Papers I browsed
A few notes of the papers I read.
Source localization
Verhoeven, Thibault, et al. “Automated Diagnosis of Temporal Lobe Epilepsy in the Absence of Interictal Spikes.” NeuroImage: Clinical, vol. 17, Elsevier, Jan. 2018, pp. 10–15, doi:10.1016/J.NICL.2017.09.021.
- Summary:
- Automatic diagnosis using resting state EEG using directed connectivity and random forest.
- What is the goal of the paper? What is the problem they are trying to solve?
- Diagnosis and Laterization of the TLE patients
- What are the significance?
- functional connectivity using EEG without scalp pathological activity can be used for automatic diagnosis and lateralization of TLE.
- 1 min of artefact-free EEG, extracted from a 10- to 15 min recording, which is less time-consuming than other imaging modalities.
- What are the main technique they are using? How did they solve the problem?
- Using EEG-based directed functional connectivity
- Subjects underwent a resting-state eyes-closed recording during presurgical evaluation.
- Sixty epochs of 1 s, free of artefacts and IEDs, during wakefulness were selected per subject.
- Random forest
- What are the important results or knowledge?
- The hippocampus has a pivotal role in the generation of interictal and ictal activity in the majority of TLE cases.
- What are the problems in the paper?
- What about patients for ILAE3-5, and for those that is not laterizated. Quote: especially in difficult cases where the currently used presurgical evaluation methods are not concordant. –> not true
- How to improve?