Toward evaluation of multiresolution cortical thickness estimation with FreeSurfer, MaCRUISE, and BrainSuite.

Advances in Magnetic Resonance Imaging hardware and methodologies allow for promoting the cortical morphometry with submillimeter spatial resolution. In this paper, we generated 3D self-enhanced high-resolution (HR) MRI imaging, by adapting 1 deep learning architecture, and 3 standard pipelines, FreeSurfer, MaCRUISE, and BrainSuite, have been collectively employed to evaluate the cortical thickness. We systematically investigated the differences in cortical thickness estimation for MRI sequences at multiresolution homologously originated from the native image. It has been revealed that there systematically exhibited the preferences in determining both inner and outer cortical surfaces at higher resolution, yielding most deeper cortical surface placements toward GM/WM or GM/CSF boundaries, which directs a consistent reduction tendency of mean cortical thickness estimation; on the contrary, the lower resolution data will most probably provide a more coarse and rough evaluation in cortical surface reconstruction, resulting in a relatively thicker estimation. Although the differences of cortical thickness estimation at the diverse spatial resolution varied with one another, almost all led to roughly one-sixth to one-fifth significant reduction across the entire brain at the HR, independent to the pipelines we applied, which emphasizes on generally coherent improved accuracy in a data-independent manner and endeavors to cost-efficiency with quantitative opportunities.

The Connectivity Fingerprint of the Fusiform Gyrus Captures the Risk of Developing Autism in Infants with Tuberous Sclerosis Complex.

Tuberous sclerosis complex (TSC) is a rare genetic disorder characterized by benign tumors throughout the body; it is generally diagnosed early in life and has a high prevalence of autism spectrum disorder (ASD), making it uniquely valuable in studying the early development of autism, before neuropsychiatric symptoms become apparent. One well-documented deficit in ASD is an impairment in face processing. In this work, we assessed whether anatomical connectivity patterns of the fusiform gyrus, a central structure in face processing, capture the risk of developing autism early in life. We longitudinally imaged TSC patients at 1, 2, and 3 years of age with diffusion compartment imaging. We evaluated whether the anatomical connectivity fingerprint of the fusiform gyrus was associated with the risk of developing autism measured by the Autism Observation Scale for Infants (AOSI). Our findings suggest that the fusiform gyrus connectivity captures the risk of developing autism as early as 1 year of age and provides evidence that abnormal fusiform gyrus connectivity increases with age. Moreover, the identified connections that best capture the risk of developing autism involved the fusiform gyrus and limbic and paralimbic regions that were consistent with the ASD phenotype, involving an increased number of left-lateralized structures with increasing age.

Early white matter development is abnormal in tuberous sclerosis complex patients who develop autism spectrum disorder.

BACKGROUND: Autism spectrum disorder (ASD) is prevalent in tuberous sclerosis complex (TSC), occurring in approximately 50% of patients, and is hypothesized to be caused by disruption of neural circuits early in life. Tubers, or benign hamartomas distributed stochastically throughout the brain, are the most conspicuous of TSC neuropathology, but have not been consistently associated with ASD. Widespread neuropathology of the white matter, including deficits in myelination, neuronal migration, and axon formation, exist and may underlie ASD in TSC. We sought to identify the neural circuits associated with ASD in TSC by identifying white matter microstructural deficits in a prospectively recruited, longitudinally studied cohort of TSC infants. METHODS: TSC infants were recruited within their first year of life and longitudinally imaged at time of recruitment, 12 months of age, and at 24 months of age. Autism was diagnosed at 24 months of age with the ADOS-2. There were 108 subjects (62 TSC-ASD, 55% male; 46 TSC+ASD, 52% male) with at least one MRI and a 24-month ADOS, for a total of 187 MRI scans analyzed (109 TSC-ASD; 78 TSC+ASD). Diffusion tensor imaging properties of multiple white matter fiber bundles were sampled using a region of interest approach. Linear mixed effects modeling was performed to test the hypothesis that infants who develop ASD exhibit poor white matter microstructural integrity over the first 2 years of life compared to those who do not develop ASD. RESULTS: Subjects with TSC and ASD exhibited reduced fractional anisotropy in 9 of 17 white matter regions, sampled from the arcuate fasciculus, cingulum, corpus callosum, anterior limbs of the internal capsule, and the sagittal stratum, over the first 2 years of life compared to TSC subjects without ASD. Mean diffusivity trajectories did not differ between groups. CONCLUSIONS: Underconnectivity across multiple white matter fiber bundles develops over the first 2 years of life in subjects with TSC and ASD. Future studies examining brain-behavior relationships are needed to determine how variation in the brain structure is associated with ASD symptoms.

Reproducibility of Structural and Diffusion Tensor Imaging in the TACERN Multi-Center Study.

BACKGROUND: Multi-site MRI studies are often necessary for recruiting sufficiently sized samples when studying rare conditions. However, they require pooling data from multiple scanners into a single data set, and therefore it is critical to evaluate the variability of quantitative MRI measures within and across scanners used in multi-site studies. The aim of this study was to evaluate the reproducibility of structural and diffusion weighted (DW) MRI measurements acquired on seven scanners at five medical centers as part of the Tuberous Sclerosis Complex Autism Center of Excellence Research Network (TACERN) multisite study. METHODS: The American College of Radiology (ACR) phantom was imaged monthly to measure reproducibility of signal intensity and uniformity within and across seven 3T scanners from General Electric, Philips, and Siemens vendors. One healthy adult male volunteer was imaged repeatedly on all seven scanners under the TACERN structural and DW protocol (5 b = 0 s/mm2 and 30 b = 1000 s/mm2) over a period of 5 years (age 22-27 years). Reproducibility of inter- and intra-scanner brain segmentation volumes and diffusion tensor imaging metrics fractional anisotropy (FA) and mean diffusivity (MD) within white matter regions was quantified with coefficient of variation. RESULTS: The American College of Radiology Phantom signal intensity and uniformity were similar across scanners and changed little over time, with a mean intra-scanner coefficient of variation of 3.6 and 1.8%, respectively. The mean inter- and intra-scanner coefficients of variation of brain structure volumes derived from T1-weighted (T1w) images of the human phantom were 3.3 and 1.1%, respectively. The mean inter- and intra-scanner coefficients of variation of FA in white matter regions were 4.5 and 2.5%, while the mean inter- and intra-scanner coefficients of variation of MD in white matter regions were 5.4 and 1.5%. CONCLUSION: Our results suggest that volumetric and diffusion tensor imaging (DTI) measurements are highly reproducible between and within scanners and provide typical variation amplitudes that can be used as references to interpret future findings in the TACERN network.

Intelligent Labeling Based on Fisher Information for Medical Image Segmentation Using Deep Learning.

Deep convolutional neural networks (CNN) have recently achieved superior performance at the task of medical image segmentation compared to classic models. However, training a generalizable CNN requires a large amount of training data, which is difficult, expensive, and time-consuming to obtain in medical settings. Active Learning (AL) algorithms can facilitate training CNN models by proposing a small number of the most informative data samples to be annotated to achieve a rapid increase in performance. We proposed a new active learning method based on Fisher information (FI) for CNNs for the first time. Using efficient backpropagation methods for computing gradients together with a novel low-dimensional approximation of FI enabled us to compute FI for CNNs with a large number of parameters. We evaluated the proposed method for brain extraction with a patch-wise segmentation CNN model in two different learning scenarios: universal active learning and active semi-automatic segmentation. In both scenarios, an initial model was obtained using labeled training subjects of a source data set and the goal was to annotate a small subset of new samples to build a model that performs well on the target subject(s). The target data sets included images that differed from the source data by either age group (e.g. newborns with different image contrast) or underlying pathology that was not available in the source data. In comparison to several recently proposed AL methods and brain extraction baselines, the results showed that FI-based AL outperformed the competing methods in improving the performance of the model after labeling a very small portion of target data set (<0.25%).

A Comparison of Point and Complete Electrode Models in a Finite Difference Model of Invasive Electrode Measurements.

Invasive electrophysiological measurement of brain activity is commonly employed during epilepsy surgery to provide final validation of required resection regions. These data are critical to clinical decision making, but manual expert analysis of these data can be complicated by the need to relate individual electrode measurements to specific brain regions. To improve analysis of these data with source analysis, accurate bioelectric models are needed. Given the proximity of the measurement locations to the generating cortical sources, modeling of electrodetissue interactions is particularly important for invasive measurements. Here, we evaluate the effect of a finite difference complete electrode model on the accuracy of leadfield computations for invasive electrocorticography. Our results show that in the vicinity of electrode locations, use of the simpler point electrode model produces large topographic and magnitude differences that will likely impact the accuracy of computed source localizations.

Objective Evaluation of Multiple Sclerosis Lesion Segmentation using a Data Management and Processing Infrastructure.

We present a study of multiple sclerosis segmentation algorithms conducted at the international MICCAI 2016 challenge. This challenge was operated using a new open-science computing infrastructure. This allowed for the automatic and independent evaluation of a large range of algorithms in a fair and completely automatic manner. This computing infrastructure was used to evaluate thirteen methods of MS lesions segmentation, exploring a broad range of state-of-theart algorithms, against a high-quality database of 53 MS cases coming from four centers following a common definition of the acquisition protocol. Each case was annotated manually by an unprecedented number of seven different experts. Results of the challenge highlighted that automatic algorithms, including the recent machine learning methods (random forests, deep learning, …), are still trailing human expertise on both detection and delineation criteria. In addition, we demonstrate that computing a statistically robust consensus of the algorithms performs closer to human expertise on one score (segmentation) although still trailing on detection scores.

Localization of stereo-electroencephalography signals using a finite difference complete electrode model.

Surgical intervention in epilepsy aims to eliminate seizures in refractory patients by resecting the tissue responsible for seizure onset. Stereo-electroencephalography (sEEG) provides highly accurate but invasive electrophysiological measurements using narrow multi-contact electrodes implanted stereotactically through small holes in the skull. However, the three dimensional nature of sEEG measurements make observed seizure onsets difficult to associate with physical cortical regions. Three dimensional source localization from sEEG measurements can improve the interpretation of this data, but requires more accurate modeling as compared to localization from scalp EEG. Here, we present a finite difference approach that models the contact impedance and physical extent of each electrode (the so-called complete electrode model), to localize brain electrical activity from sEEG measurements. We applied this model to MRI and CT in a patient with intractable epilepsy, and reconstructed activity associated with multiple types of recurrent ictal spikes observed in sEEG. Independently, the neurosurgeon resected the clinically determined seizure focus, creating a resection cavity, and rendering the patient free of seizures. Our localization placed the seizure focus at a focal region in the occipital lobe, entirely contained within the resection region.

Longitudinal multiple sclerosis lesion segmentation: Resource and challenge.

In conjunction with the ISBI 2015 conference, we organized a longitudinal lesion segmentation challenge providing training and test data to registered participants. The training data consisted of five subjects with a mean of 4.4 time-points, and test data of fourteen subjects with a mean of 4.4 time-points. All 82 data sets had the white matter lesions associated with multiple sclerosis delineated by two human expert raters. Eleven teams submitted results using state-of-the-art lesion segmentation algorithms to the challenge, with ten teams presenting their results at the conference. We present a quantitative evaluation comparing the consistency of the two raters as well as exploring the performance of the eleven submitted results in addition to three other lesion segmentation algorithms. The challenge presented three unique opportunities: (1) the sharing of a rich data set; (2) collaboration and comparison of the various avenues of research being pursued in the community; and (3) a review and refinement of the evaluation metrics currently in use. We report on the performance of the challenge participants, as well as the construction and evaluation of a consensus delineation. The image data and manual delineations will continue to be available for download, through an evaluation website2 as a resource for future researchers in the area. This data resource provides a platform to compare existing methods in a fair and consistent manner to each other and multiple manual raters.

Tubers are neither static nor discrete: Evidence from serial diffusion tensor imaging.

OBJECTIVE: To assess the extent and evolution of tissue abnormality of tubers, perituber tissue, and normal-appearing white matter (NAWM) in patients with tuberous sclerosis complex using serial diffusion tensor imaging. METHODS: We applied automatic segmentation based on a combined global-local intensity mixture model of 3T structural and 35 direction diffusion tensor MRIs (diffusion tensor imaging) to define 3 regions: tuber tissue, an equal volume perituber rim, and the remaining NAWM. For each patient, scan, lobe, and tissue type, we analyzed the averages of mean diffusivity (MD) and fractional anisotropy (FA) in a generalized additive mixed model. RESULTS: Twenty-five patients (mean age 5.9 years; range 0.5-24.5 years) underwent 2 to 6 scans each, totaling 70 scans. Average time between scans was 1.2 years (range 0.4-2.9). Patient scans were compared with those of 73 healthy controls. FA values were lowest, and MD values were highest in tubers, next in perituber tissue, then in NAWM. Longitudinal analysis showed a positive (FA) and negative (MD) correlation with age in tubers, perituber tissue, and NAWM. All 3 tissue types followed a biexponential developmental trajectory, similar to the white matter of controls. An additional qualitative analysis showed a gradual transition of diffusion values across the tissue type boundaries. CONCLUSIONS: Similar to NAWM, tuber and perituber tissues in tuberous sclerosis complex undergo microstructural evolution with age. The extent of diffusion abnormality decreases with distance to the tuber, in line with known extension of histologic, immunohistochemical, and molecular abnormalities beyond tuber pathology.

A Model of Population and Subject (MOPS) Intensities With Application to Multiple Sclerosis Lesion Segmentation.

White matter (WM) lesions are thought to play an important role in multiple sclerosis (MS) disease burden. Recent work in the automated segmentation of white matter lesions from magnetic resonance imaging has utilized a model in which lesions are outliers in the distribution of tissue signal intensities across the entire brain of each patient. However, the sensitivity and specificity of lesion detection and segmentation with these approaches have been inadequate. In our analysis, we determined this is due to the substantial overlap between the whole brain signal intensity distribution of lesions and normal tissue. Inspired by the ability of experts to detect lesions based on their local signal intensity characteristics, we propose a new algorithm that achieves lesion and brain tissue segmentation through simultaneous estimation of a spatially global within-the-subject intensity distribution and a spatially local intensity distribution derived from a healthy reference population. We demonstrate that MS lesions can be segmented as outliers from this intensity model of population and subject. We carried out extensive experiments with both synthetic and clinical data, and compared the performance of our new algorithm to those of state-of-the art techniques. We found this new approach leads to a substantial improvement in the sensitivity and specificity of lesion detection and segmentation.

Electrode localization for planning surgical resection of the epileptogenic zone in pediatric epilepsy.

PURPOSE: In planning for a potentially curative resection of the epileptogenic zone in patients with pediatric epilepsy, invasive monitoring with intracranial EEG is often used to localize the seizure onset zone and eloquent cortex. A precise understanding of the location of subdural strip and grid electrodes on the brain surface, and of depth electrodes in the brain in relationship to eloquent areas is expected to facilitate pre-surgical planning. METHODS: We developed a novel algorithm for the alignment of intracranial electrodes, extracted from post-operative CT, with pre-operative MRI. Our goal was to develop a method of achieving highly accurate localization of subdural and depth electrodes, in order to facilitate surgical planning. Specifically, we created a patient-specific 3D geometric model of the cortical surface from automatic segmentation of a pre-operative MRI, automatically segmented electrodes from post-operative CT, and projected each set of electrodes onto the brain surface after alignment of the CT to the MRI. Also, we produced critical visualization of anatomical landmarks, e.g., vasculature, gyri, sulci, lesions, or eloquent cortical areas, which enables the epilepsy surgery team to accurately estimate the distance between the electrodes and the anatomical landmarks, which might help for better assessment of risks and benefits of surgical resection. RESULTS: Electrode localization accuracy was measured using knowledge of the position of placement from 2D intra-operative photographs in ten consecutive subjects who underwent intracranial EEG for pediatric epilepsy. Average spatial accuracy of localization was 1.31 ± 0.69 mm for all 385 visible electrodes in the photos. CONCLUSIONS: In comparison with previously reported approaches, our algorithm is able to achieve more accurate alignment of strip and grid electrodes with minimal user input. Unlike manual alignment procedures, our algorithm achieves excellent alignment without time-consuming and difficult judgements from an operator.