Reading Imagined Letter Shapes from the Mind's Eye Using Real-time 7 Tesla fMRI

R. Goebel; R. van Hoof; S. Bhat; M. Luhrs; M. Senden

doi:10.1109/BCI53720.2022.9735031

Reading Imagined Letter Shapes from the Mind's Eye Using Real-time 7 Tesla fMRI

R. Goebel^*, R. van Hoof, S. Bhat, M. Luhrs, M. Senden

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

102 Downloads (Pure)

Abstract

We present a 7 Tesla fMRI proof-of-concept study of the first letter speller BCI that decodes imagined letter shapes from activity patterns in early visual cortical areas. New tools are developed to enable real-time population receptive field retinotopic mapping for encoding and decoding. Using two different letter shapes (H and T), classification performance of generated activity patterns during imagery reaches 80% accuracy in each individual. Using a denoising autoencoder, recognizable letter shapes could be reconstructed and displayed as feedback to participants in the scanner.

Original language	English
Title of host publication	10th International Winter Conference On Brain-computer Interface (Bci2022)
Publisher	IEEE
Number of pages	2
ISBN (Print)	9781665413374
DOIs	https://doi.org/10.1109/BCI53720.2022.9735031
Publication status	Published - 2022
Event	10th International Winter Conference on Brain-Computer Interface (BCI) - High1 resort, Korea, Republic of Duration: 21 Feb 2022 → 23 Feb 2022 https://brain.korea.ac.kr/bci2022/

Publication series

Series	International Winter Conference on Brain-Computer Interface BCI
ISSN	2572-7672

Conference

Conference	10th International Winter Conference on Brain-Computer Interface (BCI)
Abbreviated title	IEEE
Country/Territory	Korea, Republic of
Period	21/02/22 → 23/02/22
Internet address	https://brain.korea.ac.kr/bci2022/

Keywords

fMRI
letter speller
imagery
population receptive fields
denoising autoencoder

Access to Document

10.1109/BCI53720.2022.9735031

Full TextFinal published version, 261 KBLicence: Taverne

Cite this

@inproceedings{32f3b7f397ee413496d41615bc70eb9d,

title = "Reading Imagined Letter Shapes from the Mind's Eye Using Real-time 7 Tesla fMRI",

abstract = "We present a 7 Tesla fMRI proof-of-concept study of the first letter speller BCI that decodes imagined letter shapes from activity patterns in early visual cortical areas. New tools are developed to enable real-time population receptive field retinotopic mapping for encoding and decoding. Using two different letter shapes (H and T), classification performance of generated activity patterns during imagery reaches 80% accuracy in each individual. Using a denoising autoencoder, recognizable letter shapes could be reconstructed and displayed as feedback to participants in the scanner.",

keywords = "fMRI, letter speller, imagery, population receptive fields, denoising autoencoder",

author = "R. Goebel and {van Hoof}, R. and S. Bhat and M. Luhrs and M. Senden",

year = "2022",

doi = "10.1109/BCI53720.2022.9735031",

language = "English",

isbn = "9781665413374",

series = "International Winter Conference on Brain-Computer Interface BCI",

publisher = "IEEE",

booktitle = "10th International Winter Conference On Brain-computer Interface (Bci2022)",

address = "United States",

note = "10th International Winter Conference on Brain-Computer Interface (BCI), IEEE ; Conference date: 21-02-2022 Through 23-02-2022",

url = "https://brain.korea.ac.kr/bci2022/",

}

Goebel, R, van Hoof, R, Bhat, S, Luhrs, M & Senden, M 2022, Reading Imagined Letter Shapes from the Mind's Eye Using Real-time 7 Tesla fMRI. in 10th International Winter Conference On Brain-computer Interface (Bci2022). IEEE, International Winter Conference on Brain-Computer Interface BCI, 10th International Winter Conference on Brain-Computer Interface (BCI), Korea, Republic of, 21/02/22. https://doi.org/10.1109/BCI53720.2022.9735031

Reading Imagined Letter Shapes from the Mind's Eye Using Real-time 7 Tesla fMRI. / Goebel, R.; van Hoof, R.; Bhat, S. et al.
10th International Winter Conference On Brain-computer Interface (Bci2022). IEEE, 2022. (International Winter Conference on Brain-Computer Interface BCI).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceeding › Academic › peer-review

TY - GEN

T1 - Reading Imagined Letter Shapes from the Mind's Eye Using Real-time 7 Tesla fMRI

AU - Goebel, R.

AU - van Hoof, R.

AU - Bhat, S.

AU - Luhrs, M.

AU - Senden, M.

PY - 2022

Y1 - 2022

N2 - We present a 7 Tesla fMRI proof-of-concept study of the first letter speller BCI that decodes imagined letter shapes from activity patterns in early visual cortical areas. New tools are developed to enable real-time population receptive field retinotopic mapping for encoding and decoding. Using two different letter shapes (H and T), classification performance of generated activity patterns during imagery reaches 80% accuracy in each individual. Using a denoising autoencoder, recognizable letter shapes could be reconstructed and displayed as feedback to participants in the scanner.

AB - We present a 7 Tesla fMRI proof-of-concept study of the first letter speller BCI that decodes imagined letter shapes from activity patterns in early visual cortical areas. New tools are developed to enable real-time population receptive field retinotopic mapping for encoding and decoding. Using two different letter shapes (H and T), classification performance of generated activity patterns during imagery reaches 80% accuracy in each individual. Using a denoising autoencoder, recognizable letter shapes could be reconstructed and displayed as feedback to participants in the scanner.

KW - fMRI

KW - letter speller

KW - imagery

KW - population receptive fields

KW - denoising autoencoder

U2 - 10.1109/BCI53720.2022.9735031

DO - 10.1109/BCI53720.2022.9735031

M3 - Conference article in proceeding

SN - 9781665413374

T3 - International Winter Conference on Brain-Computer Interface BCI

BT - 10th International Winter Conference On Brain-computer Interface (Bci2022)

PB - IEEE

T2 - 10th International Winter Conference on Brain-Computer Interface (BCI)

Y2 - 21 February 2022 through 23 February 2022

ER -