Deep learning for risk-based stratification of cognitively impaired individuals

Quantifying the risk of progression to Alzheimer's disease (AD) could help identify persons who could benefit from early interventions. We used data from the Alzheimer's Disease Neuroimaging Initiative (ADNI, n = 544, discovery cohort) and the National Alzheimer's Coordinating Center (NACC, n = 508, validation cohort), subdividing individuals with mild cognitive impairment (MCI) into risk groups based on cerebrospinal fluid amyloid-β levels and identifying differential gray matter patterns. We then created models that fused neural networks with survival analysis, trained using non-parcellated T1-weighted brain MRIs from ADNI data, to predict the trajectories of MCI to AD conversion within the NACC cohort (integrated Brier score: 0.192 [discovery], and 0.108 [validation]). Using modern interpretability techniques, we verified that regions important for model prediction are classically associated with AD. We confirmed AD diagnosis labels using postmortem data. We conclude that our framework provides a strategy for risk-based stratification of individuals with MCI and for identifying regions key for disease prognosis.

White matter abnormalities across different epilepsy syndromes in adults: an ENIGMA-Epilepsy study

The epilepsies are commonly accompanied by widespread abnormalities in cerebral white matter. ENIGMA-Epilepsy is a large quantitative brain imaging consortium, aggregating data to investigate patterns of neuroimaging abnormalities in common epilepsy syndromes, including temporal lobe epilepsy, extratemporal epilepsy, and genetic generalized epilepsy. Our goal was to rank the most robust white matter microstructural differences across and within syndromes in a multicentre sample of adult epilepsy patients. Diffusion-weighted MRI data were analysed from 1069 healthy controls and 1249 patients: temporal lobe epilepsy with hippocampal sclerosis (n = 599), temporal lobe epilepsy with normal MRI (n = 275), genetic generalized epilepsy (n = 182) and non-lesional extratemporal epilepsy (n = 193). A harmonized protocol using tract-based spatial statistics was used to derive skeletonized maps of fractional anisotropy and mean diffusivity for each participant, and fibre tracts were segmented using a diffusion MRI atlas. Data were harmonized to correct for scanner-specific variations in diffusion measures using a batch-effect correction tool (ComBat). Analyses of covariance, adjusting for age and sex, examined differences between each epilepsy syndrome and controls for each white matter tract (Bonferroni corrected at P < 0.001). Across 'all epilepsies' lower fractional anisotropy was observed in most fibre tracts with small to medium effect sizes, especially in the corpus callosum, cingulum and external capsule. There were also less robust increases in mean diffusivity. Syndrome-specific fractional anisotropy and mean diffusivity differences were most pronounced in patients with hippocampal sclerosis in the ipsilateral parahippocampal cingulum and external capsule, with smaller effects across most other tracts. Individuals with temporal lobe epilepsy and normal MRI showed a similar pattern of greater ipsilateral than contralateral abnormalities, but less marked than those in patients with hippocampal sclerosis. Patients with generalized and extratemporal epilepsies had pronounced reductions in fractional anisotropy in the corpus callosum, corona radiata and external capsule, and increased mean diffusivity of the anterior corona radiata. Earlier age of seizure onset and longer disease duration were associated with a greater extent of diffusion abnormalities in patients with hippocampal sclerosis. We demonstrate microstructural abnormalities across major association, commissural, and projection fibres in a large multicentre study of epilepsy. Overall, patients with epilepsy showed white matter abnormalities in the corpus callosum, cingulum and external capsule, with differing severity across epilepsy syndromes. These data further define the spectrum of white matter abnormalities in common epilepsy syndromes, yielding more detailed insights into pathological substrates that may explain cognitive and psychiatric co-morbidities and be used to guide biomarker studies of treatment outcomes and/or genetic research.

Clinical utility of structural connectomics in predicting memory in temporal lobe epilepsy

OBJECTIVE

To determine the predictive power of white matter neuronal networks (i.e., structural connectomes [SCs]) in discriminating memory-impaired patients with temporal lobe epilepsy (TLE) from those with normal memory.

METHODS

T1- and diffusion MRI (dMRI), clinical variables, and neuropsychological measures of verbal memory were available for 81 patients with TLE. Prediction of memory impairment was performed with a tree-based classifier (XGBoost) for 4 models: (1) a clinical model including demographic and clinical features, (2) a hippocampal volume (HCV) model, (3) a tract model including 5 temporal lobe white matter association tracts derived from a dMRI atlas, and (4) an SC model based on dMRI. SCs were derived by extracting cortical-cortical connections from a temporal lobe subnetwork with probabilistic tractography. Principal component (PC) analysis was then applied to reduce the dimensionality of the SC, yielding 10 PCs. Multimodal models were also tested combining SCs and tracts with HCV. Each model was trained on 48 patients from 1 epilepsy center and tested on 33 patients from a different center.

RESULTS

Multimodal models that included the SC + HCV model yielded the highest classification accuracy (81%; 0.90 sensitivity; 0.67 specificity), outperforming the clinical model (61%; p < 0.001) and HCV model (66%; p < 0.001). In addition, the unimodal SC model (76% accuracy) and tract model (73% accuracy) outperformed the clinical model (p < 0.001) and HCV model (p < 0.001) for classifying patients with TLE with and without memory impairment. Furthermore, the SC identified that short-range temporal-temporal connections were important contributors to memory performance.

CONCLUSION

SCs and tract-based models are stronger predictors of memory impairment in TLE than HCVs and clinical variables. However, SCs may provide additional information about local cortical-cortical connectivity contributing to memory that is not captured in large association tracts.

The ENIGMA-Epilepsy working group: Mapping disease from large data sets

Epilepsy is a common and serious neurological disorder, with many different constituent conditions characterized by their electro clinical, imaging, and genetic features. MRI has been fundamental in advancing our understanding of brain processes in the epilepsies. Smaller-scale studies have identified many interesting imaging phenomena, with implications both for understanding pathophysiology and improving clinical care. Through the infrastructure and concepts now well-established by the ENIGMA Consortium, ENIGMA-Epilepsy was established to strengthen epilepsy neuroscience by greatly increasing sample sizes, leveraging ideas and methods established in other ENIGMA projects, and generating a body of collaborating scientists and clinicians to drive forward robust research. Here we review published, current, and future projects, that include structural MRI, diffusion tensor imaging (DTI), and resting state functional MRI (rsfMRI), and that employ advanced methods including structural covariance, and event-based modeling analysis. We explore age of onset- and duration-related features, as well as phenomena-specific work focusing on particular epilepsy syndromes or phenotypes, multimodal analyses focused on understanding the biology of disease progression, and deep learning approaches. We encourage groups who may be interested in participating to make contact to further grow and develop ENIGMA-Epilepsy.

The white matter connectome as an individualized biomarker of language impairment in temporal lobe epilepsy

OBJECTIVE

The distributed white matter network underlying language leads to difficulties in extracting clinically meaningful summaries of neural alterations leading to language impairment. Here we determine the predictive ability of the structural connectome (SC), compared with global measures of white matter tract microstructure and clinical data, to discriminate language impaired patients with temporal lobe epilepsy (TLE) from TLE patients without language impairment.

METHODS

T1- and diffusion-MRI, clinical variables (CVs), and neuropsychological measures of naming and verbal fluency were available for 82 TLE patients. Prediction of language impairment was performed using a robust tree-based classifier (XGBoost) for three models: (1) a CV-model which included demographic and epilepsy-related clinical features, (2) an atlas-based tract-model, including four frontotemporal white matter association tracts implicated in language (i.e., the bilateral arcuate fasciculus, inferior frontal occipital fasciculus, inferior longitudinal fasciculus, and uncinate fasciculus), and (3) a SC-model based on diffusion MRI. For the association tracts, mean fractional anisotropy was calculated as a measure of white matter microstructure for each tract using a diffusion tensor atlas (i.e., AtlasTrack). The SC-model used measurement of cortical-cortical connections arising from a temporal lobe subnetwork derived using probabilistic tractography. Dimensionality reduction of the SC was performed with principal components analysis (PCA). Each model was trained on 49 patients from one epilepsy center and tested on 33 patients from a different center (i.e., an independent dataset). Randomization was performed to test the stability of the results.

RESULTS

The SC-model yielded a greater area under the curve (AUC; .73) and accuracy (79%) compared to both the tract-model (AUC: .54, p < .001; accuracy: 70%, p < .001) and the CV-model (AUC: .59, p < .001; accuracy: 64%, p < .001). Within the SC-model, lateral temporal connections had the highest importance to model performance, including connections similar to language association tracts such as links between the superior temporal gyrus to pars opercularis. However, in addition to these connections many additional connections that were widely distributed, bilateral and interhemispheric in nature were identified as contributing to SC-model performance.

CONCLUSION

The SC revealed a white matter network contributing to language impairment that was widely distributed, bilateral, and lateral temporal in nature. The distributed network underlying language may be why the SC-model has an advantage in identifying sub-components of the complex fiber networks most relevant for aspects of language performance.

Sensitivity of restriction spectrum imaging to memory and neuropathology in Alzheimer's disease

Background

Diffusion imaging has demonstrated sensitivity to structural brain changes in Alzheimer’s disease (AD). However, there remains a need for a more complete characterization of microstructural alterations occurring at the earliest disease stages, and how these changes relate to underlying neuropathology. This study evaluated the sensitivity of restriction spectrum imaging (RSI), an advanced diffusion magnetic resonance imaging (MRI) technique, to microstructural brain changes in mild cognitive impairment (MCI) and AD.

Methods

MRI and neuropsychological test data were acquired from 31 healthy controls, 12 individuals with MCI, and 13 individuals with mild AD, aged 63–93 years. Cerebrospinal fluid amyloid-β levels were measured in a subset (n = 38) of participants. RSI measures of neurite density (ND) and isotropic free water (IF) were computed in fiber tracts and in hippocampal and entorhinal cortex gray matter, respectively. Analyses evaluated whether these measures predicted memory performance, correlated with amyloid-β levels, and distinguished impaired individuals from controls. For comparison, analyses were repeated with standard diffusion tensor imaging (DTI) metrics of fractional anisotropy (FA) and mean diffusivity.

Results

Both RSI and DTI measures correlated with episodic memory and disease severity. RSI, but not DTI, measures correlated with amyloid-β42 levels. ND and FA in the arcuate fasciculus and entorhinal cortex IF most strongly predicted recall performance. RSI measures of arcuate fasciculus ND and entorhinal cortex IF best discriminated memory impaired participants from healthy participants.

Conclusions

RSI is highly sensitive to microstructural changes in the early stages of AD, and is associated with biochemical markers of AD pathology. Reduced ND in cortical association fibers and increased medial temporal lobe free-water diffusion predicted episodic memory, distinguished cognitively impaired from healthy individuals, and correlated with amyloid-β. Although further research is needed to assess the sensitivity of RSI to preclinical AD and disease progression, these results suggest that RSI may be a promising tool to better understand neuroanatomical changes in AD and their association with neuropathology.

Electronic supplementary material

The online version of this article (doi:10.1186/s13195-017-0281-7) contains supplementary material, which is available to authorized users.