Redefining diagnostic lesional status in temporal lobe epilepsy with artificial intelligence.
Authors
Affiliations (17)
Affiliations (17)
- 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.
- Department of Neurology, University of Pittsburgh, Pittsburgh, PA 15213, USA.
- Department of Pharmacology and Therapeutics, University of Liverpool, Liverpool L69 7ZX, UK.
- The Walton Centre NHS Foundation Trust, Liverpool L9 7LJ, UK.
- Department of Neuroradiology, University Hospital Bonn, Bonn, Germany 53127.
- Department of Epileptology, University Hospital Bonn, Bonn, Germany 53127.
- Department of Neurological Sciences, Rush University, Chicago, IL 60612, USA.
- The Florey Institute of Neuroscience and Mental Health, Victoria VIC 3010, Australia.
- Department of Neurology, New York University Grossman School of Medicine, New York, NY 10017, USA.
- Department of Neurology, School of Medicine at Hofstra/Northwell, Hempstead, NY 10075, USA.
- Department of Psychiatry, University of California San Diego, San Diego, CA 92093, USA.
- Department of Neurology, University of South Carolina, Columbia, SC 29203, USA.
Abstract
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.