An Automated Detection of Amyotrophic Lateral Sclerosis from Resting State MEG Data Using 3D Deep Convolutional Neural Network

Kaniska Samanta; Sujit Roy; Veronique Marchand-Pauvert; Shirin Dora; Stephanie Duguez; Muskaan Singh; Girijesh Prasad; Saugat Bhattacharyya

doi:10.1109/SMC53992.2023.10393987

An Automated Detection of Amyotrophic Lateral Sclerosis from Resting State MEG Data Using 3D Deep Convolutional Neural Network

Kaniska Samanta, Sujit Roy, Veronique Marchand-Pauvert, Shirin Dora, Stephanie Duguez, Muskaan Singh, Girijesh Prasad, Saugat Bhattacharyya

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

1 Downloads (Pure)

Abstract

A novel 3D deep convolutional neural network (3D-CNN) model called MEGNet3D has been proposed in the paper. MEGNet3D is designed to differentiate between amyotrophic lateral sclerosis (ALS) and healthy individuals from their resting state (eyes open and eyes closed condition) sensor-level magnetoencephalography (MEG) data. The raw MEG data is initially transformed into their time-frequency representation, which are then used as inputs to MEGNet3D. Both magnetometer and gradiometer recordings have been investigated separately. The proposed model exhibits an accuracy of over 75% for most classification conditions. Thus, MEGNet3D is capable of handling high subject variability and shows that spectral-temporal representation of resting-state MEG data yields relevant neural markers related to the existence of ALS. Furthermore, it has also been observed resting state with eyes closed yields better classification accuracy as compared to the resting state with eyes open condition.

Original language	English
Title of host publication	2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)
Subtitle of host publication	Improving the Quality of Life, SMC 2023 - Proceedings
Place of Publication	Oahu, Hawaii, USA
Publisher	IEEE
Pages	3337-3342
Number of pages	6
ISBN (Electronic)	9798350337020
ISBN (Print)	9798350337020
DOIs	https://doi.org/10.1109/SMC53992.2023.10393987
Publication status	Published online - 29 Jan 2024
Event	The 2023 IEEE Conference on Systems, Man, and Cybernetics - Oahu, Honolulu, United States Duration: 1 Oct 2023 → 4 Oct 2023 https://ieeesmc2023.org/

Publication series

Name	Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics
ISSN (Print)	1062-922X

Conference

Conference	The 2023 IEEE Conference on Systems, Man, and Cybernetics
Country/Territory	United States
City	Honolulu
Period	1/10/23 → 4/10/23
Internet address	https://ieeesmc2023.org/

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

Amyotrophic lateral sclerosis (ALS)
vision transformer
deep learning
magnetoencephalography (MEG)

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/SMC53992.2023.10393987

IEEE_SMC_2023__Copy_Author Accepted Manuscript, 2.19 MB

Cite this

Samanta, K., Roy, S., Marchand-Pauvert, V., Dora, S., Duguez, S., Singh, M., Prasad, G., & Bhattacharyya, S. (2024). An Automated Detection of Amyotrophic Lateral Sclerosis from Resting State MEG Data Using 3D Deep Convolutional Neural Network. In 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC): Improving the Quality of Life, SMC 2023 - Proceedings (pp. 3337-3342). (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). IEEE. Advance online publication. https://doi.org/10.1109/SMC53992.2023.10393987

Samanta, Kaniska ; Roy, Sujit ; Marchand-Pauvert, Veronique et al. / An Automated Detection of Amyotrophic Lateral Sclerosis from Resting State MEG Data Using 3D Deep Convolutional Neural Network. 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC): Improving the Quality of Life, SMC 2023 - Proceedings. Oahu, Hawaii, USA : IEEE, 2024. pp. 3337-3342 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics).

@inproceedings{5bc691a2597648d0add8c21c95292ab9,

title = "An Automated Detection of Amyotrophic Lateral Sclerosis from Resting State MEG Data Using 3D Deep Convolutional Neural Network",

abstract = "A novel 3D deep convolutional neural network (3D-CNN) model called MEGNet3D has been proposed in the paper. MEGNet3D is designed to differentiate between amyotrophic lateral sclerosis (ALS) and healthy individuals from their resting state (eyes open and eyes closed condition) sensor-level magnetoencephalography (MEG) data. The raw MEG data is initially transformed into their time-frequency representation, which are then used as inputs to MEGNet3D. Both magnetometer and gradiometer recordings have been investigated separately. The proposed model exhibits an accuracy of over 75% for most classification conditions. Thus, MEGNet3D is capable of handling high subject variability and shows that spectral-temporal representation of resting-state MEG data yields relevant neural markers related to the existence of ALS. Furthermore, it has also been observed resting state with eyes closed yields better classification accuracy as compared to the resting state with eyes open condition.",

keywords = "Amyotrophic lateral sclerosis (ALS), vision transformer, deep learning, magnetoencephalography (MEG)",

author = "Kaniska Samanta and Sujit Roy and Veronique Marchand-Pauvert and Shirin Dora and Stephanie Duguez and Muskaan Singh and Girijesh Prasad and Saugat Bhattacharyya",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; The 2023 IEEE Conference on Systems, Man, and Cybernetics ; Conference date: 01-10-2023 Through 04-10-2023",

year = "2024",

month = jan,

day = "29",

doi = "10.1109/SMC53992.2023.10393987",

language = "English",

isbn = "9798350337020",

series = "Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics",

publisher = "IEEE",

pages = "3337--3342",

booktitle = "2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)",

address = "United States",

url = "https://ieeesmc2023.org/",

}

Samanta, K, Roy, S, Marchand-Pauvert, V, Dora, S, Duguez, S , Singh, M , Prasad, G & Bhattacharyya, S 2024, An Automated Detection of Amyotrophic Lateral Sclerosis from Resting State MEG Data Using 3D Deep Convolutional Neural Network. in 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC): Improving the Quality of Life, SMC 2023 - Proceedings. Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics, IEEE, Oahu, Hawaii, USA, pp. 3337-3342, The 2023 IEEE Conference on Systems, Man, and Cybernetics, Honolulu, Hawaii, United States, 1/10/23. https://doi.org/10.1109/SMC53992.2023.10393987

An Automated Detection of Amyotrophic Lateral Sclerosis from Resting State MEG Data Using 3D Deep Convolutional Neural Network. / Samanta, Kaniska; Roy, Sujit; Marchand-Pauvert, Veronique et al.
2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC): Improving the Quality of Life, SMC 2023 - Proceedings. Oahu, Hawaii, USA: IEEE, 2024. p. 3337-3342 (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics).

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

TY - GEN

T1 - An Automated Detection of Amyotrophic Lateral Sclerosis from Resting State MEG Data Using 3D Deep Convolutional Neural Network

AU - Samanta, Kaniska

AU - Roy, Sujit

AU - Marchand-Pauvert, Veronique

AU - Dora, Shirin

AU - Duguez, Stephanie

AU - Singh, Muskaan

AU - Prasad, Girijesh

AU - Bhattacharyya, Saugat

PY - 2024/1/29

Y1 - 2024/1/29

N2 - A novel 3D deep convolutional neural network (3D-CNN) model called MEGNet3D has been proposed in the paper. MEGNet3D is designed to differentiate between amyotrophic lateral sclerosis (ALS) and healthy individuals from their resting state (eyes open and eyes closed condition) sensor-level magnetoencephalography (MEG) data. The raw MEG data is initially transformed into their time-frequency representation, which are then used as inputs to MEGNet3D. Both magnetometer and gradiometer recordings have been investigated separately. The proposed model exhibits an accuracy of over 75% for most classification conditions. Thus, MEGNet3D is capable of handling high subject variability and shows that spectral-temporal representation of resting-state MEG data yields relevant neural markers related to the existence of ALS. Furthermore, it has also been observed resting state with eyes closed yields better classification accuracy as compared to the resting state with eyes open condition.

AB - A novel 3D deep convolutional neural network (3D-CNN) model called MEGNet3D has been proposed in the paper. MEGNet3D is designed to differentiate between amyotrophic lateral sclerosis (ALS) and healthy individuals from their resting state (eyes open and eyes closed condition) sensor-level magnetoencephalography (MEG) data. The raw MEG data is initially transformed into their time-frequency representation, which are then used as inputs to MEGNet3D. Both magnetometer and gradiometer recordings have been investigated separately. The proposed model exhibits an accuracy of over 75% for most classification conditions. Thus, MEGNet3D is capable of handling high subject variability and shows that spectral-temporal representation of resting-state MEG data yields relevant neural markers related to the existence of ALS. Furthermore, it has also been observed resting state with eyes closed yields better classification accuracy as compared to the resting state with eyes open condition.

KW - Amyotrophic lateral sclerosis (ALS)

KW - vision transformer

KW - deep learning

KW - magnetoencephalography (MEG)

UR - http://www.scopus.com/inward/record.url?scp=85187278759&partnerID=8YFLogxK

UR - https://pure.ulster.ac.uk/en/publications/5bc691a2-5976-48d0-add8-c21c95292ab9

U2 - 10.1109/SMC53992.2023.10393987

DO - 10.1109/SMC53992.2023.10393987

M3 - Conference contribution

AN - SCOPUS:85187278759

SN - 9798350337020

T3 - Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics

SP - 3337

EP - 3342

BT - 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

PB - IEEE

CY - Oahu, Hawaii, USA

T2 - The 2023 IEEE Conference on Systems, Man, and Cybernetics

Y2 - 1 October 2023 through 4 October 2023

ER -

Samanta K, Roy S, Marchand-Pauvert V, Dora S, Duguez S , Singh M et al. An Automated Detection of Amyotrophic Lateral Sclerosis from Resting State MEG Data Using 3D Deep Convolutional Neural Network. In 2023 IEEE International Conference on Systems, Man, and Cybernetics (SMC): Improving the Quality of Life, SMC 2023 - Proceedings. Oahu, Hawaii, USA: IEEE. 2024. p. 3337-3342. (Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics). Epub 2024 Jan 29. doi: 10.1109/SMC53992.2023.10393987

An Automated Detection of Amyotrophic Lateral Sclerosis from Resting State MEG Data Using 3D Deep Convolutional Neural Network

Abstract

Publication series

Conference

Bibliographical note

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this