The classification of flash visual evoked potential based on deep learning.
Convolutional neural networks
Deep learning
FVEP
Out-of-distribution detection
Journal
BMC medical informatics and decision making
ISSN: 1472-6947
Titre abrégé: BMC Med Inform Decis Mak
Pays: England
ID NLM: 101088682
Informations de publication
Date de publication:
19 01 2023
19 01 2023
Historique:
received:
23
08
2022
accepted:
12
01
2023
entrez:
19
1
2023
pubmed:
20
1
2023
medline:
24
1
2023
Statut:
epublish
Résumé
Visual electrophysiology is an objective visual function examination widely used in clinical work and medical identification that can objectively evaluate visual function and locate lesions according to waveform changes. However, in visual electrophysiological examinations, the flash visual evoked potential (FVEP) varies greatly among individuals, resulting in different waveforms in different normal subjects. Moreover, most of the FVEP wave labelling is performed automatically by a machine, and manually corrected by professional clinical technicians. These labels may have biases due to the individual variations in subjects, incomplete clinical examination data, different professional skills, personal habits and other factors. Through the retrospective study of big data, an artificial intelligence algorithm is used to maintain high generalization abilities in complex situations and improve the accuracy of prescreening. A novel multi-input neural network based on convolution and confidence branching (MCAC-Net) for retinitis pigmentosa RP recognition and out-of-distribution detection is proposed. The MCAC-Net with global and local feature extraction is designed for the FVEP signal that has different local and global information, and a confidence branch is added for out-of-distribution sample detection. For the proposed manual features,a new input layer is added. The model is verified by a clinically collected FVEP dataset, and an accuracy of 90.7% is achieved in the classification task and 93.3% in the out-of-distribution detection task. We built a deep learning-based FVEP classification algorithm that promises to be an excellent tool for screening RP diseases by using FVEP signals.
Sections du résumé
BACKGROUND
Visual electrophysiology is an objective visual function examination widely used in clinical work and medical identification that can objectively evaluate visual function and locate lesions according to waveform changes. However, in visual electrophysiological examinations, the flash visual evoked potential (FVEP) varies greatly among individuals, resulting in different waveforms in different normal subjects. Moreover, most of the FVEP wave labelling is performed automatically by a machine, and manually corrected by professional clinical technicians. These labels may have biases due to the individual variations in subjects, incomplete clinical examination data, different professional skills, personal habits and other factors. Through the retrospective study of big data, an artificial intelligence algorithm is used to maintain high generalization abilities in complex situations and improve the accuracy of prescreening.
METHODS
A novel multi-input neural network based on convolution and confidence branching (MCAC-Net) for retinitis pigmentosa RP recognition and out-of-distribution detection is proposed. The MCAC-Net with global and local feature extraction is designed for the FVEP signal that has different local and global information, and a confidence branch is added for out-of-distribution sample detection. For the proposed manual features,a new input layer is added.
RESULTS
The model is verified by a clinically collected FVEP dataset, and an accuracy of 90.7% is achieved in the classification task and 93.3% in the out-of-distribution detection task.
CONCLUSION
We built a deep learning-based FVEP classification algorithm that promises to be an excellent tool for screening RP diseases by using FVEP signals.
Identifiants
pubmed: 36658545
doi: 10.1186/s12911-023-02107-5
pii: 10.1186/s12911-023-02107-5
pmc: PMC9851116
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
13Subventions
Organisme : The research was supported by the project of Chongqing Science and Technology Bureau
ID : cstc2018jscxmszdX0120
Informations de copyright
© 2023. The Author(s).
Références
Doc Ophthalmol. 2015 Feb;130(1):1-12
pubmed: 25502644
Int J Neural Syst. 2021 Mar;31(3):2130001
pubmed: 33588711
Int J Med Inform. 2021 Dec 20;158:104667
pubmed: 34952282
J Neural Eng. 2018 Dec;15(6):066031
pubmed: 30279309
Doc Ophthalmol. 2018 Aug;137(1):47-56
pubmed: 30027431
Neurodiagn J. 2016;56(4):245-252
pubmed: 28436791
Appl Psychophysiol Biofeedback. 2018 Jun;43(2):153-159
pubmed: 29808441
Bioinformatics. 2006 Jul 15;22(14):e507-13
pubmed: 16873514
Transl Vis Sci Technol. 2019 Nov 20;8(6):21
pubmed: 31788350
Clin Neurophysiol. 2021 Feb;132(2):392-403
pubmed: 33450562
Int J Med Inform. 2022 Aug;164:104791
pubmed: 35594810