2021
DOI: 10.1007/978-3-030-87240-3_32
|View full text |Cite|
|
Sign up to set email alerts
|

Transfer Learning of Deep Spatiotemporal Networks to Model Arbitrarily Long Videos of Seizures

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
5
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
4
3
1

Relationship

0
8

Authors

Journals

citations
Cited by 14 publications
(5 citation statements)
references
References 22 publications
0
5
0
Order By: Relevance
“…Some workarounds may include transfer learning and fine-tuning, techniques that first train a model to perform an easy task on an existing, large dataset, and then adjust the model to perform a similar task on the smaller dataset of interest. 44 Abbreviations: 3D, three-dimensional; ANN, artificial neural network; CNN, convolutional neural network; CT, computed tomography; CV, computer vision; FFNN, feed-forward neural network; LSTM, long short-term memory; MRI, magnetic resonance imaging; OF, optical flow; PNN, probabilistic neural network; RNN, recurrent neural network; SVM, support vector machine.…”
Section: Algorithm Descriptionmentioning
confidence: 99%
See 2 more Smart Citations
“…Some workarounds may include transfer learning and fine-tuning, techniques that first train a model to perform an easy task on an existing, large dataset, and then adjust the model to perform a similar task on the smaller dataset of interest. 44 Abbreviations: 3D, three-dimensional; ANN, artificial neural network; CNN, convolutional neural network; CT, computed tomography; CV, computer vision; FFNN, feed-forward neural network; LSTM, long short-term memory; MRI, magnetic resonance imaging; OF, optical flow; PNN, probabilistic neural network; RNN, recurrent neural network; SVM, support vector machine.…”
Section: Algorithm Descriptionmentioning
confidence: 99%
“…A popular type of RNN is LSTM, which is better at learning over longer periods of time than a vanilla RNN and has seen use in many CV algorithms. 26,30,44,59,64,66,67,68,69,70,71,72 (Continues)…”
Section: Rnnsmentioning
confidence: 99%
See 1 more Smart Citation
“…Neural network approaches have previously been applied to video data for distinguishing epileptic seizure type, e.g. mesial temporal versus extra-temporal (Ahmedt-Aristizabal et al, 2018), temporal versus frontal (Karácsony et al, 2020), and focal versus focal to bilateral tonic-clonic seizures (Pérez-García et al, 2021). However, no work to date has focused on deep learning approaches to investigate individual semiologic features.…”
Section: Introductionmentioning
confidence: 99%
“…Currently, most automated analyses of EEGs focus on specific diseases [1,8,17], where labelled EEGs at the onset of disease and normal (healthy) status are collected to train a classifier for prediction of patient status at the level of seconds. However, such automated systems can only help analyze specific diseases and would fail to recognize novel unhealthy statuses which do not appear during classifier training.…”
Section: Introductionmentioning
confidence: 99%