King's College London

Research portal

Learning to see the invisible: A data-driven approach to finding the underlying patterns of abnormality in visually normal brain magnetic resonance images in patients with temporal lobe epilepsy

Research output: Contribution to journalArticle

Standard

Learning to see the invisible : A data-driven approach to finding the underlying patterns of abnormality in visually normal brain magnetic resonance images in patients with temporal lobe epilepsy. / Bennett, Oscar F.; Kanber, Baris; Hoskote, Chandrashekar; Cardoso, M. Jorge; Ourselin, Sebastien; Duncan, John S.; Winston, Gavin P.

In: Epilepsia, Vol. 60, No. 12, 01.12.2019, p. 2499-2507.

Research output: Contribution to journalArticle

Harvard

Bennett, OF, Kanber, B, Hoskote, C, Cardoso, MJ, Ourselin, S, Duncan, JS & Winston, GP 2019, 'Learning to see the invisible: A data-driven approach to finding the underlying patterns of abnormality in visually normal brain magnetic resonance images in patients with temporal lobe epilepsy', Epilepsia, vol. 60, no. 12, pp. 2499-2507. https://doi.org/10.1111/epi.16380

APA

Bennett, O. F., Kanber, B., Hoskote, C., Cardoso, M. J., Ourselin, S., Duncan, J. S., & Winston, G. P. (2019). Learning to see the invisible: A data-driven approach to finding the underlying patterns of abnormality in visually normal brain magnetic resonance images in patients with temporal lobe epilepsy. Epilepsia, 60(12), 2499-2507. https://doi.org/10.1111/epi.16380

Vancouver

Bennett OF, Kanber B, Hoskote C, Cardoso MJ, Ourselin S, Duncan JS et al. Learning to see the invisible: A data-driven approach to finding the underlying patterns of abnormality in visually normal brain magnetic resonance images in patients with temporal lobe epilepsy. Epilepsia. 2019 Dec 1;60(12):2499-2507. https://doi.org/10.1111/epi.16380

Author

Bennett, Oscar F. ; Kanber, Baris ; Hoskote, Chandrashekar ; Cardoso, M. Jorge ; Ourselin, Sebastien ; Duncan, John S. ; Winston, Gavin P. / Learning to see the invisible : A data-driven approach to finding the underlying patterns of abnormality in visually normal brain magnetic resonance images in patients with temporal lobe epilepsy. In: Epilepsia. 2019 ; Vol. 60, No. 12. pp. 2499-2507.

Bibtex Download

@article{0fd4f599ee784588a7df47d35dea7261,
title = "Learning to see the invisible: A data-driven approach to finding the underlying patterns of abnormality in visually normal brain magnetic resonance images in patients with temporal lobe epilepsy",
abstract = "Objective: To find the covert patterns of abnormality in patients with unilateral temporal lobe epilepsy (TLE) and visually normal brain magnetic resonance images (MRI-negative), comparing them to those with visible abnormalities (MRI-positive). Methods: We used multimodal brain MRI from patients with unilateral TLE and employed contemporary machine learning methods to predict the known laterality of seizure onset in 104 subjects (82 MRI-positive, 22 MRI-negative). A visualization approach entitled {"}Importance Maps{"} was developed to highlight image features predictive of seizure laterality in both the MRI-positive and MRI-negative cases. Results: Seizure laterality could be predicted with an area under the receiver operating characteristic curve of 0.981 (95{\%} confidence interval [CI] =0.974-0.989) in MRI-positive and 0.842 (95{\%} CI = 0.736-0.949) in MRI-negative cases. The known image features arising from the hippocampus were the leading predictors of seizure laterality in the MRI-positive cases, whereas widespread temporal lobe abnormalities were revealed in the MRI-negative cases. Significance: Covert abnormalities not discerned on visual reading were detected in MRI-negative TLE, with a spatial pattern involving the whole temporal lobe, rather than just the hippocampus. This suggests that MRI-negative TLE may be associated with subtle but widespread temporal lobe abnormalities. These abnormalities merit close inspection and postacquisition processing if there is no overt lesion.",
keywords = "abnormality, data-driven, epilepsy, machine learning, MRI-negative",
author = "Bennett, {Oscar F.} and Baris Kanber and Chandrashekar Hoskote and Cardoso, {M. Jorge} and Sebastien Ourselin and Duncan, {John S.} and Winston, {Gavin P.}",
year = "2019",
month = "12",
day = "1",
doi = "10.1111/epi.16380",
language = "English",
volume = "60",
pages = "2499--2507",
journal = "Epilepsia",
issn = "0013-9580",
publisher = "Wiley-Blackwell",
number = "12",

}

RIS (suitable for import to EndNote) Download

TY - JOUR

T1 - Learning to see the invisible

T2 - A data-driven approach to finding the underlying patterns of abnormality in visually normal brain magnetic resonance images in patients with temporal lobe epilepsy

AU - Bennett, Oscar F.

AU - Kanber, Baris

AU - Hoskote, Chandrashekar

AU - Cardoso, M. Jorge

AU - Ourselin, Sebastien

AU - Duncan, John S.

AU - Winston, Gavin P.

PY - 2019/12/1

Y1 - 2019/12/1

N2 - Objective: To find the covert patterns of abnormality in patients with unilateral temporal lobe epilepsy (TLE) and visually normal brain magnetic resonance images (MRI-negative), comparing them to those with visible abnormalities (MRI-positive). Methods: We used multimodal brain MRI from patients with unilateral TLE and employed contemporary machine learning methods to predict the known laterality of seizure onset in 104 subjects (82 MRI-positive, 22 MRI-negative). A visualization approach entitled "Importance Maps" was developed to highlight image features predictive of seizure laterality in both the MRI-positive and MRI-negative cases. Results: Seizure laterality could be predicted with an area under the receiver operating characteristic curve of 0.981 (95% confidence interval [CI] =0.974-0.989) in MRI-positive and 0.842 (95% CI = 0.736-0.949) in MRI-negative cases. The known image features arising from the hippocampus were the leading predictors of seizure laterality in the MRI-positive cases, whereas widespread temporal lobe abnormalities were revealed in the MRI-negative cases. Significance: Covert abnormalities not discerned on visual reading were detected in MRI-negative TLE, with a spatial pattern involving the whole temporal lobe, rather than just the hippocampus. This suggests that MRI-negative TLE may be associated with subtle but widespread temporal lobe abnormalities. These abnormalities merit close inspection and postacquisition processing if there is no overt lesion.

AB - Objective: To find the covert patterns of abnormality in patients with unilateral temporal lobe epilepsy (TLE) and visually normal brain magnetic resonance images (MRI-negative), comparing them to those with visible abnormalities (MRI-positive). Methods: We used multimodal brain MRI from patients with unilateral TLE and employed contemporary machine learning methods to predict the known laterality of seizure onset in 104 subjects (82 MRI-positive, 22 MRI-negative). A visualization approach entitled "Importance Maps" was developed to highlight image features predictive of seizure laterality in both the MRI-positive and MRI-negative cases. Results: Seizure laterality could be predicted with an area under the receiver operating characteristic curve of 0.981 (95% confidence interval [CI] =0.974-0.989) in MRI-positive and 0.842 (95% CI = 0.736-0.949) in MRI-negative cases. The known image features arising from the hippocampus were the leading predictors of seizure laterality in the MRI-positive cases, whereas widespread temporal lobe abnormalities were revealed in the MRI-negative cases. Significance: Covert abnormalities not discerned on visual reading were detected in MRI-negative TLE, with a spatial pattern involving the whole temporal lobe, rather than just the hippocampus. This suggests that MRI-negative TLE may be associated with subtle but widespread temporal lobe abnormalities. These abnormalities merit close inspection and postacquisition processing if there is no overt lesion.

KW - abnormality

KW - data-driven

KW - epilepsy

KW - machine learning

KW - MRI-negative

UR - http://www.scopus.com/inward/record.url?scp=85074761828&partnerID=8YFLogxK

U2 - 10.1111/epi.16380

DO - 10.1111/epi.16380

M3 - Article

AN - SCOPUS:85074761828

VL - 60

SP - 2499

EP - 2507

JO - Epilepsia

JF - Epilepsia

SN - 0013-9580

IS - 12

ER -

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454