External evaluation of a deep learning-based approach for automated brain volumetry in patients with huntington's disease.

A crucial step in the clinical adaptation of an AI-based tool is an external, independent validation. The aim of this study was to investigate brain atrophy in patients with confirmed, progressed Huntington's disease using a certified software for automated volumetry and to compare the results with the manual measurement methods used in clinical practice as well as volume calculations of the caudate nuclei based on manual segmentations. Twenty-two patients were included retrospectively, consisting of eleven patients with Huntington's disease and caudate nucleus atrophy and an age- and sex-matched control group. To quantify caudate head atrophy, the frontal horn width to intercaudate distance ratio and the intercaudate distance to inner table width ratio were obtained. The software mdbrain was used for automated volumetry. Manually measured ratios and automatically measured volumes of the groups were compared using two-sample t-tests. Pearson correlation analyses were performed. The relative difference between automatically and manually determined volumes of the caudate nuclei was calculated. Both ratios were significantly different between the groups. The automatically and manually determined volumes of the caudate nuclei showed a high level of agreement with a mean relative discrepancy of - 2.3 ± 5.5%. The Huntington's disease group showed significantly lower volumes in a variety of supratentorial brain structures. The highest degree of atrophy was shown for the caudate nucleus, putamen, and pallidum (all p < .0001). The caudate nucleus volume and the ratios were found to be strongly correlated in both groups. In conclusion, in patients with progressed Huntington's disease, it was shown that the automatically determined caudate nucleus volume correlates strongly with measured ratios commonly used in clinical practice. Both methods allowed clear differentiation between groups in this collective. The software additionally allows radiologists to more objectively assess the involvement of a variety of brain structures that are less accessible to standard semiquantitative methods.

Evidence for interictal blood-brain barrier dysfunction in people with epilepsy.

OBJECTIVE: Interictal blood-brain barrier dysfunction in chronic epilepsy has been demonstrated in animal models and pathological specimens. Ictal blood-brain barrier dysfunction has been shown in humans in vivo using an experimental quantitative magnetic resonance imaging (MRI) protocol. Here, we hypothesized that interictal blood-brain barrier dysfunction is also present in people with drug-resistant epilepsy. METHODS: Thirty-nine people (21 females, mean age at MRI ± SD = 30 ± 8 years) with drug-resistant epilepsy were prospectively recruited and underwent interictal T1-relaxometry before and after administration of a paramagnetic contrast agent. Likewise, quantitative T1 was acquired in 29 people without epilepsy (12 females, age at MRI = 48 ± 18 years). Quantitative T1 difference maps were calculated and served as a surrogate imaging marker for blood-brain barrier dysfunction. Values of quantitative T1 difference maps inside hemispheres ipsilateral to the presumed seizure onset zone were then compared, on a voxelwise level and within presumed seizure onset zones, to the contralateral side of people with epilepsy and to people without epilepsy. RESULTS: Compared to the contralateral side, ipsilateral T1 difference values were significantly higher in white matter (corrected p < .05), gray matter (uncorrected p < .05), and presumed seizure onset zones (p = .04) in people with epilepsy. Compared to people without epilepsy, significantly higher T1 difference values were found in the anatomical vicinity of presumed seizure onset zones (p = .004). A subgroup of people with hippocampal sclerosis demonstrated significantly higher T1 difference values in the ipsilateral hippocampus and in regions strongly interconnected with the hippocampus compared to people without epilepsy (corrected p < .01). Finally, z-scores reflecting the deviation of T1 difference values within the presumed seizure onset zone were associated with verbal memory performance (p = .02) in people with temporal lobe epilepsy. SIGNIFICANCE: Our results indicate a blood-brain barrier dysfunction in drug-resistant epilepsy that is detectable interictally in vivo, anatomically related to the presumed seizure onset zone, and associated with cognitive deficits.

Patterns of subregional cerebellar atrophy across epilepsy syndromes: An ENIGMA-Epilepsy study.

OBJECTIVE: The intricate neuroanatomical structure of the cerebellum is of longstanding interest in epilepsy, but has been poorly characterized within the current corticocentric models of this disease. We quantified cross-sectional regional cerebellar lobule volumes using structural magnetic resonance imaging in 1602 adults with epilepsy and 1022 healthy controls across 22 sites from the global ENIGMA-Epilepsy working group. METHODS: A state-of-the-art deep learning-based approach was employed that parcellates the cerebellum into 28 neuroanatomical subregions. Linear mixed models compared total and regional cerebellar volume in (1) all epilepsies, (2) temporal lobe epilepsy with hippocampal sclerosis (TLE-HS), (3) nonlesional temporal lobe epilepsy, (4) genetic generalized epilepsy, and (5) extratemporal focal epilepsy (ETLE). Relationships were examined for cerebellar volume versus age at seizure onset, duration of epilepsy, phenytoin treatment, and cerebral cortical thickness. RESULTS: Across all epilepsies, reduced total cerebellar volume was observed (d = .42). Maximum volume loss was observed in the corpus medullare (dmax = .49) and posterior lobe gray matter regions, including bilateral lobules VIIB (dmax = .47), crus I/II (dmax = .39), VIIIA (dmax = .45), and VIIIB (dmax = .40). Earlier age at seizure onset ( η ρ max 2 = .05) and longer epilepsy duration ( η ρ max 2 = .06) correlated with reduced volume in these regions. Findings were most pronounced in TLE-HS and ETLE, with distinct neuroanatomical profiles observed in the posterior lobe. Phenytoin treatment was associated with reduced posterior lobe volume. Cerebellum volume correlated with cerebral cortical thinning more strongly in the epilepsy cohort than in controls. SIGNIFICANCE: We provide robust evidence of deep cerebellar and posterior lobe subregional gray matter volume loss in patients with chronic epilepsy. Volume loss was maximal for posterior subregions implicated in nonmotor functions, relative to motor regions of both the anterior and posterior lobe. Associations between cerebral and cerebellar changes, and variability of neuroanatomical profiles across epilepsy syndromes argue for more precise incorporation of cerebellar subregional damage into neurobiological models of epilepsy.

Volumetric gray matter findings in autonomic network regions of people with focal epilepsy.

BACKGROUND AND PURPOSE: Voxel-based morphometry (VBM) studies of people with focal epilepsies revealed gray matter (GM) alterations in brain regions involved in cardiorespiratory regulation, which have been linked to the risk of sudden unexpected death in epilepsy (SUDEP). It remains unclear whether the type and localization of epileptogenic lesions influence the occurrence of such alterations. METHODS: To test the hypothesis that VBM alterations of autonomic network regions are independent of epileptogenic lesions and that they reveal structural underpinnings of SUDEP risk, VBM was performed in 100 people with focal epilepsies without an epileptogenic lesion identifiable on MRI (mean age ± standard deviation = 35 ± 11 years, 56 female). The group was further stratified in high (sample size n = 29) and low risk of SUDEP (n = 71). GM volumes were compared between these two subgroups and to 100 matched controls. RESULTS: People with epilepsy displayed higher GM volume in both amygdalae and parahippocampal gyri and lower GM volume in the cerebellum and occipital (p<.05, familywise error corrected). There were no significant volumetric differences between high and low SUDEP risk subgroups. CONCLUSION: Our findings confirm that autonomic networks are structurally altered in people with focal epilepsy and they question VBM as a suitable method to show structural correlates of the SUDEP risk score.

Subcortical grey matter volume and asymmetry in the long-term course of Rasmussen's encephalitis.

Rasmussen's encephalitis is characterized by drug-resistant focal seizures and chronic inflammation of one hemisphere leading to progressive loss of hemispheric volume. In this cohort study, we aimed to investigate subcortical grey matter volumes and asymmetries in Rasmussen's encephalitis longitudinally in clinically relevant subgroups. We retrospectively included all T1-weighted MRI scans of all people with Rasmussen's encephalitis who were treated at the University Hospital Bonn between 1995 and 2022 (n = 56, 345 scans, median onset 8 years, 36 female). All cases were classified as type 1 (onset ≤ 6 years) or type 2 (onset > 6 years). Subcortical segmentations were performed using FreeSurfer. Longitudinal trajectories of subcortical volumes and hemispheric ratios (ipsi-/contralesional) were assessed using linear mixed-effect models. Unihemispheric cortical degeneration was accompanied by ipsilesional atrophy of the nucleus accumbens, caudate nucleus, putamen, thalamus and contralesional atrophy of the nucleus accumbens and caudate nucleus both in type 1 (all P ≤ 0.014) and type 2 (all P < 0.001). In type 1, however, contralesional volume increase of the amygdala, hippocampus, pallidum and thalamus was found (all P ≤ 0.013). Both ipsilesional and contralesional subcortical atrophies, like cortical atrophy, are most probably caused by neurodegeneration following chronic neuroinflammation. We speculate that contralesional volume increase in type 1 could be related to either neuroplasticity or ongoing acute neuroinflammation, which needs to be investigated in further studies.

Patterns of subregional cerebellar atrophy across epilepsy syndromes: An ENIGMA-Epilepsy study.

Objective: The intricate neuroanatomical structure of the cerebellum is of longstanding interest in epilepsy, but has been poorly characterized within the current cortico-centric models of this disease. We quantified cross-sectional regional cerebellar lobule volumes using structural MRI in 1,602 adults with epilepsy and 1,022 healthy controls across twenty-two sites from the global ENIGMA-Epilepsy working group. Methods: A state-of-the-art deep learning-based approach was employed that parcellates the cerebellum into 28 neuroanatomical subregions. Linear mixed models compared total and regional cerebellar volume in i) all epilepsies; ii) temporal lobe epilepsy with hippocampal sclerosis (TLE-HS); iii) non-lesional temporal lobe epilepsy (TLE-NL); iv) genetic generalised epilepsy; and (v) extra-temporal focal epilepsy (ETLE). Relationships were examined for cerebellar volume versus age at seizure onset, duration of epilepsy, phenytoin treatment, and cerebral cortical thickness. Results: Across all epilepsies, reduced total cerebellar volume was observed (d=0.42). Maximum volume loss was observed in the corpus medullare (dmax=0.49) and posterior lobe grey matter regions, including bilateral lobules VIIB (dmax= 0.47), Crus I/II (dmax= 0.39), VIIIA (dmax=0.45) and VIIIB (dmax=0.40). Earlier age at seizure onset (ηρ2max=0.05) and longer epilepsy duration (ηρ2max=0.06) correlated with reduced volume in these regions. Findings were most pronounced in TLE-HS and ETLE with distinct neuroanatomical profiles observed in the posterior lobe. Phenytoin treatment was associated with reduced posterior lobe volume. Cerebellum volume correlated with cerebral cortical thinning more strongly in the epilepsy cohort than in controls. Significance: We provide robust evidence of deep cerebellar and posterior lobe subregional grey matter volume loss in patients with chronic epilepsy. Volume loss was maximal for posterior subregions implicated in non-motor functions, relative to motor regions of both the anterior and posterior lobe. Associations between cerebral and cerebellar changes, and variability of neuroanatomical profiles across epilepsy syndromes argue for more precise incorporation of cerebellum subregions into neurobiological models of epilepsy.

Globally altered microstructural properties and network topology in Rasmussen's encephalitis.

Rasmussen's encephalitis is an immune-mediated brain disorder characterised by progressive unilateral cerebral atrophy, neuroinflammation, drug-resistant seizures and cognitive decline. However, volumetric changes and epileptiform EEG activity were also observed in the contralateral hemisphere, raising questions about the aetiology of contralateral involvement. In this study, we aim to investigate alterations of white matter integrity, structural network topology and network efficiency in Rasmussen's encephalitis using diffusion-tensor imaging. Fourteen individuals with Rasmussen's encephalitis (11 female, median onset 6 years, range 4-22, median disease duration at MRI 5 years, range 0-42) and 20 healthy control subjects were included. All subjects underwent T1-weighted structural and diffusion-tensor imaging. Diffusion-tensor images were analysed using the fixel-based analysis framework included in the MRtrix3 toolbox. Fibre density and cross-section served as a quantitative measure for microstructural white matter integrity. T1-weighted structural images were processed using FreeSurfer, subcortical segmentations and cortical parcellations using the Desikan-Killiany atlas served as nodes in a structural network model, edge weights were determined based on streamline count between pairs of nodes and compared using network-based statistics. Global efficiency was used to quantify network integration on an intrahemispheric level. All metrics were compared cross-sectionally between individuals with Rasmussen's encephalitis and healthy control subjects using sex and age as regressors and within the Rasmussen's encephalitis group using linear regression including age at onset and disease duration as independent variables. Relative to healthy control subjects, individuals with Rasmussen's encephalitis showed significantly (family-wise-error-corrected P < 0.05) lower fibre density and cross-section as well as edge weights in intrahemispheric connections within the ipsilesional hemisphere and in interhemispheric connections. Lower edge weights were noted in the contralesional hemisphere and in interhemispheric connections, with the latter being mainly affected within the first 2 years after disease onset. With longer disease duration, fibre density and cross-section significantly (uncorrected P < 0.01) decreased in both hemispheres. In the contralesional corticospinal tract, fibre density and cross-section significantly (uncorrected P < 0.01) increased with disease duration. Intrahemispheric edge weights (uncorrected P < 0.01) and global efficiency significantly increased with disease duration in both hemispheres (ipsilesional r = 0.74, P = 0.001; contralesional r = 0.67, P = 0.012). Early disease onset was significantly (uncorrected P < 0.01) negatively correlated with lower fibre density and cross-section bilaterally. Our results show that the disease process of Rasmussen's encephalitis is not limited to the cortex of the lesioned hemisphere but should be regarded as a network disease affecting white matter across the entire brain and causing degenerative as well as compensatory changes on a network level.

An open presurgery MRI dataset of people with epilepsy and focal cortical dysplasia type II.

Automated detection of lesions using artificial intelligence creates new standards in medical imaging. For people with epilepsy, automated detection of focal cortical dysplasias (FCDs) is widely used because subtle FCDs often escape conventional neuroradiological diagnosis. Accurate recognition of FCDs, however, is of outstanding importance for affected people, as surgical resection of the dysplastic cortex is associated with a high chance of postsurgical seizure freedom. Here, we make publicly available a dataset of 85 people affected by epilepsy due to FCD type II and 85 healthy control persons. We publish 3D-T1 and 3D-FLAIR, manually labeled regions of interest, and carefully selected clinical features. The open presurgery MRI dataset may be used to validate existing automated algorithms of FCD detection as well as to create new approaches. Most importantly, it will enable comparability of already existing approaches and support a more widespread use of automated lesion detection tools.

Fundus autofluorescence imaging using red excitation light.

Retinal disease accounts significantly for visual impairment and blindness. An important role in the pathophysiology of retinal disease and aging is attributed to lipofuscin, a complex of fluorescent metabolites. Fundus autofluorescence (AF) imaging allows non-invasive mapping of lipofuscin and is a key technology to diagnose and monitor retinal disease. However, currently used short-wavelength (SW) excitation light has several limitations, including glare and discomfort during image acquisition, reduced image quality in case of lens opacities, limited visualization of the central retina, and potential retinal light toxicity. Here, we establish a novel imaging modality which uses red excitation light (R-AF) and overcomes these drawbacks. R-AF images are high-quality, high-contrast fundus images and image interpretation may build on clinical experience due to similar appearance of pathology as on SW-AF images. Additionally, R-AF images may uncover disease features that previously remained undetected. The R-AF signal increases with higher abundance of lipofuscin and does not depend on photopigment bleaching or on the amount of macular pigment. Improved patient comfort, limited effect of cataract on image quality, and lack of safety concerns qualify R-AF for routine clinical monitoring, e.g. for patients with age-related macular degeneration, Stargardt disease, or for quantitative analysis of AF signal intensity.

A novel geometry-based analysis of hippocampal morphometry in mesial temporal lobe epilepsy.

Hippocampal volumetry is an essential tool in researching and diagnosing mesial temporal lobe epilepsy (mTLE). However, it has a limited ability to detect subtle alterations in hippocampal morphometry. Here, we establish and apply a novel geometry-based tool that enables point-wise morphometric analysis based on an intrinsic coordinate system of the hippocampus. We hypothesized that this point-wise analysis uncovers structural alterations not measurable by volumetry, but associated with histological underpinnings and the neuropsychological profile of mTLE. We conducted a retrospective study in 204 individuals with mTLE and 57 age- and gender-matched healthy subjects. FreeSurfer-based segmentations of hippocampal subfields in 3T-MRI were subjected to a geometry-based analysis that resulted in a coordinate system of the hippocampal mid-surface and allowed for point-wise measurements of hippocampal thickness and other features. Using point-wise analysis, we found significantly lower thickness and higher FLAIR signal intensity in the entire affected hippocampus of individuals with hippocampal sclerosis (HS-mTLE). In the contralateral hippocampus of HS-mTLE and the affected hippocampus of MRI-negative mTLE, we observed significantly lower thickness in the presubiculum. Impaired verbal memory was associated with lower thickness in the left presubiculum. In HS-mTLE histological subtype 3, we observed higher curvature than in subtypes 1 and 2 (all p < .05). These findings could not be observed using conventional volumetry (Bonferroni-corrected p < .05). We show that point-wise measures of hippocampal morphometry can uncover structural alterations not measurable by volumetry while also reflecting histological underpinnings and verbal memory. This substantiates the prospect of their clinical application.

Convolutional Neural Network Algorithm to Determine Lateralization of Seizure Onset in Patients With Epilepsy: A Proof-of-Principle Study.

BACKGROUND AND OBJECTIVES: A new frontier in diagnostic radiology is the inclusion of machine-assisted support tools that facilitate the identification of subtle lesions often not visible to the human eye. Structural neuroimaging plays an essential role in the identification of lesions in patients with epilepsy, which often coincide with the seizure focus. In this study, we explored the potential for a convolutional neural network (CNN) to determine lateralization of seizure onset in patients with epilepsy using T1-weighted structural MRI scans as input. METHODS: Using a dataset of 359 patients with temporal lobe epilepsy (TLE) from 7 surgical centers, we tested whether a CNN based on T1-weighted images could classify seizure laterality concordant with clinical team consensus. This CNN was compared with a randomized model (comparison with chance) and a hippocampal volume logistic regression (comparison with current clinically available measures). Furthermore, we leveraged a CNN feature visualization technique to identify regions used to classify patients. RESULTS: Across 100 runs, the CNN model was concordant with clinician lateralization on average 78% (SD = 5.1%) of runs with the best-performing model achieving 89% concordance. The CNN outperformed the randomized model (average concordance of 51.7%) on 100% of runs with an average improvement of 26.2% and outperformed the hippocampal volume model (average concordance of 71.7%) on 85% of runs with an average improvement of 6.25%. Feature visualization maps revealed that in addition to the medial temporal lobe, regions in the lateral temporal lobe, cingulate, and precentral gyrus aided in classification. DISCUSSION: These extratemporal lobe features underscore the importance of whole-brain models to highlight areas worthy of clinician scrutiny during temporal lobe epilepsy lateralization. This proof-of-concept study illustrates that a CNN applied to structural MRI data can visually aid clinician-led localization of epileptogenic zone and identify extrahippocampal regions that may require additional radiologic attention. CLASSIFICATION OF EVIDENCE: This study provides Class II evidence that in patients with drug-resistant unilateral temporal lobe epilepsy, a convolutional neural network algorithm derived from T1-weighted MRI can correctly classify seizure laterality.

Mesiotemporal Volumetry, Cortical Thickness, and Neuropsychological Deficits in the Long-term Course of Limbic Encephalitis.

BACKGROUND AND OBJECTIVES: Limbic encephalitis (LE) is an autoimmune disease often associated with temporal lobe epilepsy and subacute memory deficits. It is categorized into serologic subgroups, which differ in clinical progress, therapy response, and prognosis. Using longitudinal MRI analysis, we hypothesized that mesiotemporal and cortical atrophy rates would reveal serotype-specific patterns and reflect disease severity. METHODS: In this longitudinal case-control study, all individuals with antibody-positive (glutamic acid decarboxylase 65 [GAD], leucine-rich glioma-inactivated protein 1 [LGI1], contactin-associated protein 2 [CASPR2], and N-methyl-d-aspartate receptor [NMDAR]) nonparaneoplastic LE according to Graus' diagnostic criteria treated between 2005 and 2019 at the University Hospital Bonn were enrolled. A longitudinal healthy cohort was included as the control group. Subcortical segmentation and cortical reconstruction of T1-weighted MRI were performed using the longitudinal framework in FreeSurfer. We applied linear mixed models to examine mesiotemporal volumes and cortical thickness longitudinally. RESULTS: Two hundred fifty-seven MRI scans from 59 individuals with LE (34 female, age at disease onset [mean ± SD] 42.5 ± 20.4 years; GAD: n = 30, 135 scans; LGI1: n = 15, 55 scans; CASPR2: n = 9, 37 scans; and NMDAR: n = 5, 30 scans) were included. The healthy control group consisted of 128 scans from 41 individuals (22 female, age at first scan [mean ± SD] 37.7 ± 14.6 years). The amygdalar volume at disease onset was significantly higher in individuals with LE (p ≤ 0.048 for all antibody subgroups) compared with that in healthy controls and decreased over time in all antibody subgroups, except in the GAD subgroup. We observed a significantly higher hippocampal atrophy rate in all antibody subgroups compared with that in healthy controls (all p ≤ 0.002), except in the GAD subgroup. Cortical atrophy rates exceeded normal aging in individuals with impaired verbal memory, while those who were not impaired did not differ significantly from healthy controls. DISCUSSION: Our data depict higher mesiotemporal volumes in the early disease stage, most likely due to edematous swelling, followed by volume regression and atrophy/hippocampal sclerosis in the late disease stage. Our study reveals a continuous and pathophysiologically meaningful trajectory of mesiotemporal volumetry across all serogroups and provides evidence that LE should be considered a network disorder in which extratemporal involvement is an important determinant of disease severity.

Automatic and manual segmentation of the piriform cortex: Method development and validation in patients with temporal lobe epilepsy and Alzheimer's disease.

The piriform cortex (PC) is located at the junction of the temporal and frontal lobes. It is involved physiologically in olfaction as well as memory and plays an important role in epilepsy. Its study at scale is held back by the absence of automatic segmentation methods on MRI. We devised a manual segmentation protocol for PC volumes, integrated those manually derived images into the Hammers Atlas Database (n = 30) and used an extensively validated method (multi-atlas propagation with enhanced registration, MAPER) for automatic PC segmentation. We applied automated PC volumetry to patients with unilateral temporal lobe epilepsy with hippocampal sclerosis (TLE; n = 174 including n = 58 controls) and to the Alzheimer's Disease Neuroimaging Initiative cohort (ADNI; n = 151, of whom with mild cognitive impairment (MCI), n = 71; Alzheimer's disease (AD), n = 33; controls, n = 47). In controls, mean PC volume was 485 mm3 on the right and 461 mm3 on the left. Automatic and manual segmentations overlapped with a Jaccard coefficient (intersection/union) of ~0.5 and a mean absolute volume difference of ~22 mm3 in healthy controls, ~0.40/ ~28 mm3 in patients with TLE, and ~ 0.34/~29 mm3 in patients with AD. In patients with TLE, PC atrophy lateralised to the side of hippocampal sclerosis (p < .001). In patients with MCI and AD, PC volumes were lower than those of controls bilaterally (p < .001). Overall, we have validated automatic PC volumetry in healthy controls and two types of pathology. The novel finding of early atrophy of PC at the stage of MCI possibly adds a novel biomarker. PC volumetry can now be applied at scale.

MRI-based deep learning can discriminate between temporal lobe epilepsy, Alzheimer's disease, and healthy controls.

BACKGROUND: Radiological identification of temporal lobe epilepsy (TLE) is crucial for diagnosis and treatment planning. TLE neuroimaging abnormalities are pervasive at the group level, but they can be subtle and difficult to identify by visual inspection of individual scans, prompting applications of artificial intelligence (AI) assisted technologies. METHOD: We assessed the ability of a convolutional neural network (CNN) algorithm to classify TLE vs. patients with AD vs. healthy controls using T1-weighted magnetic resonance imaging (MRI) scans. We used feature visualization techniques to identify regions the CNN employed to differentiate disease types. RESULTS: We show the following classification results: healthy control accuracy = 81.54% (SD = 1.77%), precision = 0.81 (SD = 0.02), recall = 0.85 (SD = 0.03), and F1-score = 0.83 (SD = 0.02); TLE accuracy = 90.45% (SD = 1.59%), precision = 0.86 (SD = 0.03), recall = 0.86 (SD = 0.04), and F1-score = 0.85 (SD = 0.04); and AD accuracy = 88.52% (SD = 1.27%), precision = 0.64 (SD = 0.05), recall = 0.53 (SD = 0.07), and F1 score = 0.58 (0.05). The high accuracy in identification of TLE was remarkable, considering that only 47% of the cohort had deemed to be lesional based on MRI alone. Model predictions were also considerably better than random permutation classifications (p < 0.01) and were independent of age effects. CONCLUSIONS: AI (CNN deep learning) can classify and distinguish TLE, underscoring its potential utility for future computer-aided radiological assessments of epilepsy, especially for patients who do not exhibit easily identifiable TLE associated MRI features (e.g., hippocampal sclerosis).

In people with temporal lobe epilepsy, seizures start in a particular part of the brain positioned behind the ears called the temporal lobe. It is difficult for a doctor to detect that a person has temporal lobe epilepsy using brain scans. In this study, we developed a computer model that was able to identify people with temporal lobe epilepsy from scans of their brain. This computer model could be used to help doctors identify temporal lobe epilepsy from brain scans in the future.

Artificial intelligence for the detection of focal cortical dysplasia: Challenges in translating algorithms into clinical practice.

Focal cortical dysplasias (FCDs) are malformations of cortical development and one of the most common pathologies causing pharmacoresistant focal epilepsy. Resective neurosurgery yields high success rates, especially if the full extent of the lesion is correctly identified and completely removed. The visual assessment of magnetic resonance imaging does not pinpoint the FCD in 30%-50% of cases, and half of all patients with FCD are not amenable to epilepsy surgery, partly because the FCD could not be sufficiently localized. Computational approaches to FCD detection are an active area of research, benefitting from advancements in computer vision. Automatic FCD detection is a significant challenge and one of the first clinical grounds where the application of artificial intelligence may translate into an advance for patients' health. The emergence of new methods from the combination of health and computer sciences creates novel challenges. Imaging data need to be organized into structured, well-annotated datasets and combined with other clinical information, such as histopathological subtypes or neuroimaging characteristics. Algorithmic output, that is, model prediction, requires a technically correct evaluation with adequate metrics that are understandable and usable for clinicians. Publication of code and data is necessary to make research accessible and reproducible. This critical review introduces the field of automatic FCD detection, explaining underlying medical and technical concepts, highlighting its challenges and current limitations, and providing a perspective for a novel research environment.

The diagnostic value of ictal SPECT-A retrospective, semiquantitative monocenter study.

OBJECTIVE: Ictal single photon emission computed tomography (SPECT) can be used as an advanced diagnostic modality to detect the seizure onset zone in the presurgical evaluation of people with epilepsy. In addition to visual assessment (VSA) of ictal and interictal SPECT images, postprocessing methods such as ictal-interictal SPECT analysis using SPM (ISAS) can visualize regional ictal blood flow differences. We aimed to evaluate and differentiate the diagnostic value of VSA and ISAS in the Bonn cohort. METHODS: We included 161 people with epilepsy who underwent presurgical evaluation at the University Hospital Bonn between 2008 and 2020 and received ictal and interictal SPECT and ISAS. We retrospectively assigned SPECT findings to one of five categories according to their degree of concordance with the clinical focus hypothesis. RESULTS: Seizure onset zones could be identified more likely on a sublobar concordance level by ISAS than by VSA (31% vs. 19% of cases; OR = 1.88; 95% Cl [1.04, 3.42]; P = 0.03). Both VSA and ISAS more often localized a temporal seizure onset zone than an extratemporal one. Neither VSA nor ISAS findings were predicted by the latency between seizure onset and tracer injection (P = 0.75). In people who underwent successful epilepsy surgery, VSA and ISAS indicated the correct resection site in 54% of individuals, while MRI and EEG showed the correct resection localization in 96% and 33% of individuals, respectively. It was more likely to become seizure-free after epilepsy surgery if ISAS or VSA had been successful. There was no MR-negative case with successful surgery, indicating that ictal SPECT is more useful for confirmation than for localization. SIGNIFICANCE: The results of the most extensive clinical study of ictal SPECT to date allow an assessment of the diagnostic value of this elaborate examination and emphasize the importance of postprocessing routines.

The neurovasculature as a target in temporal lobe epilepsy.

The blood-brain barrier (BBB) is a physiological barrier maintaining a specialized brain micromilieu that is necessary for proper neuronal function. Endothelial tight junctions and specific transcellular/efflux transport systems provide a protective barrier against toxins, pathogens, and immune cells. The barrier function is critically supported by other cell types of the neurovascular unit, including pericytes, astrocytes, microglia, and interneurons. The dysfunctionality of the BBB is a hallmark of neurological diseases, such as ischemia, brain tumors, neurodegenerative diseases, infections, and autoimmune neuroinflammatory disorders. Moreover, BBB dysfunction is critically involved in epilepsy, a brain disorder characterized by spontaneously occurring seizures because of abnormally synchronized neuronal activity. While resistance to antiseizure drugs that aim to reduce neuronal hyperexcitability remains a clinical challenge, drugs targeting the neurovasculature in epilepsy patients have not been explored. The use of novel imaging techniques permits early detection of BBB leakage in epilepsy; however, the detailed mechanistic understanding of causes and consequences of BBB compromise remains unknown. Here, we discuss the current knowledge of BBB involvement in temporal lobe epilepsy with the emphasis on the neurovasculature as a therapeutic target.

A genome-wide association study in autoimmune neurological syndromes with anti-GAD65 autoantibodies.

Autoimmune neurological syndromes (AINS) with autoantibodies against the 65 kDa isoform of the glutamic acid decarboxylase (GAD65) present with limbic encephalitis, including temporal lobe seizures or epilepsy, cerebellitis with ataxia, and stiff-person-syndrome or overlap forms. Anti-GAD65 autoantibodies are also detected in autoimmune diabetes mellitus, which has a strong genetic susceptibility conferred by human leukocyte antigen (HLA) and non-HLA genomic regions. We investigated the genetic predisposition in patients with anti-GAD65 AINS. We performed a genome-wide association study (GWAS) and an association analysis of the HLA region in a large German cohort of 1214 individuals. These included 167 patients with anti-GAD65 AINS, recruited by the German Network for Research on Autoimmune Encephalitis (GENERATE), and 1047 individuals without neurological or endocrine disease as population-based controls. Predictions of protein expression changes based on GWAS findings were further explored and validated in the CSF proteome of a virtually independent cohort of 10 patients with GAD65-AINS and 10 controls. Our GWAS identified 16 genome-wide significant (P < 5 × 10-8) loci for the susceptibility to anti-GAD65 AINS. The top variant, rs2535288 [P = 4.42 × 10-16, odds ratio (OR) = 0.26, 95% confidence interval (CI) = 0.187-0.358], localized to an intergenic segment in the middle of the HLA class I region. The great majority of variants in these loci (>90%) mapped to non-coding regions of the genome. Over 40% of the variants have known regulatory functions on the expression of 48 genes in disease relevant cells and tissues, mainly CD4+ T cells and the cerebral cortex. The annotation of epigenomic marks suggested specificity for neural and immune cells. A network analysis of the implicated protein-coding genes highlighted the role of protein kinase C beta (PRKCB) and identified an enrichment of numerous biological pathways participating in immunity and neural function. Analysis of the classical HLA alleles and haplotypes showed no genome-wide significant associations. The strongest associations were found for the DQA1*03:01-DQB1*03:02-DRB1*04:01HLA haplotype (P = 4.39 × 10-4, OR = 2.5, 95%CI = 1.499-4.157) and DRB1*04:01 allele (P = 8.3 × 10-5, OR = 2.4, 95%CI = 1.548-3.682) identified in our cohort. As predicted, the CSF proteome showed differential levels of five proteins (HLA-A/B, C4A, ATG4D and NEO1) of expression quantitative trait loci genes from our GWAS in the CSF proteome of anti-GAD65 AINS. These findings suggest a strong genetic predisposition with direct functional implications for immunity and neural function in anti-GAD65 AINS, mainly conferred by genomic regions outside the classical HLA alleles.

Temporal lobe epilepsy surgery: Piriform cortex resection impacts seizure control in the long-term.

OBJECTIVE: Recently, we showed that resection of at least 27% of the temporal part of piriform cortex (PiC) strongly correlated with seizure freedom 1 year following selective amygdalo-hippocampectomy (tsSAHE) in patients with mesial temporal lobe epilepsy (mTLE). However, the impact of PiC resection on long-term seizure outcome following tsSAHE is currently unknown. The aim of this study was to evaluate the impact of PiC resection on long-term seizure outcome in patients with mTLE treated with tsSAHE. METHODS: Between 2012 and 2017, 64 patients were included in the retrospective analysis. Long-term follow-up (FU) was defined as at least 2 years postoperatively. Seizure outcome was assessed according to the International League against Epilepsy (ILAE). The resected proportions of hippocampus, amygdala, and PiC were volumetrically assessed. RESULTS: The mean FU duration was 3.75 ± 1.61 years. Patients with ILAE class 1 revealed a significantly larger median proportion of resected PiC compared to patients with ILAE class 2-6 [46% (IQR 31-57) vs. 16% (IQR 6-38), p = 0.001]. Resected proportions of hippocampus and amygdala did not significantly differ for these groups. Among those patients with at least 27% resected proportion of PiC, there were significantly more patients with seizure freedom compared to the patients with <27% resected proportion of PiC (83% vs. 39%, p = 0.0007). CONCLUSIONS: Our results show a strong impact of the extent of PiC resection on long-term seizure outcome following tsSAHE in mTLE. The authors suggest the PiC to constitute a key target volume in tsSAHE to achieve seizure freedom in the long term.

Seizure underreporting in LGI1 and CASPR2 antibody encephalitis.

Patients with anti-leucine-rich glioma-inactivated 1 protein (LGI1) or anti-contactin-associated protein 2 (CASPR2) antibody encephalitis typically present with frequent epileptic seizures. The seizures generally respond well to immunosuppressive therapy, and the long-term seizure outcome seems to be favorable. Consequentially, diagnosing acute symptomatic seizures secondary to autoimmune encephalitis instead of autoimmune epilepsy was proposed. However, published data on long-term seizure outcomes in CASPR2 and LGI1 antibody encephalitis are mostly based on patient reports, and seizure underreporting is a recognized issue. Clinical records from our tertiary epilepsy center were screened retrospectively for patients with LGI1 and CASPR2 antibody encephalitis who reported seizure freedom for at least 3 months and received video-electroencephalography (EEG) for >24 h at follow-up visits. Twenty (LGI1, n = 15; CASPR2, n = 5) of 32 patients with LGI1 (n = 24) and CASPR2 (n = 8) antibody encephalitis fulfilled these criteria. We recorded focal aware and impaired awareness seizures in four of these patients (20%) with reported seizure-free intervals ranging from 3 to 27 months. Our results question the favorable seizure outcome in patients with CASPR2 and LGI1 antibody encephalitis and suggest that the proportion of patients who have persistent seizures may be greater. Our findings underline the importance of prolonged video-EEG telemetry in this population.