and quadratic orders, respectively, both of which are best among reference approaches. So, it can be used for large biological datasets. It is hosted in http://telemedik.iitkgp.ernet.in/COSPEDTree_BCB.zip.

IDXL: Species Tree Inference Using Internode Distance and Excess Gene Leaf Count

We propose an extension of the distance matrix methods NJst and ASTRID to infer species trees from incongruent gene trees having Incomplete Lineage Sorting. Both approaches consider the average internode distance (ID) between individual taxa pairs as the distance measure. The measure ID does not use the root of a tree, and thus may not always infer the relative position of a taxon with respect to the root. We define a novel distance measure excess gene leaf count (XL) between individual couplets. The XL measure is computed using the root of a tree. It is proved to be additive, and is shown to infer the relative order of divergence among individual couplets better. We propose a novel method IDXL which uses both the XL and ID measures for species tree construction. IDXL is shown to perform better than NJst and other distance matrix approaches for most of the biological and simulated datasets. Having the same computational complexity as NJst, IDXL can be applied for species tree inference on large-scale biological datasets.

Study on life cycle of a sporogenous probiotic bacterium in mammalian gastrointestinal tract with image processing analysis

During different phases of growth cycle, Bacillus coagulans RK-02, a sporogenous probiotic bacterium, exhibits different morphological characteristics. Sequential morphological changes of the bacterium, when grown in a 2 L bioreactor in batch mode, were captured under microscope. Processing of the microscopic images and subsequent computational analysis to extract characteristic features, strictly in numerical values, elucidated a time course of quantitative changes in the cell morphology during batch cultivation. This information was further exploited in deciphering different state of growth of the probiotic bacterium across a pH gradient while passing through gastrointestinal tract (GIT) in mouse model. This study would thus help us to understand the kinetics of growth of B. coagulans RK-02 in mouse GIT and consequently decide the dosage regimen of the probiotic.

COSPEDTree-II: Improved couplet based phylogenetic supertree

Phylogenetic supertrees synthesize a set of phylogenetic trees carrying overlapping taxa set, preferably with the consensus topologies of individual taxa subsets. Supertree construction is an NP-hard problem, and the methods based on decomposition and synthesis of fixed size subtree topologies (such as triplets or quartets) are the most popular. Time and space complexities of these methods, however, depend on the subtree size considered. Our earlier work proposed a couplet (taxa pair) based supertree method COSPEDTree, which produces slightly conservative (not fully resolved) supertrees. Here we propose its improved version COSPEDTree-II, which produces better resolved supertrees with lower number of missing branches, and incurs much lower running time.

Android application for therapeutic feed and fluid calculation in neonatal care - a way to fast, accurate and safe health-care delivery

Delivering medical care to newborn babies in their early days of life, involves complex mathematical calculation for feeding, intravenous fluid and electrolytes requirements. Manual calculation of this process is time consuming and potential source of medical error. This work proposes a standalone Android application for newborn care unit, which can run in any handheld Android device like mobile phones and helps health-care professionals to calculate certain parameters regarding the feed and intravenous fluid to be given to a newborn baby. The parameters are - total fluid intake, Glucose Infusion Rate, energy, protein, lipid amount, electrolytes, etc. Its logic is based on the medical guidelines for feed and fluid management of newborn babies. It maintains consistency in a large set of inter-related variables using an existential abstraction approach excluding the possibility of having wrong proportions of dextrose, protein, lipid or fluid volume by showing error and warning messages wherever needed, which acts as a safety measure to avoid medication errors. The objective of the work is to make the medical calculation process faster, safer and accurate. A prototype of the application is being tested in a Sick Newborn Care Unit (SNCU) in Kolkata,India for evaluation.

Automatic sleep spindle detection in raw EEG signal of newborn babies

In this study, a novel method for automatically detecting sleep spindles from a given raw EEG (Electroencephalogram) data is proposed. We do not use any feature extraction and learning technique. Rather, we model the visual perception of identifying rhythmic peaks within frequency range 11.5–15 Hz. To achieve the performance close to visual detection, we first use a Gaussian window for smoothening of the signal. Then peak detection method is applied for identifying visually distinguishable peaks. If the frequency of peaks lies within frequency range 11.5–15 Hz, then we declare existence of a sleep spindle. Validity of our process is determined by visual scoring of sleep spindles and comparing it with the automatic scoring. We get a specificity range of 89%–98% for a sensitivity range of 87%–96% which is better that any other automatic detection process.