Filters








2,175 Hits in 4.4 sec

Monitoring and Diagnosing Neonatal Seizures by Video Signal Processing

Guy Mathurin Kouamou Ntonfo
2014 ELCVIA Electronic Letters on Computer Vision and Image Analysis  
The aim of automatic detection and classification of neonatal seizures through a video camera is not to completely replace the EEG (still required for accurate diagnosis), but to make a realtime, low-cost  ...  Therefore, non-invasive, real-time, automated, low-cost, wide-scale diagnostic methods and equipments capable of reliably recognizing neonatal seizures would be of significant value in the NICUs.  ...  Therefore, we make use of relevant video signal features for the diagnosis of neonatal myoclonic seizures [5] .  ... 
doi:10.5565/rev/elcvia.623 fatcat:z53ws5nz75gqhj4xbvanjpjpji

Automatic detection of epileptic seizures in Neonatal Intensive Care Units through EEG, ECG and video recordings: a survey

B. Olmi, L. Frassineti, A. Lanata, C. Manfredi
2021 IEEE Access  
In Neonatal Intensive Care Units (NICUs), the early detection of neonatal seizures is of utmost importance for a timely, effective and efficient clinical intervention.  ...  Expert systems based on the analysis of EEG, ECG and video recordings are investigated, and their usefulness as support tools for the medical staff in detecting and diagnosing neonatal seizures in NICUs  ...  Identifying and measuring them might allow the use of more specific and useful features for the neonatal seizure detection task through ECG signals.  ... 
doi:10.1109/access.2021.3118227 fatcat:ylikimc2nbcoppbpte3iknpfcm

Real-time automated detection of clonic seizures in newborns

Francesco Pisani, Carlotta Spagnoli, Elena Pavlidis, Carlotta Facini, Guy Mathurin Kouamou Ntonfo, Gianluigi Ferrari, Riccardo Raheli
2014 Clinical Neurophysiology  
Here we describe a new algorithm for real-time, low-cost clonic neonatal seizures detection based on differential average luminance signal analysis.  ...  Significance: It could represent a low-cost, low complexity, real-time automated screening tool for clonic neonatal seizures.  ...  Average motion signal, extracted from a video of a newborn affected by a neonatal seizure (a).  ... 
doi:10.1016/j.clinph.2013.12.119 pmid:24602566 fatcat:nhlnsc7afngdhdk2os74fddm2m

Electrocardiogram Based Neonatal Seizure Detection

Barry R. Greene, Philip de Chazal, Geraldine B. Boylan, Sen Connolly, Richard B. Reilly
2007 IEEE Transactions on Biomedical Engineering  
The results of our ECG-based method are comparable with those reported for EEG-based neonatal seizure detection systems and offer the benefit of an easier acquisition methodology for seizure detection.  ...  The system uses a linear discriminant classifier to process 41 heartbeat timing interval features.  ...  ACKNOWLEDGMENT The authors would like to acknowledge the software contribution of C. O'Brien in the QRS detection. They would also like to acknowledge the useful technical discussions with E. Lalor.  ... 
doi:10.1109/tbme.2006.890137 pmid:17405374 fatcat:npsdqdvfvjdjxolse4nrds6vwq

Heart Rate Variability Analysis for Seizure Detection in Neonatal Intensive Care Units

Benedetta Olmi, Claudia Manfredi, Lorenzo Frassineti, Carlo Dani, Silvia Lori, Giovanna Bertini, Cesarina Cossu, Maria Bastianelli, Simonetta Gabbanini, Antonio Lanatà
2022 Bioengineering  
In Neonatal Intensive Care Units (NICUs), the early detection of neonatal seizures is of utmost importance for a timely clinical intervention.  ...  To the best of our knowledge, our study proposes for the first time a multi-feature ECG-based NSD system that also offers a comparative analysis between babies suffering from seizures and seizure-free  ...  However, there is still room for improvement in HRV features for neonatal seizure detection.  ... 
doi:10.3390/bioengineering9040165 pmid:35447725 pmcid:PMC9031489 fatcat:uzeemujervay5bvmttr5x5pmqq

Dynamic time warping based neonatal seizure detection system

R. Ahmed, A. Temko, W. Marnane, G. Boylan, G. Lighbody
2012 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society  
sequences of feature vectors of neonatal seizures.  ...  The fusion of the two approaches is expected to improve the current state of the art neonatal seizure detection system  ...  Robert Goulding for providing the figure of evolutionary characteristics of a seizure.  ... 
doi:10.1109/embc.2012.6347097 pmid:23367031 dblp:conf/embc/AhmedTMBL12 fatcat:v6dhabzw4raafld2yqpmsbhsqq

Toward a Personalized Real-Time Diagnosis in Neonatal Seizure Detection

Andriy Temko, Achintya Kr. Sarkar, Geraldine B. Boylan, Sean Mathieson, William P. Marnane, Gordon Lightbody
2017 IEEE Journal of Translational Engineering in Health and Medicine  
The problem of creating a personalized seizure detection algorithm for newborns is tackled in this paper.  ...  This is the first study to propose the use of online adaptation without clinical labels, to build a personalized diagnostic system for the detection of neonatal seizures.  ...  Conflict of interest: None of the authors have potential conflicts of interest to be disclosed.  ... 
doi:10.1109/jtehm.2017.2737992 pmid:29021923 pmcid:PMC5633333 fatcat:ydcujixy3bfznpdhd2iu5sspfe

Improved multi-stage neonatal seizure detection using a heuristic classifier and a data-driven post-processor

A.H. Ansari, P.J. Cherian, A. Dereymaeker, V. Matic, K. Jansen, L. De Wispelaere, C. Dielman, J. Vervisch, R.M. Swarte, P. Govaert, G. Naulaers, M. De Vos (+1 others)
2016 Clinical Neurophysiology  
The structure of this post-processor is generic, improves our understanding of the core visually determined EEG features of neonatal seizures and is applicable for other neonatal seizure detectors.  ...  Highlights  An improved neonatal seizure detection method is discussed.  A set of characteristic features of seizures are identified by data-driven methods.  Described core characteristics of neonatal  ...  for real-time implementation.  ... 
doi:10.1016/j.clinph.2016.06.018 pmid:27472536 fatcat:htr3usundbha5p3a3qarimn3iu

EEG-based neonatal seizure detection with Support Vector Machines

A. Temko, E. Thomas, W. Marnane, G. Lightbody, G. Boylan
2011 Clinical Neurophysiology  
Conclusions: The results obtained with the proposed SVM-based seizure detection system allow for its practical application in neonatal intensive care units.  ...  The obtained results may provide a reference for future seizure detection systems.  ...  Feature extraction The features which have been shown to be useful for neonatal seizure detection in a number of papers are extracted for each epoch (Gotman et al., 1997; Aarabi et al., 2007; Faul et  ... 
doi:10.1016/j.clinph.2010.06.034 pmid:20713314 pmcid:PMC3036797 fatcat:kjofrxe63bdr3oa7k62csfzfou

Neonatal seizure detection from raw multi-channel EEG using a fully convolutional architecture

Alison O'Shea, Gordon Lightbody, Geraldine Boylan, Andriy Temko
2020 Neural Networks  
A deep learning classifier for detecting seizures in neonates is proposed.  ...  The seizure detection system utilises only convolutional layers in order to process the multichannel time domain signal and is designed to exploit the large amount of weakly labelled data in the training  ...  When considering the clinical implementation of a neonatal seizure detection algorithm the processing needs to be realizable in real-time.  ... 
doi:10.1016/j.neunet.2019.11.023 pmid:31821947 fatcat:t4gskbbdzvb27og2gnq2itmwby

Neonatal Seizure Detection Using Deep Convolutional Neural Networks

Amir H. Ansari, Perumpillichira J. Cherian, Alexander Caicedo, Gunnar Naulaers, Maarten De Vos, Sabine Van Huffel
2018 International Journal of Neural Systems  
of 77% using a test set of EEG recordings of 22 neonates that also included dubious seizures.  ...  The newly proposed CNN classifier outperformed three data-driven feature-based approaches and performed similar to a previously developed heuristic method.  ...  The computational time is very important for the real-time implementation.  ... 
doi:10.1142/s0129065718500119 pmid:29747532 fatcat:lxnu3iyui5gbnbe7czyyepg3q4

Temporal evolution of seizure burden for automated neonatal EEG classification

A. Temko, N. Stevenson, W. Marnane, G. Boylan, G. Lightbody
2012 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society  
Probabilistic weights are designed from temporal locations of neonatal seizure events relative to time of birth.  ...  The number of false detections per hour is decreased from 0.72 to 0.36, while maintaining the correct detection of seizure burden at 75%.  ...  Fifty-five features were extracted from each channel which represent both time and frequency domain characteristics as well as information theory based parameters.  ... 
doi:10.1109/embc.2012.6347096 pmid:23367030 dblp:conf/embc/TemkoSMBL12 fatcat:2tnhaimxzzgchn733hjtlllaam

A Gaussian mixture model based statistical classification system for neonatal seizure detection

Eoin M. Thomas, Andriy Temko, Gordon Lightbody, William P. Marnane, Geraldine B. Boylan
2009 2009 IEEE International Workshop on Machine Learning for Signal Processing  
A neonatal seizure detection system is proposed based on a Gaussian mixture model classifier.  ...  Linear discriminant analysis and principal component analysis are compared for the task of feature vector preprocessing.  ...  INTRODUCTION An automated neonatal seizure detection system is designed to process physiological measurements from a patient in order to deliver real time alerts to the staff in a neonatal intensive care  ... 
doi:10.1109/mlsp.2009.5306203 fatcat:eho5qouoezcmnihnskzm6vo5ie

Application of Frequency Features of Optical Flow for Event Detection in Video-EEG Monitoring Data

Dmitry Murashov, Yury Obukhov, Ivan Kershner, Mikhail Sinkin
2021 Journal of Biomedical Photonics & Engineering  
It is necessary to obtain features to recognize epileptic seizures and differentiate them from non-epileptic events.  ...  The work is devoted to the study of the frequency features of the optical flow obtained from the video record of long-term videoelectroencephalographic (video-EEG) monitoring data of patients with epilepsy  ...  Acknowledgements This research was carried out within the framework of the state task and was partially supported by the RFBR, grant No 18-29-02035.  ... 
doi:10.18287/jbpe21.07.030301 fatcat:qlifsmw6ifdulmaqlqfpiqo7ky

Inclusion of temporal priors for automated neonatal EEG classification

Andriy Temko, Nathan Stevenson, William Marnane, Geraldine Boylan, Gordon Lightbody
2012 Journal of Neural Engineering  
Probabilistic weights are designed from temporal locations of neonatal seizure events relative to time of birth.  ...  The number of false detections per hour is decreased from 0.45 to 0.25, while maintaining the correct detection of seizure burden at 70%.  ...  Fifty-five features were extracted from each channel which represent both time and frequency domain characteristics as well as information theory based parameters. The features are listed in table 2.  ... 
doi:10.1088/1741-2560/9/4/046002 pmid:22713600 pmcid:PMC3951711 fatcat:rls5h22uxrhrna2mv4k5rlovta
« Previous Showing results 1 — 15 out of 2,175 results