| 1. |
- Löfhede, Johan, et al.
(author)
-
Comparing a Supervised and an Unsupervised Classification Method for Burst Detection in Neonatal EEG
- 2008
-
In: Proceedings of Engineering in Medicine and Biology Society, EMBS 2008. 30th Annual International Conference of the IEEE, 20-24 August, 2008. - : IEEE. - 1557-170X. - 9781424418145 ; , s. 3836-3839
-
Conference paper (peer-reviewed)abstract
- Hidden Markov Models (HMM) and Support Vector Machines (SVM) using unsupervised and supervised training, respectively, were compared with respect to their ability to correctly classify burst and suppression in neonatal EEG. Each classifier was fed five feature signals extracted from EEG signals from six full term infants who had suffered from perinatal asphyxia. Visual inspection of the EEG by an experienced electroencephalographer was used as the gold standard when training the SVM, and for evaluating the performance of both methods. The results are presented as receiver operating characteristic (ROC) curves and quantified by the area under the curve (AUC). Our study show that the SVM and the HMM exhibit similar performance, despite their fundamental differences.
|
|
| 2. |
|
|
| 3. |
- Flisberg, Anders, 1958, et al.
(author)
-
Does indomethacin for closure of patent ductus arteriosus affect cerebral function?
- 2010
-
In: Acta Paediatrica. - : Wiley. - 0803-5253 .- 1651-2227. ; 99:10, s. 1493-1497
-
Journal article (peer-reviewed)abstract
- Objective: To study whether indomethacin used in conventional dose for closure of patent ductus arteriosus affects cerebral function measured by Electroencephalograms (EEG) evaluated by quantitative measures. Study design: Seven premature neonates with haemodynamically significant persistent ductus arteriosus were recruited. EEG were recorded before, during and after an intravenous infusion of 0.2 mg/kg indomethacin over 10 min. The EEG was analysed by two methods with different degrees of complexity for the amount of low-activity periods (LAP, "suppressions") as an indicator of affection of cerebral function. Results: Neither of the two methods identified any change in the amount of LAPs in the EEG as compared to before the indomethacin infusion. Conclusion: Indomethacin in conventional dose for closure of patent ductus arteriosus does not affect cerebral function as evaluated by quantitative EEG.
|
|
| 4. |
|
|
| 5. |
- Löfhede, Johan, 1978, et al.
(author)
-
Automatic classification of background EEG activity in healthy and sick neonates
- 2010
-
In: Journal of Neural Engineering. - : IOP Publishing. - 1741-2560 .- 1741-2552. ; 7:1
-
Journal article (peer-reviewed)abstract
- The overall aim of our research is to develop methods for a monitoring system to be used at neonatal intensive care units. When monitoring a baby, a range of different types of background activity needs to be considered. In this work, we have developed a scheme for automatic classification of background EEG activity in newborn babies. EEG from six full-term babies who were displaying a burst suppression pattern while suffering from the after-effects of asphyxia during birth was included along with EEG from 20 full-term healthy newborn babies. The signals from the healthy babies were divided into four behavioural states: active awake, quiet awake, active sleep and quiet sleep. By using a number of features extracted from the EEG together with Fisher’s linear discriminant classifier we have managed to achieve 100% correct classification when separating burst suppression EEG from all four healthy EEG types and 93% true positive classification when separating quiet sleep from the other types. The other three sleep stages could not be classified. When the pathological burst suppression pattern was detected, the analysis was taken one step further and the signal was segmented into burst and suppression, allowing clinically relevant parameters such as suppression length and burst suppression ratio to be calculated. The segmentation of the burst suppression EEG works well, with a probability of error around 4%.
|
|
| 6. |
- Löfhede, Johan, 1978
(author)
-
Classification of Burst and Suppression in the Neonatal EEG
- 2007
-
Licentiate thesis (other academic/artistic)abstract
- The brain requires a continuous supply of oxygen and even a short period of reduced oxygen supply risks severe and lifelong consequences for the affected individual. The delivery is a vulnerable period for a baby who may experience for example hypoxia (lack of oxygen) that can damage the brain. Babies who experience problems are placed in an intensive care unit where their vital signs are monitored, but there is no reliable way to monitor the brain directly. Monitoring the brain would provide valuable information about the processes going on in it and could influence the treatment and help to improve the quality of neonatal care. The scope of this project is to develop methods that eventually can be put together to form a monitoring system for the brain that can function as decision-support for the physician in charge of treating the patient.The specific technical problem that is the topic of this thesis is detection of burst and suppression in the electroencephalogram (EEG) signal. The thesis starts with a brief description of the brain, with a focus on where the EEG originates, what types of activity can be found in this signal and what they mean. The data that have been available for the project are described, followed by the signal processing methods that have been used for pre-processing, and the feature functions that can be used for extracting certain types of characteristics from the data are defined. The next section describes classification methodology and how it can be used for making decisions based on combinations of several features extracted from a signal. The classification methods Fisher’s Linear Discriminant, Neural Networks and Support Vector Machines are described and are finally compared with respect to their ability to discriminate between burst and suppression. An experiment with different combinations of features in the classification has also been carried out. The results show similar results for the three methods but it can be seen that the SVM is the best method with respect to handling multiple features.
|
|
| 7. |
- Löfhede, Johan, et al.
(author)
-
Classification of burst and suppression in the neonatal electroencephalogram
- 2008
-
In: Journal of Neural Engineering. - : Institute of Physics Publishing Ltd.. - 1741-2560 .- 1741-2552. ; 5:4, s. 402-410
-
Journal article (peer-reviewed)abstract
- Fisher's linear discriminant (FLD), a feed-forward artificial neural network (ANN) and a support vector machine (SVM) were compared with respect to their ability to distinguish bursts from suppressions in electroencephalograms (EEG) displaying a burst-suppression pattern. Five features extracted from the EEG were used as inputs. The study was based on EEG signals from six full-term infants who had suffered from perinatal asphyxia, and the methods have been trained with reference data classified by an experienced electroencephalographer. The results are summarized as the area under the curve (AUC), derived from receiver operating characteristic (ROC) curves for the three methods. Based on this, the SVM performs slightly better than the others. Testing the three methods with combinations of increasing numbers of the five features shows that the SVM handles the increasing amount of information better than the other methods.
|
|
| 8. |
|
|
| 9. |
|
|
| 10. |
|
|
