Feature extraction from electroencephalograms for Bayesian assessment of newborn brain maturity

Jakaite, Livia; Schetinin, Vitaly; Schult, Joachim

doi:10.1109/cbms.2011.5999109

Cited by 31 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We will expect that the posterior information on EEG features will be effectively used within this strategy and the ensemble of DTs will be refined by discarding those models which exploit weak features. Similarly to the results obtained in our previous research, we will expect that the proposed strategy will reduce a portion of oversized DT models in the ensemble and the uncertainty in assessment will be decreased Jakaite, Schetinin, & Maple 2008).…”

mentioning

confidence: 70%

“…Given a threshold we could find a set of such features and then could refine the ensemble by discarding those DTs which use these weak features. As discussed in (Jakaite, Schetinin, & Maple 2008), gradually increasing a threshold we can discard these DTs while their contribution to the ensemble outcome is negligible. As part of the research we will explore whether such a discarding technique is able to improve the accuracy of Bayesian assessment.…”

Section: Problem Statementmentioning

confidence: 99%

See 1 more Smart Citation

Classification of newborn EEG maturity with Bayesian averaging over decision trees

Schetinin

Jakaite

2012

Expert Systems with Applications

View full text Add to dashboard Cite

-EEG experts can assess a newborn's brain maturity by visual analysis of age-related patterns in sleep EEG. It is highly desirable to make the results of assessment most accurate and reliable. However, the expert analysis is limited in capability to provide the estimate of uncertainty in assessments. Bayesian inference has been shown providing the most accurate estimates of uncertainty by using Markov Chain Monte Carlo (MCMC) integration over the posterior distribution. The use of MCMC enables to approximate the desired distribution by sampling the areas of interests in which the density of distribution is high. In practice, the posterior distribution can be multimodal, and so that the existing MCMC techniques cannot provide the proportional sampling from the areas of interest. The lack of prior information makes MCMC integration more difficult when a model parameter space is large and cannot be explored in detail within a reasonable time. In particular, the lack of information about EEG feature importance can affect the results of Bayesian assessment of EEG maturity. In this paper we explore how the posterior information about EEG feature importance can be used to reduce a negative influence of disproportional sampling on the results of Bayesian assessment. We found that the MCMC integration tends to oversample the areas in which a model parameter space includes one or more features, the importance of which counted in terms of their posterior use is low. Using this finding, we proposed to cure the results of MCMC integration and then described the results of testing the proposed method on a set of sleep EEG recordings.

show abstract

mentioning

confidence: 70%

Section: Problem Statementmentioning

confidence: 99%

Classification of newborn EEG maturity with Bayesian averaging over decision trees

Schetinin

Jakaite

2012

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…К дополнительной ценности 3D-моделирования можно отнести и возможность визуального представления хода оперативного вмешательства для пациента и его семьи, улучшая тем самым взаимосвязь между врачом и пациентом [17]. Дополнительной возможностью метода является оценка индивидуального для пациента риска осложнений [18,19,20]. Получение такой оценки возможно на стадии планирования хирургических вмешательств.…”

Section: Original Research оригинальные исследованияunclassified

3D reconstruction in surgery of hydatid cyst of the liver

Minaev¹,

Gerasimenko²,

Shchetinin³

et al. 2019

Medical news of the North Caucasus

Self Cite

View full text Add to dashboard Cite

Л апароскопический подход в лечении эхинококковых кист печени является одним из быстроразвивающихся направлений в хирургическом лечении данной паразитарной патологии [1]. Вместе с тем предоперационная оценка состояния кисты и планирование хирургической стратегии лечения основаны на лучевых методах визуализации (ультразвуковое исследование (УЗИ), магнитно-резонансная томография (МРТ) и компьютерная томография (КТ)) [2]. К сожалению, в большинстве своем данные диагностические методики обладают возможностью представлять изображение в двух проекциях.Перспективным направлением медицинской визуализации является виртуальная трехмерная (3D) реконструкция с использованием специализированного программного обеспечения, которая позволяет не только лучше представить пространственные вза-имоотношения между кистой и окружающими анатомическими структурами, но и в интерактивной форме изучить хирургическую анатомию до операции [3]. Трехмерная реконструкция позволяет быстро и наглядно представить изображения в 3D, используя стандарт создания, хранения, передачи и визуализации цифровых медицинских изображений (DICOm) из данных, полученных при проведении МРТ или КТ [4].В настоящее время имеется достаточно большое количество исследований, в которых акцентируется полезность и необходимость развития 3D-технологий в медицине, как с образовательной точки зрения, так и для планирования и хирургического обучения [5,6]. К сожалению, работ, оценивающих анатомические особенности желчных и сосудистых изменений, которые возникают под действием паразитарной кисты, а также определяющих возможность уменьшения интраоперационных осложнений (ранений структур © Коллектив авторов, 2019 УДК 616.995.121.36-089.844 Северо-Осетинская государственная медицинская академия, Владикавказ, Россия influence of coBalT chloride on calcium homeosTasis and sYsTemic hemodYnamics under The condiTions of eXPerimenTal hYPercalcemia oganesyan d. h. north ossetian state medical academy, Vladikavkaz, russiaИсследовались концентрации ионизированного и общего кальция крови, кальция и кобальта в костной ткани, функциональное состояние сердечно-сосудистой системы. Экспериментальную гиперкальциемию у крыс создавали путём ежедневного однократного введения препарата «Аквадетрим» в дозировке 3000 МЕ 100 г и 10 % раствора кальция хлорида в дозе 0,3 мл на 200 г массы тела. Хлорид кобальта вводили внутрижелудочно с помощью зонда,

show abstract

“…61 EEG is an important tool for the assessment of brain development in newborns. [62][63][64][65] It has been found that coherent EEG activity during sleep may provide unique insight into maturation processes of brain functional connectivity. Assessments have confirmed that sleep EEG coherence increases across development.…”

Section: Possible Application Areas and Future Workmentioning

confidence: 99%

Feature Extraction with GMDH-Type Neural Networks for EEG-Based Person Identification

Schetinin

Jakaite

Nyah

et al. 2018

Int. J. Neur. Syst.

Self Cite

View full text Add to dashboard Cite

The brain activity observed on EEG electrodes is influenced by volume conduction and functional connectivity of a person performing a task. When the task is a biometric test the EEG signals represent the unique "brain print", which is defined by the functional connectivity that is represented by the interactions between electrodes, whilst the conduction components cause trivial correlations. Orthogonalization using autoregressive modeling minimizes the conduction components, and then the residuals are related to features correlated with the functional connectivity. However, the orthogonalization can be unreliable for high-dimensional EEG data. We have found that the dimensionality can be significantly reduced if the baselines required for estimating the residuals can be modeled by using relevant electrodes. In our approach, the required models are learnt by a Group Method of Data Handling (GMDH) algorithm which we have made capable of discovering reliable models from multidimensional EEG data. In our experiments on the EEG-MMI benchmark data which include 109 participants, the proposed method has correctly identified all the subjects and provided a statistically significant ([Formula: see text]) improvement of the identification accuracy. The experiments have shown that the proposed GMDH method can learn new features from multi-electrode EEG data, which are capable to improve the accuracy of biometric identification.

show abstract

Feature extraction from electroencephalograms for Bayesian assessment of newborn brain maturity

Abstract: Abstract

Cited by 31 publications

References 19 publications

Classification of newborn EEG maturity with Bayesian averaging over decision trees

Classification of newborn EEG maturity with Bayesian averaging over decision trees

3D reconstruction in surgery of hydatid cyst of the liver

Feature Extraction with GMDH-Type Neural Networks for EEG-Based Person Identification

Contact Info

Product

Resources

About