Redefining diagnostic lesional status in temporal lobe epilepsy with artificial intelligence
Brain · 03.06.2025 · 148 (6) · 2189-2200
DOI: 10.1093/brain/awaf020 ↗Kurz gefasst
Fachartikel in der Zeitschrift Brain, online erschienen am 22.01.2025. Verfasst von Ezequiel Gleichgerrcht und 17 weiteren Autor:innen. Beteiligte Einrichtung: Department of Neurology, Emory University, Atlanta, GA 30329, USA. Hauptthemen laut MEDLINE: Epilepsy, Temporal Lobe, Artificial Intelligence, Brain, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NINDS NIH HHS, NCATS NIH HHS, NIA NIH HHS.
Abstract (Originalsprache)
Despite decades of advancements in diagnostic MRI, 30%–50% of temporal lobe epilepsy (TLE) patients remain categorized as ‘non-lesional’ (i.e. MRI negative) based on visual assessment by human experts. MRI-negative patients face diagnostic uncertainty and significant delays in treatment planning. Quantitative MRI studies have demonstrated that MRI-negative patients often exhibit a TLE-specific pattern of temporal and limbic atrophy that might be too subtle for the human eye to detect. This signature pattern could be translated successfully into clinical use via advances in artificial intelligence in computer-aided MRI interpretation, thereby improving the detection of brain ‘lesional’ patterns associated with TLE. Here, we tested this hypothesis by using a three-dimensional convolutional neural network applied to a dataset of 1178 scans from 12 different centres, which was able to differentiate TLE from healthy controls with high accuracy (85.9% ± 2.8%), significantly outperforming support vector machines based on hippocampal (74.4% ± 2.6%) and whole-brain (78.3% ± 3.3%) volumes. Our analysis focused subsequently on a subset of patients who achieved sustained seizure freedom post-surgery as a gold standard for confirming TLE. Importantly, MRI-negative patients from this cohort were accurately identified as TLE 82.7% ± 0.9% of the time, an encouraging finding given that clinically these were all patients considered to be MRI negative (i.e. not radiographically different from controls). The saliency maps from the convolutional neural network revealed that limbic structures, particularly medial temporal, cingulate and orbitofrontal areas, were most influential in classification, confirming the importance of the well-established TLE signature atrophy pattern for diagnosis. Indeed, the saliency maps were similar in MRI-positive and MRI-negative TLE groups, suggesting that even when humans cannot distinguish more subtle levels of atrophy, these MRI-negative patients are on the same continuum common across all TLE patients. As such, artificial intelligence can identify TLE lesional patterns, and artificial intelligence-aided diagnosis has the potential to enhance the neuroimaging diagnosis of TLE greatly and to redefine the concept of ‘lesional’ TLE.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Neurology, Emory University, Atlanta, GA 30329, USA.
- Department of Radiation Medicine & Applied Sciences, University of California San Diego, San Diego, CA 92093, USA.
- Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, GA 30303, USA.
- School of Electrical and Computer Engineering (ECE), Georgia Institute of Technology, Atlanta, GA 30332, USA.
- Department of Neurology, Medical University of South Carolina, Charleston, SC 29425, USA.
- Department of Neurology, University of Pennsylvania, Philadelphia, PA 19104, USA.
ORCID-Profile: Ezequiel Gleichgerrcht, Kathryn A Davis, Theodor Rüber
Förderung
- NINDS NIH HHS
- NCATS NIH HHS
- NIA NIH HHS
- NINDS
Zitieren
APA
Gleichgerrcht, E., Kaestner, E., Hassanzadeh, R., Roth, R. W., Parashos, A., Davis, K. A., Bagić, A., Keller, S. S., Rüber, T., Stoub, T., Pardoe, H. R., Dugan, P., Drane, D. L., Abrol, A., Calhoun, V., Kuzniecky, R. I., McDonald, C. R., & Bonilha, L. (2025). Redefining diagnostic lesional status in temporal lobe epilepsy with artificial intelligence. Brain, 148(6), 2189-2200. https://doi.org/10.1093/brain/awaf020
Vancouver
Gleichgerrcht E, Kaestner E, Hassanzadeh R, Roth RW, Parashos A, Davis KA, et al. Redefining diagnostic lesional status in temporal lobe epilepsy with artificial intelligence. Brain. 2025;148(6):2189-2200. doi:10.1093/brain/awaf020
BibTeX
@article{Gleichgerrcht2025,
author = {Gleichgerrcht, Ezequiel and Kaestner, Erik and Hassanzadeh, Reihaneh and Roth, Rebecca W and Parashos, Alexandra and Davis, Kathryn A and Bagić, Anto and Keller, Simon S and Rüber, Theodor and Stoub, Travis and Pardoe, Heath R and Dugan, Patricia and Drane, Daniel L and Abrol, Anees and Calhoun, Vince and Kuzniecky, Ruben I and McDonald, Carrie R and Bonilha, Leonardo},
title = {Redefining diagnostic lesional status in temporal lobe epilepsy with artificial intelligence},
journal = {Brain},
year = {2025},
volume = {148},
number = {6},
pages = {2189--2200},
doi = {10.1093/brain/awaf020}
}
EUVIMED