Quantitative analysis of structural neuroimaging of mesial temporal lobe epilepsy

Brain morphologic abnormalities in migraine patients: an observational study

Background

Migraine is a common neurological disorder characterized by a complex physiopathology. We assessed brain morphologic differences in migraine and the possible pathogenetic mechanism underlying this disease.

Methods

We analyzed brain morphologic images of migraine patients, 14 with aura (MwA) [the mean (SD) age was 42.36 (2.95) years (range, 37–47)] and 14 without aura (MwoA) [the mean (SD) age was 43.5 (3.25) years (range, 39–50)] during episodic attack compared with health subjects balanced (HS) [the mean (SD) age was 42.5 (5.17) years (range, 34–51)]. All subjects underwent a Magnetic Resonance Imaging (MRI) examination with a scanner operating at 3.0 T and voxel based morphometry (VBM) approach was used to examine the gray matter volume (GMV). The statistical analysis to compare clinicl characteristics was performed using unpaired t-test an one-way Anova. Results: Total cerebral GMV showed a significant difference between MwA and HS (p = 0.02), and between MwoA and HS (p = 0.003). In addition, not significative differences were found between MwA and MwoA groups (p = 0.17). We found three clusters of regions which showed significant GMV reduction in MwA compared with MwoA. MwA subjects showed a less of GMV in 4 clusters if compared with HS, and MwoA subjects showed a less of GMV in 3 clusters if compared with HS. We observed that MwA and MwoA patients had a significant reduction of GMV in the frontal and temporal lobe and the cerebellum, if compared to HS. The bilateral fusiform gyrus and the cingulate gyrus were increase in MwoA patients compared with HS.

Conclusion

Our findings could provide a approach to understand possible differences in the pathogenesis of two type of migraine.

Machine learning for detecting mesial temporal lobe epilepsy by structural and functional neuroimaging

Mesial temporal lobe epilepsy (mTLE), the most common type of focal epilepsy, is associated with functional and structural brain alterations. Machine learning (ML) techniques have been successfully used in discriminating mTLE from healthy controls. However, either functional or structural neuroimaging data are mostly used separately as input, and the opportunity to combine both has not been exploited yet. We conducted a multimodal ML study based on functional and structural neuroimaging measures. We enrolled 37 patients with left mTLE, 37 patients with right mTLE, and 74 healthy controls and trained a support vector ML model to distinguish them by using each measure and the combinations of the measures. For each single measure, we obtained a mean accuracy of 74% and 69% for discriminating left mTLE and right mTLE from controls, respectively, and 64% when all patients were combined. We achieved an accuracy of 78% by integrating functional data and 79% by integrating structural data for left mTLE, and the highest accuracy of 84% was obtained when all functional and structural measures were combined. These findings suggest that combining multimodal measures within a single model is a promising direction for improving the classification of individual patients with mTLE.

An empirical assessment of appearance descriptors applied to MRI for automated diagnosis of TLE and MCI

OBJECTIVE

Differential diagnosis of mild cognitive impairment MCI and temporal lobe epilepsy TLE is a debated issue, specifically because these conditions may coincide in the elderly population. We evaluate automated differential diagnosis based on characteristics derived from structural brain MRI of different brain regions.

METHODS

In 22 healthy controls, 19 patients with MCI, and 17 patients with TLE we used scale invariant feature transform (SIFT), local binary patterns (LBP), and wavelet-based features and investigate their predictive performance for MCI and TLE.

RESULTS

The classification based on SIFT features resulted in an accuracy of 81% of MCI vs. TLE and reasonable generalizability. Local binary patterns yielded satisfactory diagnostic performance with up to 94.74% sensitivity and 88.24% specificity in the right Thalamus for the distinction of MCI vs. TLE, but with limited generalizable. Wavelet features yielded similar results as LPB with 94.74% sensitivity and 82.35% specificity but generalize better.

SIGNIFICANCE

Features beyond volume analysis are a valid approach when applied to specific regions of the brain. Most significant information could be extracted from the thalamus, frontal gyri, and temporal regions, among others. These results suggest that analysis of changes of the central nervous system should not be limited to the most typical regions of interest such as the hippocampus and parahippocampal areas. Region-independent approaches can add considerable information for diagnosis. We emphasize the need to characterize generalizability in future studies, as our results demonstrate that not doing so can lead to overestimation of classification results.

LIMITATIONS

The data used within this study allows for separation of MCI and TLE subjects using a simple age threshold. While we present a strong indication that the presented method is age-invariant and therefore agnostic to this situation, new data would be needed for a rigorous empirical assessment of this findings.

Morphometric MRI features and surgical outcome in patients with epilepsy related to hippocampal sclerosis and low intellectual quotient

OBJECTIVE

The objectives of this study were to verify in a series of patients with mesial temporal lobe epilepsy with hippocampal sclerosis (MTLE-HS) if those with low intellectual quotient (IQ) levels have more extended areas of atrophy compared with those with higher IQ levels and to analyze whether IQ could be a variable implicated on a surgical outcome.

MATERIAL AND METHODS

Patients (n=106) with refractory MTLE-HS submitted to corticoamygdalohippocampectomy (CAH) (57 left mesial temporal lobe epilepsy (MTLE); 45 males) were enrolled. To determine if the IQ was a predictor of seizure outcome, totally seizure-free (SF) versus nonseizure-free (NSF) patients were evaluated. FreeSurfer was used for cortical thickness and volume estimation, comparing groups with lower (<80) and higher IQ (90-109) levels.

RESULTS

In the whole series, 42.45% of patients were SF (Engel Class 1a; n=45), and 57.54% were NSF (n=61). Total cortical volume was significantly reduced in the group with lower IQ (p=0.01). Significant reductions in the left hemisphere included the following: rostral middle frontal (p=0.001), insula (p=0.002), superior temporal gyrus (p=0.003), thalamus (p=0.004), and precentral gyrus (p=0.02); and those in the right hemisphere included the following: rostral middle frontal (p=0.003), pars orbitalis (p=0.01), and insula (p=0.02). Cortical thickness analysis also showed reductions in the right superior parietal gyrus in patients with lower IQ. No significant relationship between IQ and seizure outcome was found.

CONCLUSIONS

This is the first study of a series of patients with pure MTLE-HS, including those with low IQ and their morphometric magnetic resonance imaging (MRI) features using FreeSurfer. Although patients with lower intellectual scores presented more areas of brain atrophy, IQ was not a predictor of surgical outcome. Therefore, when evaluating seizure follow-up, low IQ in patients with MTLE-HS might not contraindicate resective surgery.

Quantitative Evaluation of Medial Temporal Lobe Morphology in Children with Febrile Status Epilepticus: Results of the FEBSTAT Study

BACKGROUND AND PURPOSE

The pathogenesis of febrile status epilepticus is poorly understood, but prior studies have suggested an association with temporal lobe abnormalities, including hippocampal malrotation. We used a quantitative morphometric method to assess the association between temporal lobe morphology and febrile status epilepticus.

MATERIALS AND METHODS

Brain MR imaging was performed in children presenting with febrile status epilepticus and control subjects as part of the Consequences of Prolonged Febrile Seizures in Childhood study. Medial temporal lobe morphologic parameters were measured manually, including the distance of the hippocampus from the midline, hippocampal height:width ratio, hippocampal angle, collateral sulcus angle, and width of the temporal horn.

RESULTS

Temporal lobe morphologic parameters were correlated with the presence of visual hippocampal malrotation; the strongest association was with left temporal horn width (P < .001; adjusted OR, 10.59). Multiple morphologic parameters correlated with febrile status epilepticus, encompassing both the right and left sides. This association was statistically strongest in the right temporal lobe, whereas hippocampal malrotation was almost exclusively left-sided in this cohort. The association between temporal lobe measurements and febrile status epilepticus persisted when the analysis was restricted to cases with visually normal imaging findings without hippocampal malrotation or other visually apparent abnormalities.

CONCLUSIONS

Several component morphologic features of hippocampal malrotation are independently associated with febrile status epilepticus, even when complete hippocampal malrotation is absent. Unexpectedly, this association predominantly involves the right temporal lobe. These findings suggest that a spectrum of bilateral temporal lobe anomalies are associated with febrile status epilepticus in children. Hippocampal malrotation may represent a visually apparent subset of this spectrum.

Individual feature maps: a patient-specific analysis tool with applications in temporal lobe epilepsy

PURPOSE

MRI-based diagnosis of temporal lobe epilepsy (TLE) can be challenging when pathology is not visually evident due to low image contrast or small lesion size. Computer-assisted analyses are able to detect lesions common in a specific patient population, but most techniques do not address clinically relevant individual pathologies resulting from the heterogeneous etiology of the disease. We propose a novel method to supplement the radiological inspection of TLE patients (n = 15) providing patient-specific quantitative assessment.

METHOD

Regions of interest are defined across the brain and volume, relaxometry, and diffusion features are extracted from them. Statistical comparisons between individual patients and a healthy control group (n = 17) are performed on these features, identifying and visualizing significant differences through individual feature maps. Four maps are created per patient showing differences in intensity, asymmetry, and volume.

RESULTS

Detailed reports were generated per patient. Abnormal hippocampal intensity and volume differences were detected in all patients diagnosed with mesial temporal sclerosis (MTS). Abnormal intensities in the temporal cortex were identified in patients with no MTS. A laterality score correctly distinguished left from right TLE in 12 out of 15 patients.

CONCLUSION

The proposed focus on subject-specific quantitative changes has the potential of improving the assessment of TLE patients using MRI techniques, possibly even redefining current imaging protocols for TLE.

Multimodal data and machine learning for surgery outcome prediction in complicated cases of mesial temporal lobe epilepsy

BACKGROUND

This study sought to predict postsurgical seizure freedom from pre-operative diagnostic test results and clinical information using a rapid automated approach, based on supervised learning methods in patients with drug-resistant focal seizures suspected to begin in temporal lobe.

METHOD

We applied machine learning, specifically a combination of mutual information-based feature selection and supervised learning classifiers on multimodal data, to predict surgery outcome retrospectively in 20 presurgical patients (13 female; mean age±SD, in years 33±9.7 for females, and 35.3±9.4 for males) who were diagnosed with mesial temporal lobe epilepsy (MTLE) and subsequently underwent standard anteromesial temporal lobectomy. The main advantage of the present work over previous studies is the inclusion of the extent of ipsilateral neocortical gray matter atrophy and spatiotemporal properties of depth electrode-recorded seizures as training features for individual patient surgery planning.

RESULTS

A maximum relevance minimum redundancy (mRMR) feature selector identified the following features as the most informative predictors of postsurgical seizure freedom in this study's sample of patients: family history of epilepsy, ictal EEG onset pattern (positive correlation with seizure freedom), MRI-based gray matter thickness reduction in the hemisphere ipsilateral to seizure onset, proportion of seizures that first appeared in ipsilateral amygdala to total seizures, age, epilepsy duration, delay in the spread of ipsilateral ictal discharges from site of onset, gender, and number of electrode contacts at seizure onset (negative correlation with seizure freedom). Using these features in combination with a least square support vector machine (LS-SVM) classifier compared to other commonly used classifiers resulted in very high surgical outcome prediction accuracy (95%).

CONCLUSIONS

Supervised machine learning using multimodal compared to unimodal data accurately predicted postsurgical outcome in patients with atypical MTLE.