Predicting the laterality of temporal lobe epilepsy from PET, MRI, and DTI: A multimodal study
Pre-surgical evaluation of patients with temporal lobe epilepsy (TLE) relies on information obtained from multiple neuroimaging modalities. The relationship between modalities and their combined power in predicting the seizure focus is currently unknown. We investigated asymmetries from three differ...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2015-01-01
|
| Series: | NeuroImage: Clinical |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2213158215001291 |
| _version_ | 1819229232412229632 |
|---|---|
| author | Dorian Pustina Brian Avants Michael Sperling Richard Gorniak Xiaosong He Gaelle Doucet Paul Barnett Scott Mintzer Ashwini Sharan Joseph Tracy |
| author_facet | Dorian Pustina Brian Avants Michael Sperling Richard Gorniak Xiaosong He Gaelle Doucet Paul Barnett Scott Mintzer Ashwini Sharan Joseph Tracy |
| author_sort | Dorian Pustina |
| collection | DOAJ |
| description | Pre-surgical evaluation of patients with temporal lobe epilepsy (TLE) relies on information obtained from multiple neuroimaging modalities. The relationship between modalities and their combined power in predicting the seizure focus is currently unknown. We investigated asymmetries from three different modalities, PET (glucose metabolism), MRI (cortical thickness), and diffusion tensor imaging (DTI; white matter anisotropy) in 28 left and 30 right TLE patients (LTLE and RTLE). Stepwise logistic regression models were built from each modality separately and from all three combined, while bootstrapped methods and split-sample validation verified the robustness of predictions. Among all multimodal asymmetries, three PET asymmetries formed the best predictive model (100% success in full sample, >95% success in split-sample validation). The combinations of PET with other modalities did not perform better than PET alone. Probabilistic classifications were obtained for new clinical cases, which showed correct lateralization for 7/7 new TLE patients (100%) and for 4/5 operated patients with discordant or non-informative PET reports (80%). Metabolism showed closer relationship with white matter in LTLE and closer relationship with gray matter in RTLE. Our data suggest that metabolism is a powerful modality that can predict seizure laterality with high accuracy, and offers high value for automated predictive models. The side of epileptogenic focus can affect the relationship of metabolism with brain structure. The data and tools necessary to obtain classifications for new TLE patients are made publicly available. |
| first_indexed | 2024-12-23T11:09:54Z |
| format | Article |
| id | doaj.art-11424b993080457f8574b26d9d9d6ee6 |
| institution | Directory Open Access Journal |
| issn | 2213-1582 |
| language | English |
| last_indexed | 2024-12-23T11:09:54Z |
| publishDate | 2015-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | NeuroImage: Clinical |
| spelling | doaj.art-11424b993080457f8574b26d9d9d6ee62022-12-21T17:49:22ZengElsevierNeuroImage: Clinical2213-15822015-01-019C203110.1016/j.nicl.2015.07.010Predicting the laterality of temporal lobe epilepsy from PET, MRI, and DTI: A multimodal studyDorian Pustina0Brian Avants1Michael Sperling2Richard Gorniak3Xiaosong He4Gaelle Doucet5Paul Barnett6Scott Mintzer7Ashwini Sharan8Joseph Tracy9Department of Neurology, University of Pennsylvania, Philadelphia, USADepartment of Radiology, University of Pennsylvania, Philadelphia, USADepartment of Neurology, Thomas Jefferson University/Sidney Kimmel Medical College, Philadelphia, PA 19107, USADepartment of Radiology, Thomas Jefferson University/Sidney Kimmel Medical College, Philadelphia, PA 19107, USADepartment of Neurology, Thomas Jefferson University/Sidney Kimmel Medical College, Philadelphia, PA 19107, USADepartment of Neurology, Thomas Jefferson University/Sidney Kimmel Medical College, Philadelphia, PA 19107, USADepartment of Neurology, Thomas Jefferson University/Sidney Kimmel Medical College, Philadelphia, PA 19107, USADepartment of Neurology, Thomas Jefferson University/Sidney Kimmel Medical College, Philadelphia, PA 19107, USADepartment of Neurosurgery, Thomas Jefferson University, Philadelphia, USADepartment of Neurology, Thomas Jefferson University/Sidney Kimmel Medical College, Philadelphia, PA 19107, USAPre-surgical evaluation of patients with temporal lobe epilepsy (TLE) relies on information obtained from multiple neuroimaging modalities. The relationship between modalities and their combined power in predicting the seizure focus is currently unknown. We investigated asymmetries from three different modalities, PET (glucose metabolism), MRI (cortical thickness), and diffusion tensor imaging (DTI; white matter anisotropy) in 28 left and 30 right TLE patients (LTLE and RTLE). Stepwise logistic regression models were built from each modality separately and from all three combined, while bootstrapped methods and split-sample validation verified the robustness of predictions. Among all multimodal asymmetries, three PET asymmetries formed the best predictive model (100% success in full sample, >95% success in split-sample validation). The combinations of PET with other modalities did not perform better than PET alone. Probabilistic classifications were obtained for new clinical cases, which showed correct lateralization for 7/7 new TLE patients (100%) and for 4/5 operated patients with discordant or non-informative PET reports (80%). Metabolism showed closer relationship with white matter in LTLE and closer relationship with gray matter in RTLE. Our data suggest that metabolism is a powerful modality that can predict seizure laterality with high accuracy, and offers high value for automated predictive models. The side of epileptogenic focus can affect the relationship of metabolism with brain structure. The data and tools necessary to obtain classifications for new TLE patients are made publicly available.http://www.sciencedirect.com/science/article/pii/S2213158215001291AsymmetryClassificationMetabolismResectionMachine learning |
| spellingShingle | Dorian Pustina Brian Avants Michael Sperling Richard Gorniak Xiaosong He Gaelle Doucet Paul Barnett Scott Mintzer Ashwini Sharan Joseph Tracy Predicting the laterality of temporal lobe epilepsy from PET, MRI, and DTI: A multimodal study NeuroImage: Clinical Asymmetry Classification Metabolism Resection Machine learning |
| title | Predicting the laterality of temporal lobe epilepsy from PET, MRI, and DTI: A multimodal study |
| title_full | Predicting the laterality of temporal lobe epilepsy from PET, MRI, and DTI: A multimodal study |
| title_fullStr | Predicting the laterality of temporal lobe epilepsy from PET, MRI, and DTI: A multimodal study |
| title_full_unstemmed | Predicting the laterality of temporal lobe epilepsy from PET, MRI, and DTI: A multimodal study |
| title_short | Predicting the laterality of temporal lobe epilepsy from PET, MRI, and DTI: A multimodal study |
| title_sort | predicting the laterality of temporal lobe epilepsy from pet mri and dti a multimodal study |
| topic | Asymmetry Classification Metabolism Resection Machine learning |
| url | http://www.sciencedirect.com/science/article/pii/S2213158215001291 |
| work_keys_str_mv | AT dorianpustina predictingthelateralityoftemporallobeepilepsyfrompetmrianddtiamultimodalstudy AT brianavants predictingthelateralityoftemporallobeepilepsyfrompetmrianddtiamultimodalstudy AT michaelsperling predictingthelateralityoftemporallobeepilepsyfrompetmrianddtiamultimodalstudy AT richardgorniak predictingthelateralityoftemporallobeepilepsyfrompetmrianddtiamultimodalstudy AT xiaosonghe predictingthelateralityoftemporallobeepilepsyfrompetmrianddtiamultimodalstudy AT gaelledoucet predictingthelateralityoftemporallobeepilepsyfrompetmrianddtiamultimodalstudy AT paulbarnett predictingthelateralityoftemporallobeepilepsyfrompetmrianddtiamultimodalstudy AT scottmintzer predictingthelateralityoftemporallobeepilepsyfrompetmrianddtiamultimodalstudy AT ashwinisharan predictingthelateralityoftemporallobeepilepsyfrompetmrianddtiamultimodalstudy AT josephtracy predictingthelateralityoftemporallobeepilepsyfrompetmrianddtiamultimodalstudy |