On the cutting edge of glioblastoma surgery: where neurosurgeons agree and disagree on surgical decisions.

OBJECTIVE: The aim of glioblastoma surgery is to maximize the extent of resection while preserving functional integrity. Standards are lacking for surgical decision-making, and previous studies indicate treatment variations. These shortcomings reflect the need to evaluate larger populations from different care teams. In this study, the authors used probability maps to quantify and compare surgical decision-making throughout the brain by 12 neurosurgical teams for patients with glioblastoma. METHODS: The study included all adult patients who underwent first-time glioblastoma surgery in 2012-2013 and were treated by 1 of the 12 participating neurosurgical teams. Voxel-wise probability maps of tumor location, biopsy, and resection were constructed for each team to identify and compare patient treatment variations. Brain regions with different biopsy and resection results between teams were identified and analyzed for patient functional outcome and survival. RESULTS: The study cohort consisted of 1087 patients, of whom 363 underwent a biopsy and 724 a resection. Biopsy and resection decisions were generally comparable between teams, providing benchmarks for probability maps of resections and biopsies for glioblastoma. Differences in biopsy rates were identified for the right superior frontal gyrus and indicated variation in biopsy decisions. Differences in resection rates were identified for the left superior parietal lobule, indicating variations in resection decisions. CONCLUSIONS: Probability maps of glioblastoma surgery enabled capture of clinical practice decisions and indicated that teams generally agreed on which region to biopsy or to resect. However, treatment variations reflecting clinical dilemmas were observed and pinpointed by using the probability maps, which could therefore be useful for quality-of-care discussions between surgical teams for patients with glioblastoma.

Accurate MR Image Registration to Anatomical Reference Space for Diffuse Glioma.

To summarize the distribution of glioma location within a patient population, registration of individual MR images to anatomical reference space is required. In this study, we quantified the accuracy of MR image registration to anatomical reference space with linear and non-linear transformations using estimated tumor targets of glioblastoma and lower-grade glioma, and anatomical landmarks at pre- and post-operative time-points using six commonly used registration packages (FSL, SPM5, DARTEL, ANTs, Elastix, and NiftyReg). Routine clinical pre- and post-operative, post-contrast T1-weighted images of 20 patients with glioblastoma and 20 with lower-grade glioma were collected. The 2009a Montreal Neurological Institute brain template was used as anatomical reference space. Tumors were manually segmented in the patient space and corresponding healthy tissue was delineated as a target volume in the anatomical reference space. Accuracy of the tumor alignment was quantified using the Dice score and the Hausdorff distance. To measure the accuracy of general brain alignment, anatomical landmarks were placed in patient and in anatomical reference space, and the landmark distance after registration was quantified. Lower-grade gliomas were registered more accurately than glioblastoma. Registration accuracy for pre- and post-operative MR images did not differ. SPM5 and DARTEL registered tumors most accurate, and FSL least accurate. Non-linear transformations resulted in more accurate general brain alignment than linear transformations, but tumor alignment was similar between linear and non-linear transformation. We conclude that linear transformation suffices to summarize glioma locations in anatomical reference space.

Quantifying eloquent locations for glioblastoma surgery using resection probability maps.

OBJECTIVE: Decisions in glioblastoma surgery are often guided by presumed eloquence of the tumor location. The authors introduce the "expected residual tumor volume" (eRV) and the "expected resectability index" (eRI) based on previous decisions aggregated in resection probability maps. The diagnostic accuracy of eRV and eRI to predict biopsy decisions, resectability, functional outcome, and survival was determined. METHODS: Consecutive patients with first-time glioblastoma surgery in 2012-2013 were included from 12 hospitals. The eRV was calculated from the preoperative MR images of each patient using a resection probability map, and the eRI was derived from the tumor volume. As reference, Sawaya's tumor location eloquence grades (EGs) were classified. Resectability was measured as observed extent of resection (EOR) and residual volume, and functional outcome as change in Karnofsky Performance Scale score. Receiver operating characteristic curves and multivariable logistic regression were applied. RESULTS: Of 915 patients, 674 (74%) underwent a resection with a median EOR of 97%, functional improvement in 71 (8%), functional decline in 78 (9%), and median survival of 12.8 months. The eRI and eRV identified biopsies and EORs of at least 80%, 90%, or 98% better than EG. The eRV and eRI predicted observed residual volumes under 10, 5, and 1 ml better than EG. The eRV, eRI, and EG had low diagnostic accuracy for functional outcome changes. Higher eRV and lower eRI were strongly associated with shorter survival, independent of known prognostic factors. CONCLUSIONS: The eRV and eRI predict biopsy decisions, resectability, and survival better than eloquence grading and may be useful preoperative indices to support surgical decisions.

Robust Deep Learning-based Segmentation of Glioblastoma on Routine Clinical MRI Scans Using Sparsified Training.

PURPOSE: To improve the robustness of deep learning-based glioblastoma segmentation in a clinical setting with sparsified datasets. MATERIALS AND METHODS: In this retrospective study, preoperative T1-weighted, T2-weighted, T2-weighted fluid-attenuated inversion recovery, and postcontrast T1-weighted MRI from 117 patients (median age, 64 years; interquartile range [IQR], 55-73 years; 76 men) included within the Multimodal Brain Tumor Image Segmentation (BraTS) dataset plus a clinical dataset (2012-2013) with similar imaging modalities of 634 patients (median age, 59 years; IQR, 49-69 years; 382 men) with glioblastoma from six hospitals were used. Expert tumor delineations on the postcontrast images were available, but for various clinical datasets, one or more sequences were missing. The convolutional neural network, DeepMedic, was trained on combinations of complete and incomplete data with and without site-specific data. Sparsified training was introduced, which randomly simulated missing sequences during training. The effects of sparsified training and center-specific training were tested using Wilcoxon signed rank tests for paired measurements. RESULTS: A model trained exclusively on BraTS data reached a median Dice score of 0.81 for segmentation on BraTS test data but only 0.49 on the clinical data. Sparsified training improved performance (adjusted P < .05), even when excluding test data with missing sequences, to median Dice score of 0.67. Inclusion of site-specific data during sparsified training led to higher model performance Dice scores greater than 0.8, on par with a model based on all complete and incomplete data. For the model using BraTS and clinical training data, inclusion of site-specific data or sparsified training was of no consequence. CONCLUSION: Accurate and automatic segmentation of glioblastoma on clinical scans is feasible using a model based on large, heterogeneous, and partially incomplete datasets. Sparsified training may boost the performance of a smaller model based on public and site-specific data.Supplemental material is available for this article.Published under a CC BY 4.0 license.

Quantitative Third Harmonic Generation Microscopy for Assessment of Glioma in Human Brain Tissue.

Distinguishing tumors from normal brain cells is important but challenging in glioma surgery due to the lack of clear interfaces between the two. The ability of label-free third harmonic generation (THG) microscopy in combination with automated image analysis to quantitatively detect glioma infiltration in fresh, unprocessed tissue in real time is assessed. The THG images reveal increased cellularity in grades II-IV glioma samples from 23 patients, as confirmed by subsequent hematoxylin and eosin histology. An automated image quantification workflow is presented for quantitative assessment of the imaged cellularity as a reflection of the degree of glioma invasion. The cellularity is validated in three ways: 1) Quantitative comparison of THG imaging with fluorescence microscopy of nucleus-stained samples demonstrates that THG reflects the true tissue cellularity. 2) Thresholding of THG cellularity differentiates normal brain from glioma infiltration, with 96.6% sensitivity and 95.5% specificity, in nearly perfect (93%) agreement with pathologists. 3) In one patient, a good correlation between THG cellularity and preoperative magnetic resonance and positron emission tomography imaging is demonstrated. In conclusion, quantitative real-time THG microscopy accurately assesses glioma infiltration in ex vivo human brain samples, and therefore holds strong potential for improving the accuracy of surgical resection.

FAst Segmentation Through SURface Fairing (FASTSURF): A novel semi-automatic hippocampus segmentation method.

OBJECTIVE: The objective is to present a proof-of-concept of a semi-automatic method to reduce hippocampus segmentation time on magnetic resonance images (MRI). MATERIALS AND METHODS: FAst Segmentation Through SURface Fairing (FASTSURF) is based on a surface fairing technique which reconstructs the hippocampus from sparse delineations. To validate FASTSURF, simulations were performed in which sparse delineations extracted from full manual segmentations served as input. On three different datasets with different diagnostic groups, FASTSURF hippocampi were compared to the original segmentations using Jaccard overlap indices and percentage volume differences (PVD). In one data set for which back-to-back scans were available, unbiased estimates of overlap and PVD were obtained. Using longitudinal scans, we compared hippocampal atrophy rates measured by manual, FASTSURF and two automatic segmentations (FreeSurfer and FSL-FIRST). RESULTS: With only seven input contours, FASTSURF yielded mean Jaccard indices ranging from 72(±4.3)% to 83(±2.6)% and PVDs ranging from 0.02(±2.40)% to 3.2(±3.40)% across the three datasets. Slightly poorer results were obtained for the unbiased analysis, but the performance was still considerably better than both tested automatic methods with only five contours. CONCLUSIONS: FASTSURF segmentations have high accuracy and require only a fraction of the delineation effort of fully manual segmentation. Atrophy rate quantification based on completely manual segmentation is well reproduced by FASTSURF. Therefore, FASTSURF is a promising tool to be implemented in clinical workflow, provided a future prospective validation confirms our findings.

Comparing Glioblastoma Surgery Decisions Between Teams Using Brain Maps of Tumor Locations, Biopsies, and Resections.

PURPOSE: The aim of glioblastoma surgery is to maximize the extent of resection while preserving functional integrity, which depends on the location within the brain. A standard to compare these decisions is lacking. We present a volumetric voxel-wise method for direct comparison between two multidisciplinary teams of glioblastoma surgery decisions throughout the brain. METHODS: Adults undergoing first-time glioblastoma surgery from 2012 to 2013 performed by two neuro-oncologic teams were included. Patients had had a diagnostic biopsy or resection. Preoperative tumors and postoperative residues were segmented on magnetic resonance imaging in three dimensions and registered to standard brain space. Voxel-wise probability maps of tumor location, biopsy, and resection were constructed for each team to compare patient referral bias, indication variation, and treatment variation. To evaluate the quality of care, subgroups of differentially resected brain regions were analyzed for survival and functional outcome. RESULTS: One team included 101 patients, and the other included 174; 91 tumors were biopsied, and 181 were resected. Patient characteristics were largely comparable between teams. Distributions of tumor locations were dissimilar, suggesting referral bias. Distributions of biopsies were similar, suggesting absence of indication variation. Differentially resected regions were identified in the anterior limb of the right internal capsule and the right caudate nucleus, indicating treatment variation. Patients with (n = 12) and without (n = 6) surgical removal in these regions had similar overall survival and similar permanent neurologic deficits. CONCLUSION: Probability maps of tumor location, biopsy, and resection provide additional information that can inform surgical decision making across multidisciplinary teams for patients with glioblastoma.

Novel imaging phantom for accurate and robust measurement of brain atrophy rates using clinical MRI.

Brain volume loss, or atrophy, has been proven to be an important characteristic of neurological diseases such as Alzheimer's disease and multiple sclerosis. To use atrophy rate as a reliable clinical biomarker and to increase statistical power in clinical treatment trials, measurement variability needs to be minimized. Among other sources, systematic differences between different MR scanners are suspected to contribute to this variability. In this study we developed and performed initial validation tests of an MR-compatible phantom and analysis software for robust and reliable evaluation of the brain volume loss. The phantom contained three inflatable models of brain structures, i.e. cerebral hemisphere, putamen, and caudate nucleus. Software to reliably quantify volumes form the phantom images was also developed. To validate the method, the phantom was imaged using 3D T1-weighted protocols at three clinical 3T MR scanners from different vendors. Calculated volume change from MRI was compared with the known applied volume change using ICC and mean absolute difference. As assessed by the ICC, the agreement between our developed software and the applied volume change for different structures ranged from 0.999-1 for hemisphere, 0.976-0.998 for putamen, and 0.985-0.999 for caudate nucleus. The mean absolute differences between measured and applied volume change were 109-332 µL for hemisphere, 2.9-11.9 µL for putamen, and 2.2-10.1 µL for caudate nucleus. This method offers a reliable and robust measurement of volume change using MR images and could potentially be used to standardize clinical measurement of atrophy rates.

Tensor regularized total variation for denoising of third harmonic generation images of brain tumors.

Third harmonic generation (THG) microscopy shows great potential for instant pathology of brain tissue during surgery. However, the rich morphologies contained and the noise associated makes image restoration, necessary for quantification of the THG images, challenging. Anisotropic diffusion filtering (ADF) has been recently applied to restore THG images of normal brain, but ADF is hard-to-code, time-consuming and only reconstructs salient edges. This work overcomes these drawbacks by expressing ADF as a tensor regularized total variation model, which uses the Huber penalty and the L1 norm for tensor regularization and fidelity measurement, respectively. The diffusion tensor is constructed from the structure tensor of ADF yet the tensor decomposition is performed only in the non-flat areas. The resulting model is solved by an efficient and easy-to-code primal-dual algorithm. Tests on THG brain tumor images show that the proposed model has comparable denoising performance as ADF while it much better restores weak edges and it is up to 60% more time efficient.

Functional brain network centrality is related to APOE genotype in cognitively normal elderly.

INTRODUCTION: Amyloid plaque deposition in the brain is an early pathological change in Alzheimer's disease (AD), causing disrupted synaptic connections. Brain network disruptions in AD have been demonstrated with eigenvector centrality (EC), a measure that identifies central regions within networks. Carrying an apolipoprotein (APOE)-ε4 allele is a genetic risk for AD, associated with increased amyloid deposition. We studied whether APOE-ε4 carriership is associated with EC disruptions in cognitively normal individuals. METHODS: A total of 261 healthy middle-aged to older adults (mean age 56.6 years) were divided into high-risk (APOE-ε4 carriers) and low-risk (noncarriers) groups. EC was computed from resting-state functional MRI data. Clusters of between-group differences were assessed with a permutation-based method. Correlations between cluster mean EC with brain volume, CSF biomarkers, and psychological test scores were assessed. RESULTS: Decreased EC in the visual cortex was associated with APOE-ε4 carriership, a genetic risk factor for AD. EC differences were correlated with age, CSF amyloid levels, and scores on the trail-making and 15-object recognition tests. CONCLUSION: Our findings suggest that the APOE-ε4 genotype affects brain connectivity in regions previously found to be abnormal in AD as a sign of very early disease-related pathology. These differences were too subtle in healthy elderly to use EC for single-subject prediction of APOE genotype.

Spatial resolution for EEG source reconstruction-A simulation study on SEPs.

BACKGROUND: The accuracy of source reconstruction depends on the spatial configuration of the neural sources underlying encephalographic signals, the temporal distance of the source activity, the level and structure of noise in the recordings, and - of course - on the employed inverse method. This plenitude of factors renders a definition of 'spatial resolution' of the electro-encephalogram (EEG) a challenge. NEW METHOD: A proper definition of spatial resolution requires a ground truth. We used data from numerical simulations of two dipoles changed with waveforms resembling somatosensory evoked potentials peaking at 20, 30, 50, 100 ms. We varied inter-dipole distances and added noise to the simulated scalp recordings with distinct signal-to-noise ratios (SNRs). Prior to inverse modeling we pre-whitened the simulated data and the leadfield. We tested a two-dipole fit, sc-MUSIC, and sc-eLORETA and assessed their accuracy via the distance between the simulated and estimated sources. RESULTS: To quantify the spatial resolution of EEG, we introduced the notion of separability, i.e. the separation of two dipolar sources with a certain inter-dipole distance. Our results indicate separability of two sources in the presence of realistic noise with SNR up to 3 if they are 11 mm or further apart. COMPARISON WITH EXISTING METHODS: In the presence of realistic noise, spatial pre-whitening appears mandatory preprocessing step irrespective of the inverse method employed. CONCLUSIONS: Separability is a legitimate measure to quantify EEG's spatial resolution. An optimal resolution in source reconstruction requires spatial pre-whitening as a crucial pre-processing step.

Disentangling Somatosensory Evoked Potentials of the Fingers: Limitations and Clinical Potential.

In searching for clinical biomarkers of the somatosensory function, we studied reproducibility of somatosensory potentials (SEP) evoked by finger stimulation in healthy subjects. SEPs induced by electrical stimulation and especially after median nerve stimulation is a method widely used in the literature. It is unclear, however, if the EEG recordings after finger stimulation are reproducible within the same subject. We tested in five healthy subjects the consistency and reproducibility of responses through bootstrapping as well as test-retest recordings. We further evaluated the possibility to discriminate activity of different fingers both at electrode and at source level. The lack of consistency and reproducibility suggest responses to finger stimulation to be unreliable, even with reasonably high signal-to-noise ratio and adequate number of trials. At sources level, somatotopic arrangement of the fingers representation was only found in one of the subjects. Although finding distinct locations of the different fingers activation was possible, our protocol did not allow for non-overlapping dipole representations of the fingers. We conclude that despite its theoretical advantages, we cannot recommend the use of somatosensory potentials evoked by finger stimulation to extract clinical biomarkers.

Quantitative comparison of 3D third harmonic generation and fluorescence microscopy images.

Third harmonic generation (THG) microscopy is a label-free imaging technique that shows great potential for rapid pathology of brain tissue during brain tumor surgery. However, the interpretation of THG brain images should be quantitatively linked to images of more standard imaging techniques, which so far has been done qualitatively only. We establish here such a quantitative link between THG images of mouse brain tissue and all-nuclei-highlighted fluorescence images, acquired simultaneously from the same tissue area. For quantitative comparison of a substantial pair of images, we present here a segmentation workflow that is applicable for both THG and fluorescence images, with a precision of 91.3 % and 95.8 % achieved respectively. We find that the correspondence between the main features of the two imaging modalities amounts to 88.9 %, providing quantitative evidence of the interpretation of dark holes as brain cells. Moreover, 80 % bright objects in THG images overlap with nuclei highlighted in the fluorescence images, and they are 2 times smaller than the dark holes, showing that cells of different morphologies can be recognized in THG images. We expect that the described quantitative comparison is applicable to other types of brain tissue and with more specific staining experiments for cell type identification.

A neuronal activation correlate in striatum and prefrontal cortex of prolonged cocaine intake.

Maladaptive changes in the involvement of striatal and frontal cortical regions in drug use are thought to underlie the progression to habitual drug use and loss of cognitive control over drug intake that occur with accumulating drug experience. The present experiments focus on changes in neuronal activity in these regions associated with short-term (10 days) and long-term (60 days) self-administration of cocaine. Quantitative in situ hybridization for the immediate early gene Mkp1 was combined with statistical parametric mapping to assess the distribution of neuronal activity. We hypothesized that neuronal activity in striatum would increase in its dorsal part and that activity in frontal cortex would decrease with prolonged cocaine self-administration experience. Expression of Mkp1 was profoundly increased after cocaine self-administration, and the magnitude of this effect was greater after short-term compared to long-term self-administration. Increased neuronal activity was seen in both dorsal and ventral sectors of the striatum after 10 days exposure to cocaine. However, enhanced activity was restricted to dorsomedial and dorsocentral striatum after 60 days cocaine self-administration. In virtually all medial prefrontal and most orbitofrontal areas, increased expression of Mkp1 was observed after 10 days of cocaine taking, whereas after 60 days, enhanced expression was restricted to caudal parts of medial prefrontal and caudomedial parts of orbitofrontal cortex. Our data reveal functional changes in cellular activity in striatum and frontal cortex with increasing cocaine self-administration experience. These changes might reflect the neural processes that underlie the descent from recreational drug taking to compulsive cocaine use.

Regional analysis of volumes and reproducibilities of automatic and manual hippocampal segmentations.

PURPOSE: Precise and reproducible hippocampus outlining is important to quantify hippocampal atrophy caused by neurodegenerative diseases and to spare the hippocampus in whole brain radiation therapy when performing prophylactic cranial irradiation or treating brain metastases. This study aimed to quantify systematic differences between methods by comparing regional volume and outline reproducibility of manual, FSL-FIRST and FreeSurfer hippocampus segmentations. MATERIALS AND METHODS: This study used a dataset from ADNI (Alzheimer's Disease Neuroimaging Initiative), including 20 healthy controls, 40 patients with mild cognitive impairment (MCI), and 20 patients with Alzheimer's disease (AD). For each subject back-to-back (BTB) T1-weighted 3D MPRAGE images were acquired at time-point baseline (BL) and 12 months later (M12). Hippocampi segmentations of all methods were converted into triangulated meshes, regional volumes were extracted and regional Jaccard indices were computed between the hippocampi meshes of paired BTB scans to evaluate reproducibility. Regional volumes and Jaccard indices were modelled as a function of group (G), method (M), hemisphere (H), time-point (T), region (R) and interactions. RESULTS: For the volume data the model selection procedure yielded the following significant main effects G, M, H, T and R and interaction effects G-R and M-R. The same model was found for the BTB scans. For all methods volumes reduces with the severity of disease. Significant fixed effects for the regional Jaccard index data were M, R and the interaction M-R. For all methods the middle region was most reproducible, independent of diagnostic group. FSL-FIRST was most and FreeSurfer least reproducible. DISCUSSION/CONCLUSION: A novel method to perform detailed analysis of subtle differences in hippocampus segmentation is proposed. The method showed that hippocampal segmentation reproducibility was best for FSL-FIRST and worst for Freesurfer. We also found systematic regional differences in hippocampal segmentation between different methods reinforcing the need of adopting harmonized protocols.

Extracting morphologies from third harmonic generation images of structurally normal human brain tissue.

MOTIVATION: The morphologies contained in 3D third harmonic generation (THG) images of human brain tissue can report on the pathological state of the tissue. However, the complexity of THG brain images makes the usage of modern image processing tools, especially those of image filtering, segmentation and validation, to extract this information challenging. RESULTS: We developed a salient edge-enhancing model of anisotropic diffusion for image filtering, based on higher order statistics. We split the intrinsic 3-phase segmentation problem into two 2-phase segmentation problems, each of which we solved with a dedicated model, active contour weighted by prior extreme. We applied the novel proposed algorithms to THG images of structurally normal ex-vivo human brain tissue, revealing key tissue components-brain cells, microvessels and neuropil, enabling statistical characterization of these components. Comprehensive comparison to manually delineated ground truth validated the proposed algorithms. Quantitative comparison to second harmonic generation/auto-fluorescence images, acquired simultaneously from the same tissue area, confirmed the correctness of the main THG features detected. AVAILABILITY AND IMPLEMENTATION: The software and test datasets are available from the authors. CONTACT: z.zhang@vu.nl. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Determination of head conductivity frequency response in vivo with optimized EIT-EEG.

Electroencephalography (EEG) benefits from accurate head models. Dipole source modelling errors can be reduced from over 1cm to a few millimetres by replacing generic head geometry and conductivity with tailored ones. When adequate head geometry is available, electrical impedance tomography (EIT) can be used to infer the conductivities of head tissues. In this study, the boundary element method (BEM) is applied with three-compartment (scalp, skull and brain) subject-specific head models. The optimal injection of small currents to the head with a modular EIT current injector, and voltage measurement by an EEG amplifier is first sought by simulations. The measurement with a 64-electrode EEG layout is studied with respect to three noise sources affecting EIT: background EEG, deviations from the fitting assumption of equal scalp and brain conductivities, and smooth model geometry deviations from the true head geometry. The noise source effects were investigated depending on the positioning of the injection and extraction electrode and the number of their combinations used sequentially. The deviation from equal scalp and brain conductivities produces rather deterministic errors in the three conductivities irrespective of the current injection locations. With a realistic measurement of around 2 min and around 8 distant distinct current injection pairs, the error from the other noise sources is reduced to around 10% or less in the skull conductivity. The analysis of subsequent real measurements, however, suggests that there could be subject-specific local thinnings in the skull, which could amplify the conductivity fitting errors. With proper analysis of multiplexed sinusoidal EIT current injections, the measurements on average yielded conductivities of 340 mS/m (scalp and brain) and 6.6 mS/m (skull) at 2 Hz. From 11 to 127 Hz, the conductivities increased by 1.6% (scalp and brain) and 6.7% (skull) on the average. The proper analysis was ensured by using recombination of the current injections into virtual ones, avoiding problems in location-specific skull morphology variations. The observed large intersubject variations support the need for in vivo measurement of skull conductivity, resulting in calibrated subject-specific head models.

Alzheimer Disease and Behavioral Variant Frontotemporal Dementia: Automatic Classification Based on Cortical Atrophy for Single-Subject Diagnosis.

Purpose To investigate the diagnostic accuracy of an image-based classifier to distinguish between Alzheimer disease (AD) and behavioral variant frontotemporal dementia (bvFTD) in individual patients by using gray matter (GM) density maps computed from standard T1-weighted structural images obtained with multiple imagers and with independent training and prediction data. Materials and Methods The local institutional review board approved the study. Eighty-four patients with AD, 51 patients with bvFTD, and 94 control subjects were divided into independent training (n = 115) and prediction (n = 114) sets with identical diagnosis and imager type distributions. Training of a support vector machine (SVM) classifier used diagnostic status and GM density maps and produced voxelwise discrimination maps. Discriminant function analysis was used to estimate suitability of the extracted weights for single-subject classification in the prediction set. Receiver operating characteristic (ROC) curves and area under the ROC curve (AUC) were calculated for image-based classifiers and neuropsychological z scores. Results Training accuracy of the SVM was 85% for patients with AD versus control subjects, 72% for patients with bvFTD versus control subjects, and 79% for patients with AD versus patients with bvFTD (P ≤ .029). Single-subject diagnosis in the prediction set when using the discrimination maps yielded accuracies of 88% for patients with AD versus control subjects, 85% for patients with bvFTD versus control subjects, and 82% for patients with AD versus patients with bvFTD, with a good to excellent AUC (range, 0.81-0.95; P ≤ .001). Machine learning-based categorization of AD versus bvFTD based on GM density maps outperforms classification based on neuropsychological test results. Conclusion The SVM can be used in single-subject discrimination and can help the clinician arrive at a diagnosis. The SVM can be used to distinguish disease-specific GM patterns in patients with AD and those with bvFTD as compared with normal aging by using common T1-weighted structural MR imaging. (©) RSNA, 2015.

Network analysis of EEG related functional MRI changes due to medication withdrawal in focal epilepsy.

Anti-epileptic drugs (AEDs) have a global effect on the neurophysiology of the brain which is most likely reflected in functional brain activity recorded with EEG and fMRI. These effects may cause substantial inter-subject variability in studies where EEG correlated functional MRI (EEG-fMRI) is used to determine the epileptogenic zone in patients who are candidate for epilepsy surgery. In the present study the effects on resting state fMRI are quantified in conditions with AED administration and after withdrawal of AEDs. EEG-fMRI data were obtained from 10 patients in the condition that the patient was on the steady-state maintenance doses of AEDs as prescribed (condition A) and after withdrawal of AEDs (condition B), at the end of a clinically standard pre-surgical long term video-EEG monitoring session. Resting state networks (RSN) were extracted from fMRI. The epileptic component (ICE) was identified by selecting the RSN component with the largest overlap with the EEG-fMRI correlation pattern. Changes in RSN functional connectivity between conditions A and B were quantified. EEG-fMRI correlation analysis was successful in 30% and 100% of the cases in conditions A and B, respectively. Spatial patterns of ICEs are comparable in conditions A and B, except for one patient for whom it was not possible to identify the ICE in condition A. However, the resting state functional connectivity is significantly increased in the condition after withdrawal of AEDs (condition B), which makes resting state fMRI potentially a new tool to study AED effects. The difference in sensitivity of EEG-fMRI in conditions A and B, which is not related to the number of epileptic EEG events occurring during scanning, could be related to the increased functional connectivity in condition B.

A three domain covariance framework for EEG/MEG data.

In this paper we introduce a covariance framework for the analysis of single subject EEG and MEG data that takes into account observed temporal stationarity on small time scales and trial-to-trial variations. We formulate a model for the covariance matrix, which is a Kronecker product of three components that correspond to space, time and epochs/trials, and consider maximum likelihood estimation of the unknown parameter values. An iterative algorithm that finds approximations of the maximum likelihood estimates is proposed. Our covariance model is applicable in a variety of cases where spontaneous EEG or MEG acts as source of noise and realistic noise covariance estimates are needed, such as in evoked activity studies, or where the properties of spontaneous EEG or MEG are themselves the topic of interest, like in combined EEG-fMRI experiments in which the correlation between EEG and fMRI signals is investigated. We use a simulation study to assess the performance of the estimator and investigate the influence of different assumptions about the covariance factors on the estimated covariance matrix and on its components. We apply our method to real EEG and MEG data sets.