Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Dec;60(12):2499-2507.
doi: 10.1111/epi.16380. Epub 2019 Nov 6.

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

Oscar F Bennett  1 , Baris Kanber  1   2   3 , Chandrashekar Hoskote  4 , M Jorge Cardoso  5 , Sebastien Ourselin  5 , John S Duncan  2   3 , Gavin P Winston  2   3   6
Affiliations

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

Oscar F Bennett et al. Epilepsia. 2019 Dec.

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: MRI-negative; abnormality; data-driven; epilepsy; machine learning.

PubMed Disclaimer

Conflict of interest statement

None of the authors has any conflict of interest to disclose. We confirm that we have read the Journal's position on issues involved in ethical publication and affirm that this report is consistent with those guidelines.

Figures

Figure 1
Figure 1
Examples of the magnetic resonance (MR) or MR‐derived image volumes used in the study: a T1‐weighted image volume, a junction map (JM),13 a T2‐weighted image volume, and a fluid‐attenuated inversion recovery (FLAIR) volume
Figure 2
Figure 2
Area under the receiver operating characteristic (ROC) curve measurements obtained using the top n most important features (for n = 1‐70) in the magnetic resonance imaging (MRI)‐positive (left), and MRI‐negative cases (right). The solid blue lines represent the mean area under the ROC curve obtained in Bolstering runs and the dashed lines the edges of the 95% confidence intervals. Maximum lateralization areas under the ROC curve in the MRI‐positive and MRI‐negative cases (indicated on the plots by the vertical dotted black lines) were obtained using the top three and 52, features respectively
Figure 3
Figure 3
Importance Maps for regional volume asymmetry (top), mean intensity asymmetry (middle), and intensity standard deviation asymmetry (bottom) features in each image type across the temporal lobe for magnetic resonance imaging (MRI)‐positive (left) and MRI‐negative cases (right). The intensity of red within the maps signifies the importance assigned to each region. FLAIR, fluid‐attenuated inversion recovery; JM, junction map; L, left; MR, magnetic resonance; R, right
See this image and copyright information in PMC

References

    1. Kwan P, Brodie MJ. Early identification of refractory epilepsy. N Engl J Med. 2000;342:314–9. - PubMed
    1. Duncan JS, Winston GP, Koepp MJ, Ourselin S. Brain imaging in the assessment for epilepsy surgery. Lancet Neurol. 2016;15:420–33. - PMC - PubMed
    1. de Tisi J, Bell GS, Peacock JL, et al. The long‐term outcome of adult epilepsy surgery, patterns of seizure remission, and relapse: a cohort study. Lancet. 2011;378:1388–95. - PubMed
    1. Berkovic SF, McIntosh AM, Kalnins RM,,, et al. Preoperative MRI predicts outcome of temporal lobectomy: an actuarial analysis. Neurology. 1995;45:1358–63. - PubMed
    1. Rudie JD, Colby JB, Salamon N. Machine learning classification of mesial temporal sclerosis in epilepsy patients. Epilepsy Res. 2015;117:63–9. - PubMed

Publication types