Radiology - Research Publications
Permanent URI for this collection
Search Results
1 - 10 of 16
-
ItemInterpretable surface-based detection of focal cortical dysplasias: a Multi-centre Epilepsy Lesion Detection study(OXFORD UNIV PRESS, 2022-11-21)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.
-
ItemGlutamate weighted imaging contrast in gliomas with 7 Tesla magnetic resonance imaging(ELSEVIER SCI LTD, 2019)INTRODUCTION: Diffuse gliomas are incurable malignancies, which undergo inevitable progression and are associated with seizure in 50-90% of cases. Glutamate has the potential to be an important glioma biomarker of survival and local epileptogenicity if it can be accurately quantified noninvasively. METHODS: We applied the glutamate-weighted imaging method GluCEST (glutamate chemical exchange saturation transfer) and single voxel MRS (magnetic resonance spectroscopy) at 7 Telsa (7 T) to patients with gliomas. GluCEST contrast and MRS metabolite concentrations were quantified within the tumour region and peritumoural rim. Clinical variables of tumour aggressiveness (prior adjuvant therapy and previous radiological progression) and epilepsy (any prior seizures, seizure in last month and drug refractory epilepsy) were correlated with respective glutamate concentrations. Images were separated into post-hoc determined patterns and clinical variables were compared across patterns. RESULTS: Ten adult patients with a histo-molecular (n = 9) or radiological (n = 1) diagnosis of grade II-III diffuse glioma were recruited, 40.3 +/- 12.3 years. Increased tumour GluCEST contrast was associated with prior adjuvant therapy (p = .001), and increased peritumoural GluCEST contrast was associated with both recent seizures (p = .038) and drug refractory epilepsy (p = .029). We distinguished two unique GluCEST contrast patterns with distinct clinical and radiological features. MRS glutamate correlated with GluCEST contrast within the peritumoural voxel (R = 0.89, p = .003) and a positive trend existed in the tumour voxel (R = 0.65, p = .113). CONCLUSION: This study supports the role of glutamate in diffuse glioma biology. It further implicates elevated peritumoural glutamate in epileptogenesis and altered tumour glutamate homeostasis in glioma aggressiveness. Given the ability to non-invasively visualise and quantify glutamate, our findings raise the prospect of 7 T GluCEST selecting patients for individualised therapies directed at the glutamate pathway. Larger studies with prospective follow-up are required.
-
ItemStructural network alterations in focal and generalized epilepsy assessed in a worldwide ENIGMA study follow axes of epilepsy risk gene expression(NATURE PORTFOLIO, 2022-07-27)Epilepsy is associated with genetic risk factors and cortico-subcortical network alterations, but associations between neurobiological mechanisms and macroscale connectomics remain unclear. This multisite ENIGMA-Epilepsy study examined whole-brain structural covariance networks in patients with epilepsy and related findings to postmortem epilepsy risk gene expression patterns. Brain network analysis included 578 adults with temporal lobe epilepsy (TLE), 288 adults with idiopathic generalized epilepsy (IGE), and 1328 healthy controls from 18 centres worldwide. Graph theoretical analysis of structural covariance networks revealed increased clustering and path length in orbitofrontal and temporal regions in TLE, suggesting a shift towards network regularization. Conversely, people with IGE showed decreased clustering and path length in fronto-temporo-parietal cortices, indicating a random network configuration. Syndrome-specific topological alterations reflected expression patterns of risk genes for hippocampal sclerosis in TLE and for generalized epilepsy in IGE. These imaging-transcriptomic signatures could potentially guide diagnosis or tailor therapeutic approaches to specific epilepsy syndromes.
-
ItemTopographic divergence of atypical cortical asymmetry and atrophy patterns in temporal lobe epilepsy(OXFORD UNIV PRESS, 2022-03-25)Temporal lobe epilepsy, a common drug-resistant epilepsy in adults, is primarily a limbic network disorder associated with predominant unilateral hippocampal pathology. Structural MRI has provided an in vivo window into whole-brain grey matter structural alterations in temporal lobe epilepsy relative to controls, by either mapping (i) atypical inter-hemispheric asymmetry; or (ii) regional atrophy. However, similarities and differences of both atypical asymmetry and regional atrophy measures have not been systematically investigated. Here, we addressed this gap using the multisite ENIGMA-Epilepsy dataset comprising MRI brain morphological measures in 732 temporal lobe epilepsy patients and 1418 healthy controls. We compared spatial distributions of grey matter asymmetry and atrophy in temporal lobe epilepsy, contextualized their topographies relative to spatial gradients in cortical microstructure and functional connectivity calculated using 207 healthy controls obtained from Human Connectome Project and an independent dataset containing 23 temporal lobe epilepsy patients and 53 healthy controls and examined clinical associations using machine learning. We identified a marked divergence in the spatial distribution of atypical inter-hemispheric asymmetry and regional atrophy mapping. The former revealed a temporo-limbic disease signature while the latter showed diffuse and bilateral patterns. Our findings were robust across individual sites and patients. Cortical atrophy was significantly correlated with disease duration and age at seizure onset, while degrees of asymmetry did not show a significant relationship to these clinical variables. Our findings highlight that the mapping of atypical inter-hemispheric asymmetry and regional atrophy tap into two complementary aspects of temporal lobe epilepsy-related pathology, with the former revealing primary substrates in ipsilateral limbic circuits and the latter capturing bilateral disease effects. These findings refine our notion of the neuropathology of temporal lobe epilepsy and may inform future discovery and validation of complementary MRI biomarkers in temporal lobe epilepsy.
-
ItemMachine learning approaches for imaging-based prognostication of the outcome of surgery for mesial temporal lobe epilepsy(WILEY, 2022-05)OBJECTIVES: Around 30% of patients undergoing surgical resection for drug-resistant mesial temporal lobe epilepsy (MTLE) do not obtain seizure freedom. Success of anterior temporal lobe resection (ATLR) critically depends on the careful selection of surgical candidates, aiming at optimizing seizure freedom while minimizing postoperative morbidity. Structural MRI and FDG-PET neuroimaging are routinely used in presurgical assessment and guide the decision to proceed to surgery. In this study, we evaluate the potential of machine learning techniques applied to standard presurgical MRI and PET imaging features to provide enhanced prognostic value relative to current practice. METHODS: Eighty two patients with drug resistant MTLE were scanned with FDG-PET pre-surgery and T1-weighted MRI pre- and postsurgery. From these images the following features of interest were derived: volume of temporal lobe (TL) hypometabolism, % of extratemporal hypometabolism, presence of contralateral TL hypometabolism, presence of hippocampal sclerosis, laterality of seizure onset volume of tissue resected and % of temporal lobe hypometabolism resected. These measures were used as predictor variables in logistic regression, support vector machines, random forests and artificial neural networks. RESULTS: In the study cohort, 24 of 82 (28.3%) who underwent an ATLR for drug-resistant MTLE did not achieve Engel Class I (i.e., free of disabling seizures) outcome at a minimum of 2 years of postoperative follow-up. We found that machine learning approaches were able to predict up to 73% of the 24 ATLR surgical patients who did not achieve a Class I outcome, at the expense of incorrect prediction for up to 31% of patients who did achieve a Class I outcome. Overall accuracies ranged from 70% to 80%, with an area under the receiver operating characteristic curve (AUC) of .75-.81. We additionally found that information regarding overall extent of both total and significantly hypometabolic tissue resected was crucial to predictive performance, with AUC dropping to .59-.62 using presurgical information alone. Incorporating the laterality of seizure onset and the choice of machine learning algorithm did not significantly change predictive performance. SIGNIFICANCE: Collectively, these results indicate that "acceptable" to "good" patient-specific prognostication for drug-resistant MTLE surgery is feasible with machine learning approaches utilizing commonly collected imaging modalities, but that information on the surgical resection region is critical for optimal prognostication.
-
ItemAtlas of lesion locations and postsurgical seizure freedom in focal cortical dysplasia: A MELD study(WILEY, 2022-01)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.
-
ItemAssessment of the DTI-ALPS Parameter Along the Perivascular Space in Older Adults at Risk of Dementia(WILEY, 2021-05)BACKGROUND AND PURPOSE: Recently, there has been growing interest in the glymphatic system (the functional waste clearance pathway for the central nervous system and its role in flushing solutes (such as amyloid ß and tau), metabolic, and other cellular waste products in the brain. Herein, we investigate a recent potential biomarker for glymphatic activity (the diffusion tensor imaging along the perivascular space [DTI-ALPS] parameter) using diffusion MRI imaging in an elderly cohort comprising 10 cognitively normal, 10 mild cognitive impairment (MCI), and 16 Alzheimer's disease (AD). METHODS: All 36 participants imaged on a Siemens 3.0T Tim Trio. Single-SE diffusion weighted Echo-planar imaging scans were acquired as well as T1 magnetization prepared rapid gradient echo, T2 axial, and susceptibility weighted imaging. Three millimeter regions of interest were drawn in the projection and association fibers adjacent to the medullary veins at the level of the lateral ventricle. The DTI-ALPS parameter was calculated in these regions and correlated with cognitive status, Mini-Mental State Examination (MMSE), and ADASCog11 measures. RESULTS: Significant correlations were found between DTI-ALPS and MMSE and ADASCog11 in the right hemisphere adjusting for age, sex, and APoE ε4 status. Significant differences were also found in the right DTI-ALPS indices between cognitively normal and AD groups (P < .026) and MCI groups (P < .025) in a univariate general linear model corrected for age, sex, and APoE ε4. Significant differences in apparent diffusion coefficient between cognitively normal and AD groups were found in the right projection fibers (P = .028). CONCLUSION: Further work is needed to determine the utility of DTI-ALPS index in larger elderly cohorts and whether it measures glymphatic activity.
-
ItemArtificial intelligence for classification of temporal lobe epilepsy with ROI-level MRI data: A worldwide ENIGMA-Epilepsy study(ELSEVIER SCI LTD, 2021)Artificial intelligence has recently gained popularity across different medical fields to aid in the detection of diseases based on pathology samples or medical imaging findings. Brain magnetic resonance imaging (MRI) is a key assessment tool for patients with temporal lobe epilepsy (TLE). The role of machine learning and artificial intelligence to increase detection of brain abnormalities in TLE remains inconclusive. We used support vector machine (SV) and deep learning (DL) models based on region of interest (ROI-based) structural (n = 336) and diffusion (n = 863) brain MRI data from patients with TLE with ("lesional") and without ("non-lesional") radiographic features suggestive of underlying hippocampal sclerosis from the multinational (multi-center) ENIGMA-Epilepsy consortium. Our data showed that models to identify TLE performed better or similar (68-75%) compared to models to lateralize the side of TLE (56-73%, except structural-based) based on diffusion data with the opposite pattern seen for structural data (67-75% to diagnose vs. 83% to lateralize). In other aspects, structural and diffusion-based models showed similar classification accuracies. Our classification models for patients with hippocampal sclerosis were more accurate (68-76%) than models that stratified non-lesional patients (53-62%). Overall, SV and DL models performed similarly with several instances in which SV mildly outperformed DL. We discuss the relative performance of these models with ROI-level data and the implications for future applications of machine learning and artificial intelligence in epilepsy care.
-
Item7T Magnetic Resonance Imaging Quantification of Brain Glutamate in Acute Ischaemic Stroke(Korean Stroke Society, 2021-05-01)
-
ItemSeven-tesla quantitative magnetic resonance spectroscopy of glutamate, γ-aminobutyric acid, and glutathione in the posterior cingulate cortex/precuneus in patients with epilepsy(WILEY, 2020-12)OBJECTIVE: The posterior cingulate cortex (PCC)/precuneus is a key hub of the default mode network, whose function is known to be altered in epilepsy. Glutamate and γ-aminobutyric acid (GABA) are the main excitatory and inhibitory neurotransmitters in the central nervous system, respectively. Glutathione (GSH) is the most important free radical scavenging compound in the brain. Quantification of these molecules by magnetic resonance spectroscopy (MRS) up to 4 T is limited by overlapping resonances from other molecules. In this study, we used ultra-high-field (7 T) MRS to quantify their concentrations in patients with different epilepsy syndromes. METHODS: Nineteen patients with temporal lobe epilepsy (TLE) and 16 with idiopathic generalized epilepsy (IGE) underwent magnetic resonance imaging scans using a 7-T research scanner. Single-voxel (8 cm3 ) MRS, located in the PCC/precuneus, was acquired via stimulated echo acquisition mode. Their results were compared to 10 healthy volunteers. RESULTS: Mean concentrations of glutamate, GABA, and the glutamate/GABA ratio did not differ between the IGE, TLE, and healthy volunteer groups. The mean ± SD concentration of GSH was 1.9 ± 0.3 mmol·L-1 in healthy controls, 2.0 ± 0.2 mmol·L-1 in patients with TLE, and 2.2 ± 0.4 mmol·L-1 in patients with IGE. One-way analysis of variance with post hoc Tukey-Kramer test revealed a significant difference in the concentration of GSH between patients with IGE and controls (P = .03). Short-term seizure freedom in patients with epilepsy was predicted by an elevated concentration of glutamate in the PCC/precuneus (P = .01). In patients with TLE, the concentration of GABA declined with age (P = .03). SIGNIFICANCE: Patients with IGE have higher concentrations of GSH in the PCC/precuneus than healthy controls. There is no difference in the concentrations of glutamate and GABA, or their ratio, in the PCC/precuneus between patients with IGE, patients with TLE, and healthy controls. Measuring the concentration of glutamate in the PCC/precuneus may assist with predicting drug response.