Maria Eugenia Caligiuri (Italy)
Magna Graecia University Neuroscience Research Center, Department of Medical and Surgical SciencesAuthor Of 2 Presentations
A MULTIMODAL NEUROIMAGING APPROACH TO NON LESIONAL FRONTAL LOBE EPILEPSY
- Pio Zoleo (Italy)
Abstract
Background and Aims:
Frontal Lobe Epilepsy (FLE) is a common form of epilepsy usually caused by structural lesions on frontal areas. Some FLE patients are defined “non-lesional” (nlFLE) because of the absence of clearly identifiable abnormalities on qualitative brain MRI. Our aim was to investigate nlFLE patients to identify possible microstructural abnormalities, through advanced neuroimaging techniques.
Methods:
We enrolled 127 nlFLE patients and 127 age and sex-matched HC. Diagnosis of nfFLE was based on typical ictal semeiology and interictal frontal EEG discharges; all the study participants underwent 3T brain MRI. Voxel-based morphometry (VBM), cortical-thickness (CT), Diffusion-tensor imaging (DTI) and Tract-based spatial statistics (TBSS) were the whole-brain multimodal MRI analyzes performed. We also focused on the corpus callosum (CC), evaluating thickness, fractional anisotropy (FA) and mean diffusivity (MD) from 50 regions of interest along the callosal midsagittal profile.
Results:
VBM analysis revealed regional atrophy in rolandic operculum in nlFLE patients compared to HC (p-value<0.05, TFCE-corrected). TBSS analysis showed significantly increased callosal FA and MD (p-value<0.05, TFCE-corrected) in nlFLE patients compared with controls, especially in sections I (rostrum, genu and rostral body) and III (posterior midbody) of the CC.
Conclusions:
Our study demonstrates that subtle MRI functional and morphological anomalies exist in FLE patients who did not show qualitative brain alterations, and that corpus callosum is one of the most involved cerebral structures. Our results possibly suggest a contribution from white matter alterations to the network abnormalities sustaining frontal lobe seizures, further questioning the traditional concept of epilepsy as a “cortical–only disease”.
RANDOM-FOREST CLASSIFICATION OF PSYCHOGENIC NON-EPILEPTIC SEIZURES AND TEMPORAL LOBE EPILEPSY.
- Maria Eugenia Caligiuri (Italy)
Abstract
Background and Aims:
Psychogenic nonepileptic seizures (PNES) represent a multifactorial psychopathology, which makes diagnosis particularly challenging: PNES can be misdiagnosed as pharmaco-resistant temporal lobe epilepsy (TLE), and approximately 80% of subjects actually undergo anti-epileptic drug (AED) at the time of correct diagnosis. In this study, we used machine learning (ML) to differentiate PNES and TLE patients.
Methods:
Thirty-six PNES subjects and 43 demographically-matched TLE patients underwent neuropsychiatric/neuroimaging assessment. A 10,000-trees random forest (RF) algorithm, considered more robust to overfitting compared to other ML algorithms, was trained on T1-weighted MRI, i.e., on the entire set of morphological metrics obtained through FreeSurfer (cortical thickness, surface, volume, curvature, gyrification index). All features with a mean decrease in Gini index ≥ 0.30 were selected to construct a new classifier with the lowest out-of-bag error (OOB; accuracy = 100 - OOB).
Results:
Figure 1 shows the most important features discriminating PNES from TLE, ranked according to mean Gini Index decrease. This discriminant network included regions across all lobes of the brain, from parietal-occipital regions to frontal regions, as well as the anterior portion of the corpus callosum. Based on these selected features, the RF algorithm was able to distinguish PNES from TLE with an average accuracy of 77.2%.
Conclusions:
This work provides evidence that ML techniques could aid the differential diagnosis of PNES. Involvement of cingulate and orbitofrontal cortices, a frequent finding when comparing PNES to controls, also represented a distinctive feature from TLE patients. This finding supports the hypothesis that PNES subjects experience disrupted processing of emotional information, which might ultimately lead to the insurgence of seizure-like episodes.
Presenter of 1 Presentation
RANDOM-FOREST CLASSIFICATION OF PSYCHOGENIC NON-EPILEPTIC SEIZURES AND TEMPORAL LOBE EPILEPSY.
- Maria Eugenia Caligiuri (Italy)
Abstract
Background and Aims:
Psychogenic nonepileptic seizures (PNES) represent a multifactorial psychopathology, which makes diagnosis particularly challenging: PNES can be misdiagnosed as pharmaco-resistant temporal lobe epilepsy (TLE), and approximately 80% of subjects actually undergo anti-epileptic drug (AED) at the time of correct diagnosis. In this study, we used machine learning (ML) to differentiate PNES and TLE patients.
Methods:
Thirty-six PNES subjects and 43 demographically-matched TLE patients underwent neuropsychiatric/neuroimaging assessment. A 10,000-trees random forest (RF) algorithm, considered more robust to overfitting compared to other ML algorithms, was trained on T1-weighted MRI, i.e., on the entire set of morphological metrics obtained through FreeSurfer (cortical thickness, surface, volume, curvature, gyrification index). All features with a mean decrease in Gini index ≥ 0.30 were selected to construct a new classifier with the lowest out-of-bag error (OOB; accuracy = 100 - OOB).
Results:
Figure 1 shows the most important features discriminating PNES from TLE, ranked according to mean Gini Index decrease. This discriminant network included regions across all lobes of the brain, from parietal-occipital regions to frontal regions, as well as the anterior portion of the corpus callosum. Based on these selected features, the RF algorithm was able to distinguish PNES from TLE with an average accuracy of 77.2%.
Conclusions:
This work provides evidence that ML techniques could aid the differential diagnosis of PNES. Involvement of cingulate and orbitofrontal cortices, a frequent finding when comparing PNES to controls, also represented a distinctive feature from TLE patients. This finding supports the hypothesis that PNES subjects experience disrupted processing of emotional information, which might ultimately lead to the insurgence of seizure-like episodes.