Epilepsy Lateralization by Elastic Net Regularization of a Diffusion Tensor Imaging Biomarker using Machine Learning
- 1University of Kansas Medical Center
Abstract
Objective: Accurate lateralization of the epileptogenic focus is essential for presurgical evaluation of patients with drug-resistant epilepsy. This study examined whether diffusion tensor imaging (DTI) measures of white matter microstructure, combined with clinical and demographic variables, could classify epilepsy lateralization using machine learning. Methods: We present a retrospective analysis of 334 adult patients undergoing presurgical epilepsy evaluation at the University of Kansas Health System. Fractional anisotropy (FD) and mean diffusivity (MD) were extracted from 36 bilateral white matter tracts and combined with clinical and demographic variables. Several supervised machine learning approaches were evaluated, with elastic net logistic regression selected for detailed analysis. Models classified right-sided, left-sided, and bilateral or generalized epilepsy. Performance was evaluated with area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity as performance metrics. Results: Elastic net models demonstrated good discrimination across classification tasks, with AUC values ranging from 0.76 to 0.88. The strongest performance distinguished left-sided epilepsy from bilateral or generalized epilepsy (AUC = 0.88; accuracy = 0.90; sensitivity = 0.90; specificity = 0.89). Discrimination between unilateral epilepsy and bilateral or generalized epilepsy was also good (AUC = 0.83). Classification of right-sided versus left-sided epilepsy demonstrated lower performance (AUC = 0.76). Significance: DTI-derived white matter features analyzed using a machine learning approach may provide complementary information for epilepsy lateralization during presurgical evaluation. Further studies incorporating other pre-surgical evaluation data into the machine learning model are needed to establish the clinical utility of this approach.
Related
- Diffusion MRI abnormalities localise the epileptogenic zone in paediatric drug-resistant epilepsy
- High-Resolution Parallel-Translation CT Reconstruction Based on a Patch-Based Adaptive-Regularization-Guided Diffusion Model
- A digital biomarker of white-matter routing from diffusion MRI as an early biomarker of Alzheimer's disease
- Quantitative MRI Characterization of Fluid-Related Phenotypes in Pediatric Epilepsy: Deep Learning-Assisted Assessment of Enlarged Perivascular Space Burden, Regional Distribution, and Clinical Associations
- Anatomy-guided U-Net deep learning for sparse-view chest CT reconstruction using spatially varying RTV regularization
BibTeX
@misc{lepping2026epilepsy,
title = {{Epilepsy Lateralization by Elastic Net Regularization of a Diffusion Tensor Imaging Biomarker using Machine Learning}},
author = {R. J. Lepping and M. Pearl and X. Chen and J. Hu and Y. Li and M. Akhter and M. Farrenburg and P. Landazuri and C. M. Pearson},
howpublished = {medRxiv},
year = {2026},
month = nov,
doi = {10.64898/2026.11.03.26367189},
url = {https://www.medrxiv.org/content/10.64898/2026.11.03.26367189v1},
note = {CC BY-NC-ND},
}
RIS
TY - UNPB
TI - Epilepsy Lateralization by Elastic Net Regularization of a Diffusion Tensor Imaging Biomarker using Machine Learning
AU - R. J. Lepping
AU - M. Pearl
AU - X. Chen
AU - J. Hu
AU - Y. Li
AU - M. Akhter
AU - M. Farrenburg
AU - P. Landazuri
AU - C. M. Pearson
PY - 2026
DA - 2026/11/03
PB - medRxiv
DO - 10.64898/2026.11.03.26367189
UR - https://www.medrxiv.org/content/10.64898/2026.11.03.26367189v1
AB - Objective: Accurate lateralization of the epileptogenic focus is essential for presurgical evaluation of patients with drug-resistant epilepsy. This study examined whether diffusion tensor imaging (DTI) measures of white matter microstructure, combined with clinical and demographic variables, could classify epilepsy lateralization using machine learning. Methods: We present a retrospective analysis of 334 adult patients undergoing presurgical epilepsy evaluation at the University of Kansas Health System. Fractional anisotropy (FD) and mean diffusivity (MD) were extracted from 36 bilateral white matter tracts and combined with clinical and demographic variables. Several supervised machine learning approaches were evaluated, with elastic net logistic regression selected for detailed analysis. Models classified right-sided, left-sided, and bilateral or generalized epilepsy. Performance was evaluated with area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity as performance metrics. Results: Elastic net models demonstrated good discrimination across classification tasks, with AUC values ranging from 0.76 to 0.88. The strongest performance distinguished left-sided epilepsy from bilateral or generalized epilepsy (AUC = 0.88; accuracy = 0.90; sensitivity = 0.90; specificity = 0.89). Discrimination between unilateral epilepsy and bilateral or generalized epilepsy was also good (AUC = 0.83). Classification of right-sided versus left-sided epilepsy demonstrated lower performance (AUC = 0.76). Significance: DTI-derived white matter features analyzed using a machine learning approach may provide complementary information for epilepsy lateralization during presurgical evaluation. Further studies incorporating other pre-surgical evaluation data into the machine learning model are needed to establish the clinical utility of this approach.
ER -