Search

Emerging evidence suggests brain white matter alterations in adolescents with early-onset psychosis (EOP; age of onset d = 0.37), posterior corona radiata (d = 0.32), and superior fronto‐occipital fasciculus (d = 0.31). We also found widespread higher RD and more localized higher MD and AD. We detected significant effects of diagnostic subgroup, sex, and duration of illness, but not medication status. Using the largest EOP DTI sample to date, our findings suggest a profile of widespread white matter microstructure alterations in adolescents with EOP, most prominently in male individuals with early-onset schizophrenia and individuals with a shorter duration of illness.

BackgroundEmerging evidence suggests brain white matter alterations in adolescents with early-onset psychosis (EOP; age of onset MethodsOur sample included 321 adolescents with EOP (mean age: 16.3 ± 1.4 years, 46.4% females) and 265 adolescent CTR (mean age: 16.0 ± 1.7 years, 57.7% females) pooled from nine sites. All sites extracted mean fractional anisotropy (FA), mean diffusivity (MD), radial diffusivity (RD), and axial diffusivity (AD) for 25 white matter regions of interest per participant. ComBat harmonization was performed for all DTI measures to adjust for scanner differences. Multiple linear regression models were fitted to investigate case-control differences and associations with clinical variables in regional DTI measures.ResultsWe found widespread lower FA in EOP compared to CTR, with the largest effect sizes in the superior longitudinal fasciculus (Cohen’s d = 0.37), posterior corona radiata (d = 0.32), and superior fronto□occipital fasciculus (d = 0.31). We also found widespread higher RD and more localized higher MD and AD. We detected significant effects of diagnostic subgroup, sex, and duration of illness, but not medication status.ConclusionUsing the largest EOP DTI sample to date, our findings suggest a profile of widespread white matter microstructure alterations in adolescents with EOP, most prominently in male patients with early-onset schizophrenia and patients with a shorter duration of illness.

One outstanding challenge for machine learning in diagnostic biomedical imaging is algorithm interpretability. A key application is the identification of subtle epileptogenic focal cortical dysplasias (FCDs) from structural MRI. FCDs are difficult to visualize on structural MRI but are often amenable to surgical resection. We aimed to develop an open-source, interpretable, surface-based machine-learning algorithm to automatically identify FCDs on heterogeneous structural MRI data from epilepsy surgery centres worldwide. The Multi-centre Epilepsy Lesion Detection (MELD) Project collated and harmonized a retrospective MRI cohort of 1015 participants, 618 patients with focal FCD-related epilepsy and 397 controls, from 22 epilepsy centres worldwide. We created a neural network for FCD detection based on 33 surface-based features. The network was trained and cross-validated on 50% of the total cohort and tested on the remaining 50% as well as on 2 independent test sites. Multidimensional feature analysis and integrated gradient saliencies were used to interrogate network performance. Our pipeline outputs individual patient reports, which identify the location of predicted lesions, alongside their imaging features and relative saliency to the classifier. On a restricted ‘gold-standard’ subcohort of seizure-free patients with FCD type IIB who had T1 and fluid-attenuated inversion recovery MRI data, the MELD FCD surface-based algorithm had a sensitivity of 85%. Across the entire withheld test cohort the sensitivity was 59% and specificity was 54%. After including a border zone around lesions, to account for uncertainty around the borders of manually delineated lesion masks, the sensitivity was 67%. This multicentre, multinational study with open access protocols and code has developed a robust and interpretable machine-learning algorithm for automated detection of focal cortical dysplasias, giving physicians greater confidence in the identification of subtle MRI lesions in individuals with epilepsy.

Funder: National Institute for Health Research (NIHR) GOSH BRC, OBJECTIVE: Drug-resistant focal epilepsy is often caused by focal cortical dysplasias (FCDs). The distribution of these lesions across the cerebral cortex and the impact of lesion location on clinical presentation and surgical outcome are largely unknown. We created a neuroimaging cohort of patients with individually mapped FCDs to determine factors associated with lesion location and predictors of postsurgical outcome. METHODS: The MELD (Multi-centre Epilepsy Lesion Detection) project collated a retrospective cohort of 580 patients with epilepsy attributed to FCD from 20 epilepsy centers worldwide. Magnetic resonance imaging-based maps of individual FCDs with accompanying demographic, clinical, and surgical information were collected. We mapped the distribution of FCDs, examined for associations between clinical factors and lesion location, and developed a predictive model of postsurgical seizure freedom. RESULTS: FCDs were nonuniformly distributed, concentrating in the superior frontal sulcus, frontal pole, and temporal pole. Epilepsy onset was typically before the age of 10 years. Earlier epilepsy onset was associated with lesions in primary sensory areas, whereas later epilepsy onset was associated with lesions in association cortices. Lesions in temporal and occipital lobes tended to be larger than frontal lobe lesions. Seizure freedom rates varied with FCD location, from around 30% in visual, motor, and premotor areas to 75% in superior temporal and frontal gyri. The predictive model of postsurgical seizure freedom had a positive predictive value of 70% and negative predictive value of 61%. SIGNIFICANCE: FCD location is an important determinant of its size, the age at epilepsy onset, and the likelihood of seizure freedom postsurgery. Our atlas of lesion locations can be used to guide the radiological search for subtle lesions in individual patients. Our atlas of regional seizure freedom rates and associated predictive model can be used to estimate individual likelihoods of postsurgical seizure freedom. Data-driven atlases and predictive models are essential for evidence-based, precision medicine and risk counseling in epilepsy.

IntroductionOne outstanding challenge for machine learning in diagnostic biomedical imaging is algorithm interpretability. A key application is the identification of subtle epileptogenic focal cortical dysplasias (FCDs) from structural MRI. FCDs are difficult to visualise on structural MRI but are often amenable to surgical resection. We aimed to develop an open-source, interpretable, surface-based machine-learning algorithm to automatically identify FCDs on heterogeneous structural MRI data from epilepsy surgery centres worldwide.MethodsThe Multi-centre Epilepsy Lesion Detection (MELD) Project collated and harmonised a retrospective MRI cohort of 1015 participants, 618 patients with focal FCD-related epilepsy and 397 controls, from 22 epilepsy centres worldwide. We created a neural network for FCD detection based on 33 surface-based features. The network was trained and cross-validated on 50% of the total cohort and tested on the remaining 50% as well as on 2 independent test sites. Multidimensional feature analysis and integrated gradient saliencies were used to interrogate network performance.ResultsOur pipeline outputs individual patient reports, which identify the location of predicted lesions, alongside their imaging features and relative saliency to the classifier. Overall, after including a border-zone around lesions, the developed MELD FCD surface-based algorithm had a sensitivity of 67% and a specificity of 54% on the withheld test cohort, and a sensitivity of 85% on a restricted subcohort of seizure free patients with FCD type IIB who had T1 and FLAIR MRI data.ConclusionsThis multicentre, multinational study with open access protocols and code has developed a robust and interpretable machine-learning algorithm for automated detection of focal cortical dysplasias, giving physicians greater confidence in the identification of subtle MRI lesions.HighlightsThis large, multi-centre, multi-scanner neuroimaging cohort captures the heterogeneity of histopathological subtypes and imaging features of patients with FCD.We developed a robust and interpretable surface-based algorithm which detects FCDs with a sensitivity of 67% and a specificity of 54%.The algorithm generates individual patient reports that “open the AI black-box” highlighting predicted lesion locations, alongside the imaging features and their relative saliency to the classifier.

Glutamic acid decarboxylase 65 antibodies (anti-GAD65) have been found in patients with late-onset chronic temporal lobe epilepsy (TLE). No prior neuroimaging studies have addressed how they affect hippocampal volume and shape and how they relate to cognitive abnormalities. We aimed to investigate both brain structure and function in patients with isolated TLE and high anti-GAD65 levels (RIA ≥ 2000 U/ml) compared to 8 non-immune mesial TLE (niTLE) and 8 healthy controls (HC). Hippocampal subfield volume properties were correlated with the duration of the disease and cognitive test scores. The affected hippocampus of GAD-TLE patients showed no volume changes to matched HC whereas niTLE volumes were significantly smaller. Epilepsy duration in GAD-TLE patients correlated negatively with volumes in the presubiculum, subiculum, CA1, CA2-3, CA4, molecular layer and granule cell-molecular layer of the dentate nucleus. We found differences by advanced vertex-wise shape analysis in the anterior hippocampus of the left GAD-TLE compared to HC whereas left niTLE showed bilateral posterior hippocampus deformation. Verbal deficits were similar in GAD-TLE and niTLE but did not correlate to volume changes. These data might suggest a distinct expression of hippocampal structural and functional abnormalities based on the immune response.

The Extended Frontal Aslant Tract (exFAT) is a recently described tractography-based extension of the Frontal Aslant Tract connecting Broca’s territory to both supplementary and pre-supplementary motor areas, and more anterior prefrontal regions. In this study, we aim to characterize the microstructural properties of the exFAT trajectories as a means to perform a laterality analysis to detect interhemispheric structural differences along the tracts using the Human Connectome Project (HCP) dataset. To that end, the bilateral exFAT was reconstructed for 3T and 7T HCP acquisitions in 120 randomly selected subjects. As a complementary exploration of the exFAT anatomy, we performed a white matter dissection of the exFAT trajectory of two ex-vivo left hemispheres that provide a qualitative assessment of the tract profiles. We assessed the lateralization structural differences in the exFAT by performing: (i) a laterality comparison between the mean microstructural diffusion-derived parameters for the exFAT trajectories, (ii) a laterality comparison between the tract profiles obtained by applying the Automated Fiber Quantification (AFQ) algorithm, and (iii) a cross-validated Machine Learning (ML) classifier analysis using single and combined tract profiles parameters for single-subject classification. The mean microstructural diffusion-derived parameter comparison showed statistically significant differences in mean FA values between left and right exFATs in the 3T sample. The diffusion parameters studied with the AFQ technique suggest that the inferiormost half of the exFAT trajectory has a hemispheric-dependent fingerprint of microstructural properties, with an increased measure of tissue hindrance in the orthogonal plane and a decreased measure of orientational dispersion along the main tract direction in the left exFAT compared to the right exFAT. The classification accuracy of the ML models showed a high agreement with the magnitude of those differences.

The Kocher-Monro trajectory to the cerebral ventricular system represents one of the most common surgical procedures in the field of neurosurgery. Several studies have analyzed the specific white matter disruption produced during this intervention, which has no reported adverse neurological outcomes. In this study, a graph-theoretical approach was applied to quantify the structural alterations in whole-brain level connectivity. To this end, 132 subjects were randomly selected from the Human Connectome Project dataset and used to create 3 independent 44 subjects groups. Two of the groups underwent a simulated left/right Kocher-Monro trajectory and the third was kept as a control group. For the right Kocher-Monro approach, the nodal analysis revealed decreased strength in the anterior cingulate gyrus of the transected hemisphere. The network-based statistic analysis revealed a set of right lateralized subnetworks with decreased connectivity strength that is consistent with a subset of the Default Mode Network, Salience Network, and Cingulo-Opercular Network. These findings could allow for a better understanding of structural alterations caused by Kocher-Monro approaches that could reveal previously undetected clinical alterations and inform the process of designing safer and less invasive cerebral ventricular approaches.

The Frontal Aslant Tract (FAT) is a tract recently described as having implications on language function. The originally proposed anatomical FAT definition characterizes a connection between Broca's territory and anterior supplementary and pre-supplementary motor areas in the Superior Frontal Gyrus (SFG). Here we propose an extended definition of the FAT (the exFAT) that propagates more anteriorly into the SFG. A sample of 834 subjects from the WU-Minn HCP 900 subjects data release (S900) was selected. The bilateral exFATs were reconstructed for the whole sample using an automated pipeline and thresholded adjusted tract volumes were calculated. A laterality test was performed on the whole sample. The frontal cortex has known implications on superior cognitive functions, so here we evaluate the implications of exFAT volume on performance in a language task and on a set of working memory tasks. Two sub-samples of 70 subjects each were drawn from the S900 sample by selecting the 35 top-performers and 35 bottom-performers for both language and working memory tasks. Additional laterality tests were performed on each subsample. We did not find the exFAT to be lateralized in any of the samples. We found statistically significant differences in left adjusted exFAT volume between top-performers and bottom-performers in the language task. We also found statistically significant differences in right adjusted exFAT volume between top-performers and bottom-performers for 2-back working memory tasks. To check for the predictive power of the exFAT volumes as correlates for performance, we ran a repeated random sub-sampling cross-validation procedure based on a Support Vector Machine (SVM) classifier that was capable of correctly classifying holdout subjects to their corresponding group (top-performer vs bottom-performer) with an average accuracy of 74.5% for language task performance based on left exFAT volume and an accuracy of 64.2% for Working Memory performance based on right exFAT volume.