Inception networks, data augmentation and transfer learning in EEG-based photosensitivity diagnosis
Photosensitivity refers to a neurophysiological condition in which the brain generates epileptic discharges known as Photoparoxysmal Responses (PPR) in response to light flashes. In severe cases, these PPR can lead to epileptic seizures. The standardized diagnostic procedure for this condition is ca...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/adb008 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823858286743519232 |
|---|---|
| author | Fernando Moncada Martins Víctor M González José R Villar Beatriz García López Ana Isabel Gómez-Menéndez |
| author_facet | Fernando Moncada Martins Víctor M González José R Villar Beatriz García López Ana Isabel Gómez-Menéndez |
| author_sort | Fernando Moncada Martins |
| collection | DOAJ |
| description | Photosensitivity refers to a neurophysiological condition in which the brain generates epileptic discharges known as Photoparoxysmal Responses (PPR) in response to light flashes. In severe cases, these PPR can lead to epileptic seizures. The standardized diagnostic procedure for this condition is called Intermittent Photic Stimulation. During this procedure, the patient is exposed to a flashing light, aiming to trigger these epileptic reactions while preventing their full development. Meanwhile, brain activity is monitored using Electroencephalography, which is visually analyzed by clinical staff to identify these responses. Hence, the automatic detection of PPR becomes a highly unbalanced problem that has been barely studied in the literature due to photosensitivity’s low prevalence. This research tackles this problem and proposes using Inception-based deep learning (DL) neural networks that, together with transfer learning, are trained in epilepsy seizure detection and tuned in the PPR automatic detection task. A data augmentation (DA) technique is also applied to balance the available data set, evaluating its effects on the DL models. The proposal outperformed state-of-the-art solutions in the literature, achieving higher ratios on standard performance metrics, and with DA significantly improving the Sensitivity without affecting Accuracy and Specificity. This project is currently being developed with patients from Burgos University Hospital, Spain. |
| format | Article |
| id | doaj-art-a3e806c3bdb84987bcbed04bbb4427d0 |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-a3e806c3bdb84987bcbed04bbb4427d02025-02-11T12:29:57ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-016101503410.1088/2632-2153/adb008Inception networks, data augmentation and transfer learning in EEG-based photosensitivity diagnosisFernando Moncada Martins0https://orcid.org/0000-0002-6652-9287Víctor M González1José R Villar2Beatriz García López3Ana Isabel Gómez-Menéndez4Computer Science Department, University of Oviedo , Gijón 33203, Asturias, Spain; Biomedical Engineering Center, University of Oviedo , Gijón 33203, Asturias, SpainElectrical Engineering Department, University of Oviedo , Gijón 33203, Asturias, Spain; Biomedical Engineering Center, University of Oviedo , Gijón 33203, Asturias, SpainComputer Science Department, University of Oviedo , Gijón 33203, Asturias, Spain; Biomedical Engineering Center, University of Oviedo , Gijón 33203, Asturias, SpainClinical Neurophysiology Department, Burgos University Hospital , Burgos 09006, Castilla y León, SpainClinical Neurophysiology Department, Burgos University Hospital , Burgos 09006, Castilla y León, SpainPhotosensitivity refers to a neurophysiological condition in which the brain generates epileptic discharges known as Photoparoxysmal Responses (PPR) in response to light flashes. In severe cases, these PPR can lead to epileptic seizures. The standardized diagnostic procedure for this condition is called Intermittent Photic Stimulation. During this procedure, the patient is exposed to a flashing light, aiming to trigger these epileptic reactions while preventing their full development. Meanwhile, brain activity is monitored using Electroencephalography, which is visually analyzed by clinical staff to identify these responses. Hence, the automatic detection of PPR becomes a highly unbalanced problem that has been barely studied in the literature due to photosensitivity’s low prevalence. This research tackles this problem and proposes using Inception-based deep learning (DL) neural networks that, together with transfer learning, are trained in epilepsy seizure detection and tuned in the PPR automatic detection task. A data augmentation (DA) technique is also applied to balance the available data set, evaluating its effects on the DL models. The proposal outperformed state-of-the-art solutions in the literature, achieving higher ratios on standard performance metrics, and with DA significantly improving the Sensitivity without affecting Accuracy and Specificity. This project is currently being developed with patients from Burgos University Hospital, Spain.https://doi.org/10.1088/2632-2153/adb008photosensitivityepilepsyelectroencephalographyphotoparoxysmal responsedeep learningtransfer learning |
| spellingShingle | Fernando Moncada Martins Víctor M González José R Villar Beatriz García López Ana Isabel Gómez-Menéndez Inception networks, data augmentation and transfer learning in EEG-based photosensitivity diagnosis Machine Learning: Science and Technology photosensitivity epilepsy electroencephalography photoparoxysmal response deep learning transfer learning |
| title | Inception networks, data augmentation and transfer learning in EEG-based photosensitivity diagnosis |
| title_full | Inception networks, data augmentation and transfer learning in EEG-based photosensitivity diagnosis |
| title_fullStr | Inception networks, data augmentation and transfer learning in EEG-based photosensitivity diagnosis |
| title_full_unstemmed | Inception networks, data augmentation and transfer learning in EEG-based photosensitivity diagnosis |
| title_short | Inception networks, data augmentation and transfer learning in EEG-based photosensitivity diagnosis |
| title_sort | inception networks data augmentation and transfer learning in eeg based photosensitivity diagnosis |
| topic | photosensitivity epilepsy electroencephalography photoparoxysmal response deep learning transfer learning |
| url | https://doi.org/10.1088/2632-2153/adb008 |
| work_keys_str_mv | AT fernandomoncadamartins inceptionnetworksdataaugmentationandtransferlearningineegbasedphotosensitivitydiagnosis AT victormgonzalez inceptionnetworksdataaugmentationandtransferlearningineegbasedphotosensitivitydiagnosis AT joservillar inceptionnetworksdataaugmentationandtransferlearningineegbasedphotosensitivitydiagnosis AT beatrizgarcialopez inceptionnetworksdataaugmentationandtransferlearningineegbasedphotosensitivitydiagnosis AT anaisabelgomezmenendez inceptionnetworksdataaugmentationandtransferlearningineegbasedphotosensitivitydiagnosis |