Automatic detection and quantification of hippocampal atrophy on MRI in temporal lobe epilepsy: a proof-of-principle study

A Quantitative Imaging Biomarker Supporting Radiological Assessment of Hippocampal Sclerosis Derived From Deep Learning-Based Segmentation of T1w-MRI

Purpose

Hippocampal volumetry is an important biomarker to quantify atrophy in patients with mesial temporal lobe epilepsy. We investigate the sensitivity of automated segmentation methods to support radiological assessments of hippocampal sclerosis (HS). Results from FreeSurfer and FSL-FIRST are contrasted to a deep learning (DL)-based segmentation method.

Materials and Methods

We used T1-weighted MRI scans from 105 patients with epilepsy and 354 healthy controls. FreeSurfer, FSL, and a DL-based method were applied for brain anatomy segmentation. We calculated effect sizes (Cohen's d) between left/right HS and healthy controls based on the asymmetry of hippocampal volumes. Additionally, we derived 14 shape features from the segmentations and determined the most discriminating feature to identify patients with hippocampal sclerosis by a support vector machine (SVM).

Results

Deep learning-based segmentation of the hippocampus was the most sensitive to detecting HS. The effect sizes of the volume asymmetries were larger with the DL-based segmentations (HS left d= −4.2, right = 4.2) than with FreeSurfer (left= −3.1, right = 3.7) and FSL (left= −2.3, right = 2.5). For the classification based on the shape features, the surface-to-volume ratio was identified as the most important feature. Its absolute asymmetry yielded a higher area under the curve (AUC) for the deep learning-based segmentation (AUC = 0.87) than for FreeSurfer (0.85) and FSL (0.78) to dichotomize HS from other epilepsy cases. The robustness estimated from repeated scans was statistically significantly higher with DL than all other methods.

Conclusion

Our findings suggest that deep learning-based segmentation methods yield a higher sensitivity to quantify hippocampal sclerosis than atlas-based methods and derived shape features are more robust. We propose an increased asymmetry in the surface-to-volume ratio of the hippocampus as an easy-to-interpret quantitative imaging biomarker for HS.

Different FreeSurfer versions might generate different statistical outcomes in case-control comparison studies

PURPOSE

Neuroimaging pipelines have long been known to generate mildly differing results depending on various factors, including software version. While considered generally acceptable and within the margin of reasonable error, little is known about their effect in common research scenarios such as inter-group comparisons between healthy controls and various pathological conditions. The aim of the presented study was to explore the differences in the inferences and statistical significances in a model situation comparing volumetric parameters between healthy controls and type 1 diabetes patients using various FreeSurfer versions.

METHODS

T1- and T2-weighted structural scans of healthy controls and type 1 diabetes patients were processed with FreeSurfer 5.3, FreeSurfer 5.3 HCP, FreeSurfer 6.0 and FreeSurfer 7.1, followed by inter-group statistical comparison using outputs of individual FreeSurfer versions.

RESULTS

Worryingly, FreeSurfer 5.3 detected both cortical and subcortical volume differences out of the preselected regions of interest, but newer versions such as FreeSurfer 5.3 HCP and FreeSurfer 6.0 reported only subcortical differences of lower magnitude and FreeSurfer 7.1 failed to find any statistically significant inter-group differences.

CONCLUSION

Since group averages of individual FreeSurfer versions closely matched, in keeping with previous literature, the main origin of this disparity seemed to lie in substantially higher within-group variability in the model pathological condition. Ergo, until validation in common research scenarios as case-control comparison studies is included into the development process of new software suites, confirmatory analyses utilising a similar software based on analogous, but not fully equivalent principles, might be considered as supplement to careful quality control.

Prospective Quantitative Neuroimaging Analysis of Putative Temporal Lobe Epilepsy

Purpose: A prospective study of individual and combined quantitative imaging applications for lateralizing epileptogenicity was performed in a cohort of consecutive patients with a putative diagnosis of mesial temporal lobe epilepsy (mTLE). Methods: Quantitative metrics were applied to MRI and nuclear medicine imaging studies as part of a comprehensive presurgical investigation. The neuroimaging analytics were conducted remotely to remove bias. All quantitative lateralizing tools were trained using a separate dataset. Outcomes were determined after 2 years. Of those treated, some underwent resection, and others were implanted with a responsive neurostimulation (RNS) device. Results: Forty-eight consecutive cases underwent evaluation using nine attributes of individual or combinations of neuroimaging modalities: 1) hippocampal volume, 2) FLAIR signal, 3) PET profile, 4) multistructural analysis (MSA), 5) multimodal model analysis (MMM), 6) DTI uncertainty analysis, 7) DTI connectivity, and 9) fMRI connectivity. Of the 24 patients undergoing resection, MSA, MMM, and PET proved most effective in predicting an Engel class 1 outcome (>80% accuracy). Both hippocampal volume and FLAIR signal analysis showed 76% and 69% concordance with an Engel class 1 outcome, respectively. Conclusion: Quantitative multimodal neuroimaging in the context of a putative mTLE aids in declaring laterality. The degree to which there is disagreement among the various quantitative neuroimaging metrics will judge whether epileptogenicity can be confined sufficiently to a particular temporal lobe to warrant further study and choice of therapy. Prediction models will improve with continued exploration of combined optimal neuroimaging metrics.

CERMEP-IDB-MRXFDG: a database of 37 normal adult human brain [18F]FDG PET, T1 and FLAIR MRI, and CT images available for research

We present a database of cerebral PET FDG and anatomical MRI for 37 normal adult human subjects (CERMEP-IDB-MRXFDG). Thirty-nine participants underwent static [18F]FDG PET/CT and MRI, resulting in [18F]FDG PET, T1 MPRAGE MRI, FLAIR MRI, and CT images. Two participants were excluded after visual quality control. We describe the acquisition parameters, the image processing pipeline and provide participants' individual demographics (mean age 38 ± 11.5 years, range 23-65, 20 women). Volumetric analysis of the 37 T1 MRIs showed results in line with the literature. A leave-one-out assessment of the 37 FDG images using Statistical Parametric Mapping (SPM) yielded a low number of false positives after exclusion of artefacts. The database is stored in three different formats, following the BIDS common specification: (1) DICOM (data not processed), (2) NIFTI (multimodal images coregistered to PET subject space), (3) NIFTI normalized (images normalized to MNI space). Bona fide researchers can request access to the database via a short form.

Voxel-Based Morphometry-from Hype to Hope. A Study on Hippocampal Atrophy in Mesial Temporal Lobe Epilepsy

BACKGROUND AND PURPOSE

Automated volumetry of the hippocampus is considered useful to assist the diagnosis of hippocampal sclerosis in temporal lobe epilepsy. However, voxel-based morphometry is rarely used for individual subjects because of high rates of false-positives. We investigated whether an approach with high dimensional warping to the template and nonparametric statistics would be useful to detect hippocampal atrophy in patients with hippocampal sclerosis.

MATERIALS AND METHODS

We performed single-subject voxel-based morphometry with nonparametric statistics within the framework of Statistical Parametric Mapping to compare MRI from 26 well-characterized patients with temporal lobe epilepsy individually against a group of 110 healthy controls. The following statistical threshold was used: P < .05 corrected for multiple comparisons with family-wise error over the region of interest right and left hippocampus.

RESULTS

The sensitivity for the detection of atrophy related to hippocampal sclerosis was 0.92 (95% CI, 0.67-0.99) for the right hippocampus and 0.60 (0.31-0.83) for the left, and the specificity for volume changes was 0.98 (0.93-0.99). All clusters of decreased hippocampal volumes were correctly lateralized to the seizure focus. Hippocampal volume decrease was in accordance with neuronal cell loss on histology reports.

CONCLUSIONS

Nonparametric voxel-based morphometry is sensitive and specific for hippocampal atrophy in patients with mesial temporal lobe epilepsy and may be useful in clinical practice.

Diagnosis of Hippocampal Sclerosis in Children: Comparison of Automated Brain MRI Volumetry and Readers of Varying Experience

BACKGROUND. Hippocampal sclerosis (HS) is a leading cause of medically refractory temporal lobe epilepsy in children. The diagnosis is clinically important because most patients with HS have good postsurgical outcomes. OBJECTIVE. This study aimed to compare the performance of a fully automated brain MRI volumetric tool and readers of varying experience in the diagnosis of pediatric HS. METHODS. This retrospective study included 22 children with HS diagnosed between January 2009 and January 2020 who underwent surgery and an age- and sex-matched control group of 44 patients with normal MRI findings and extratemporal epilepsy diagnosed between January 2009 and January 2020. Regional brain MRI volumes were calculated from a high-resolution 3D T1-weighted sequence using an automated volumetric tool. Four readers (two pediatric radiologists [experienced] and two radiology residents [inexperienced]) visually assessed each MRI examination to score the likelihood of HS. One inexperienced reader repeated the evaluations using the volumetric tool. The area under the ROC curve (AUROC), sensitivity, and specificity for HS were computed for the volumetric tool and the readers. Diagnostic performances were compared using McNemar tests. RESULTS. In the HS group, the hippocampal volume (affected vs unaffected, 3.54 vs 4.59 cm³) and temporal lobe volume (affected vs unaffected, 5.66 vs 6.89 cm³) on the affected side were significantly lower than on the unaffected side (p < .001) using the volu-metric tool. AUROCs of the volumetric tool were 0.813-0.842 in patients with left HS and 0.857-0.980 in patients with right HS (sensitivity, 81.8-90.9%; specificity, 70.5-95.5%). No significant difference (p = .63 to > .99) was observed between the performance of the volumetric tool and the performance of the two experienced readers as well as one inexperienced reader (AUROCs for these three readers, 0.968-0.999; sensitivity, 86.4-90.9%; specificity, 100.0%). The volumetric tool had better performance (p < .001) than the other inexperienced reader (AUROC, 0.806; sensitivity, 81.8%; specificity, 47.7%). With subsequent use of the tool, this inexperienced reader showed a nonsignificant increase (p = .10) in AUROC (0.912) as well as in sensitivity (86.4%) and specificity (84.1%). CONCLUSION. A fully automated volumetric brain MRI tool outperformed one of two inexperienced readers and performed as well as two experienced readers in identifying and lateralizing HS in pediatric patients. The tool improved the performance of an inexperienced reader. CLINICAL IMPACT. A fully automated volumetric tool facilitates diagnosis of HS in pediatric patients, especially for an inexperienced reader.

Automated MRI-based volumetry of basal ganglia and thalamus at the chronic phase of cortical stroke

Purpose

We aimed at assessing the potential of automated MR morphometry to assess individual basal ganglia and thalamus volumetric changes at the chronic phase after cortical stroke.

Methods

Ninety-six patients (mean age: 65 ± 18 years, male 55) with cortical stroke at the chronic phase were retrospectively included. Patients were scanned at 1.5 T or 3 T using a T1-MPRAGE sequence. Resulting 3D images were processed with the MorphoBox prototype software to automatically segment basal ganglia and thalamus structures, and to obtain Z scores considering the confounding effects of age and sex. Stroke volume was estimated by manual delineation on T2-SE imaging. Z scores were compared between ipsi- and contralateral stroke side and according to the vascular territory. Potential relationship between Z scores and stroke volume was assessed using the Spearman correlation coefficient.

Results

Basal ganglia and thalamus volume Z scores were lower ipsilaterally to MCA territory stroke (p values < 0.034) while they were not different between ipsi- and contralateral stroke sides in non-MCA territory stroke (p values > 0.37). In MCA territory stroke, ipsilateral caudate nucleus (rho = − 0.34, p = 0.007), putamen (rho = − 0.50, p < 0.001), pallidum (rho = − 0.44, p < 0.001), and thalamus (rho = − 0.48, p < 0.001) volume Z scores negatively correlated with the cortical stroke volume. This relation was not influenced by cardiovascular risk factors or time since stroke.

Conclusion

Automated MR morphometry demonstrated atrophy of ipsilateral basal ganglia and thalamus at the chronic phase after cortical stroke in the MCA territory. The atrophy was related to stroke volume. These results confirm the potential role for automated MRI morphometry to assess remote changes after stroke.

Longitudinal Automatic Segmentation of Hippocampal Subfields (LASHiS) using multi-contrast MRI

The volumetric and morphometric examination of hippocampus formation subfields in a longitudinal manner using in vivo MRI could lead to more sensitive biomarkers for neuropsychiatric disorders and diseases including Alzheimer's disease, as the anatomical subregions are functionally specialised. Longitudinal processing allows for increased sensitivity due to reduced confounds of inter-subject variability and higher effect-sensitivity than cross-sectional designs. We examined the performance of a new longitudinal pipeline (Longitudinal Automatic Segmentation of Hippocampus Subfields [LASHiS]) against three freely available, published approaches. LASHiS automatically segments hippocampus formation subfields by propagating labels from cross-sectionally labelled time point scans using joint-label fusion to a non-linearly realigned 'single subject template', where image segmentation occurs free of bias to any individual time point. Our pipeline measures tissue characteristics available in in vivo high-resolution MRI scans, at both clinical (3 ​T) and ultra-high field strength (7 ​T) and differs from previous longitudinal segmentation pipelines in that it leverages multi-contrast information in the segmentation process. LASHiS produces robust and reliable automatic multi-contrast segmentations of hippocampus formation subfields, as measured by higher volume similarity coefficients and Dice coefficients for test-retest reliability and robust longitudinal Bayesian Linear Mixed Effects results at 7 ​T, while showing sound results at 3 ​T. All code for this project including the automatic pipeline is available at https://github.com/CAIsr/LASHiS.

Bayesian Generative Models for Knowledge Transfer in MRI Semantic Segmentation Problems

Automatic segmentation methods based on deep learning have recently demonstrated state-of-the-art performance, outperforming the ordinary methods. Nevertheless, these methods are inapplicable for small datasets, which are very common in medical problems. To this end, we propose a knowledge transfer method between diseases via the Generative Bayesian Prior network. Our approach is compared to a pre-train approach and random initialization and obtains the best results in terms of Dice Similarity Coefficient metric for the small subsets of the Brain Tumor Segmentation 2018 database (BRATS2018).

Automated and manual hippocampal segmentation techniques: Comparison of results, reproducibility and clinical applicability

BACKGROUND

Imaging techniques used to measure hippocampal atrophy are key to understanding the clinical progression of Alzheimer's disease (AD). Various semi-automated hippocampal segmentation techniques are available and require human expert input to learn how to accurately segment new data. Our goal was to compare 1) the performance of our automated hippocampal segmentation technique relative to manual segmentations, and 2) the performance of our automated technique when provided with a training set from two different raters. We also explored the ability of hippocampal volumes obtained using manual and automated hippocampal segmentations to predict conversion from MCI to AD.

METHODS

We analyzed 161 1.5 T T1-weighted brain magnetic resonance images (MRI) from the ADCS Donepezil/Vitamin E clinical study. All subjects carried a diagnosis of mild cognitive impairment (MCI). Three different segmentation outputs (one produced by manual tracing and two produced by a semi-automated algorithm trained with training sets developed by two raters) were compared using single measure intraclass correlation statistics (smICC). The radial distance method was used to assess each segmentation technique's ability to detect hippocampal atrophy in 3D. We then compared how well each segmentation method detected baseline hippocampal differences between MCI subjects who remained stable (MCInc) and those who converted to AD (MCIc) during the trial. Our statistical maps were corrected for multiple comparisons using permutation-based statistics with a threshold of p < .01.

RESULTS

Our smICC analyses showed significant agreement between the manual and automated hippocampal segmentations from rater 1 [right smICC = 0.78 (95%CI 0.72-0.84); left smICC = 0.79 (95%CI 0.72-0.85)], the manual segmentations from rater 1 versus the automated segmentations from rater 2 [right smICC = 0.78 (95%CI 0.7-0.84); left smICC = 0.78 (95%CI 0.71-0.84)], and the automated segmentations of rater 1 versus rater 2 [right smICC = 0.97 (95%CI 0.96-0.98); left smICC = 0.97 (95%CI 0.96-0.98)]. All three segmentation methods detected significant CA1 and subicular atrophy in MCIc compared to MCInc at baseline (manual: right pcorrected = 0.0112, left pcorrected = 0.0006; automated rater 1: right pcorrected = 0.0318, left pcorrected = 0.0302; automated rater 2: right pcorrected = 0.0029, left pcorrected = 0.0166).

CONCLUSIONS

The hippocampal volumes obtained with a fast semi-automated segmentation method were highly comparable to the ones obtained with the labor-intensive manual segmentation method. The AdaBoost automated hippocampal segmentation technique is highly reliable allowing the efficient analysis of large data sets.

Clinical validation of automated hippocampal segmentation in temporal lobe epilepsy

OBJECTIVE

To provide a multi-atlas framework for automated hippocampus segmentation in temporal lobe epilepsy (TLE) and clinically validate the results with respect to surgical lateralization and post-surgical outcome.

METHODS

We retrospectively identified 47 TLE patients who underwent surgical resection and 12 healthy controls. T1-weighted 3 T MRI scans were acquired for all subjects, and patients were identified by a neuroradiologist with regards to lateralization and degree of hippocampal sclerosis (HS). Automated segmentation was implemented through the Joint Label Fusion/Corrective Learning (JLF/CL) method. Gold standard lateralization was determined from the surgically resected side in Engel I (seizure-free) patients at the two-year timepoint. ROC curves were used to identify appropriate thresholds for hippocampal asymmetry ratios, which were then used to analyze JLF/CL lateralization.

RESULTS

The optimal template atlas based on subject images with varying appearances, from normal-appearing to severe HS, was demonstrated to be composed entirely of normal-appearing subjects, with good agreement between automated and manual segmentations. In applying this atlas to 26 surgically resected seizure-free patients at a two-year timepoint, JLF/CL lateralized seizure onset 92% of the time. In comparison, neuroradiology reads lateralized 65% of patients, but correctly lateralized seizure onset in these patients 100% of the time. When compared to lateralized neuroradiology reads, JLF/CL was in agreement and correctly lateralized all 17 patients. When compared to nonlateralized radiology reads, JLF/CL correctly lateralized 78% of the nine patients.

SIGNIFICANCE

While a neuroradiologist's interpretation of MR imaging is a key, albeit imperfect, diagnostic tool for seizure localization in medically-refractory TLE patients, automated hippocampal segmentation may provide more efficient and accurate epileptic foci localization. These promising findings demonstrate the clinical utility of automated segmentation in the TLE MR imaging pipeline prior to surgical resection, and suggest that further investigation into JLF/CL-assisted MRI reading could improve clinical outcomes. Our JLF/CL software is publicly available at https://www.nitrc.org/projects/ashs/.

Data mining MR image features of select structures for lateralization of mesial temporal lobe epilepsy

PURPOSE

This study systematically investigates the predictive power of volumetric imaging feature sets extracted from select neuroanatomical sites in lateralizing the epileptogenic focus in mesial temporal lobe epilepsy (mTLE) patients.

METHODS

A cohort of 68 unilateral mTLE patients who had achieved an Engel class I outcome postsurgically was studied retrospectively. The volumes of multiple brain structures were extracted from preoperative magnetic resonance (MR) images in each. The MR image data set consisted of 54 patients with imaging evidence for hippocampal sclerosis (HS-P) and 14 patients without (HS-N). Data mining techniques (i.e., feature extraction, feature selection, machine learning classifiers) were applied to provide measures of the relative contributions of structures and their correlations with one another. After removing redundant correlated structures, a minimum set of structures was determined as a marker for mTLE lateralization.

RESULTS

Using a logistic regression classifier, the volumes of both hippocampus and amygdala showed correct lateralization rates of 94.1%. This reflected about 11.7% improvement in accuracy relative to using hippocampal volume alone. The addition of thalamic volume increased the lateralization rate to 98.5%. This ternary-structural marker provided a 100% and 92.9% mTLE lateralization accuracy, respectively, for the HS-P and HS-N groups.

CONCLUSIONS

The proposed tristructural MR imaging biomarker provides greater lateralization accuracy relative to single- and double-structural biomarkers and thus, may play a more effective role in the surgical decision-making process. Also, lateralization of the patients with insignificant atrophy of hippocampus by the proposed method supports the notion of associated structural changes involving the amygdala and thalamus.

A Subset of Dogs with Presumptive Idiopathic Epilepsy Show Hippocampal Asymmetry: A Volumetric Comparison with Non-Epileptic Dogs Using MRI

MRI-acquired volumetric measurements from 100 dogs with presumptive idiopathic epilepsy (IE) and 41 non-epileptic (non-IE) dogs were used to determine if hippocampal asymmetry exists in the IE as compared to the non-IE dogs. MRI databases from three institutions were searched for dogs that underwent MRI of the brain and were determined to have IE and those that were considered non-IE dogs. Volumes of the right and left hippocampi were measured using Mimics^® software. Median hippocampal volumes of IE and non-IE dogs were 0.47 and 0.53 cm³, respectively. There was no significant difference in overall hippocampal volume between IE and non-IE dogs; however, IE dogs had greater hippocampal asymmetry than non-IE dogs (P < 0.012). A threshold value of 1.16 from the hippocampal ratio had an 85% specificity for identifying IE-associated asymmetry. Thirty five percent of IE dogs had a hippocampal ratio >1.16. Asymmetry was not associated with any particular hemisphere (P = 0.67). Our study indicates that hippocampal asymmetry occurs in a subset of dogs with presumptive idiopathic/genetic epilepsy, suggesting a structural etiology to some cases of IE.

Personalized structural image analysis in patients with temporal lobe epilepsy

Volumetric and morphometric studies have demonstrated structural abnormalities related to chronic epilepsies on a cohort- and population-based level. On a single-patient level, specific patterns of atrophy or cortical reorganization may be widespread and heterogeneous but represent potential targets for further personalized image analysis and surgical therapy. The goal of this study was to compare morphometric data analysis in 37 patients with temporal lobe epilepsies with expert-based image analysis, pre-informed by seizure semiology and ictal scalp EEG. Automated image analysis identified abnormalities exceeding expert-determined structural epileptogenic lesions in 86% of datasets. If EEG lateralization and expert MRI readings were congruent, automated analysis detected abnormalities consistent on a lobar and hemispheric level in 82% of datasets. However, in 25% of patients EEG lateralization and expert readings were inconsistent. Automated analysis localized to the site of resection in 60% of datasets in patients who underwent successful epilepsy surgery. Morphometric abnormalities beyond the mesiotemporal structures contributed to subtype characterisation. We conclude that subject-specific morphometric information is in agreement with expert image analysis and scalp EEG in the majority of cases. However, automated image analysis may provide non-invasive additional information in cases with equivocal radiological and neurophysiological findings.

Gyri of the human parietal lobe: Volumes, spatial extents, automatic labelling, and probabilistic atlases

Accurately describing the anatomy of individual brains enables interlaboratory communication of functional and developmental studies and is crucial for possible surgical interventions. The human parietal lobe participates in multimodal sensory integration including language processing and also contains the primary somatosensory area. We describe detailed protocols to subdivide the parietal lobe, analyze morphological and volumetric characteristics, and create probabilistic atlases in MNI152 stereotaxic space. The parietal lobe was manually delineated on 3D T1 MR images of 30 healthy subjects and divided into four regions: supramarginal gyrus (SMG), angular gyrus (AG), superior parietal lobe (supPL) and postcentral gyrus (postCG). There was the expected correlation of male gender with larger brain and intracranial volume. We examined a wide range of anatomical features of the gyri and the sulci separating them. At least a rudimentary primary intermediate sulcus of Jensen (PISJ) separating SMG and AG was identified in nearly all (59/60) hemispheres. Presence of additional gyri in SMG and AG was related to sulcal features and volumetric characteristics. The parietal lobe was slightly (2%) larger on the left, driven by leftward asymmetries of the postCG and SMG. Intersubject variability was highest for SMG and AG, and lowest for postCG. Overall the morphological characteristics tended to be symmetrical, and volumes also tended to covary between hemispheres. This may reflect developmental as well as maturation factors. To assess the accuracy with which the labels can be used to segment newly acquired (unlabelled) T1-weighted brain images, we applied multi-atlas label propagation software (MAPER) in a leave-one-out experiment and compared the resulting automatic labels with the manually prepared ones. The results showed strong agreement (mean Jaccard index 0.69, corresponding to a mean Dice index of 0.82, average mean volume error of 0.6%). Stereotaxic probabilistic atlases of each subregion were obtained. They illustrate the physiological brain torque, with structures in the right hemisphere positioned more anteriorly than in the left, and right/left positional differences of up to 10 mm. They also allow an assessment of sulcal variability, e.g. low variability for parietooccipital fissure and cingulate sulcus. Illustrated protocols, individual label sets, probabilistic atlases, and a maximum-probability atlas which takes into account surrounding structures are available for free download under academic licences.

Automated volumetry for unilateral hippocampal sclerosis detection in patients with temporal lobe epilepsy

Hippocampal sclerosis (HS) is the most common cause of temporal lobe epilepsy (TLE) and can be identified in magnetic resonance imaging as hippocampal atrophy and subsequent volume loss. Detecting this kind of abnormalities through simple radiological assessment could be difficult, even for experienced radiologists. For that reason, hippocampal volumetry is generally used to support this kind of diagnosis. Manual volumetry is the traditional approach but it is time consuming and requires the physician to be familiar with neuroimaging software tools. In this paper, we propose an automated method, written as a script that uses FSL-FIRST, to perform hippocampal segmentation and compute an index to quantify hippocampi asymmetry (HAI). We compared the automated detection of HS (left or right) based on the HAI with the agreement of two experts in a group of 19 patients and 15 controls, achieving 84.2% sensitivity, 86.7% specificity and a Cohen's kappa coefficient of 0.704. The proposed method is integrated in the "Advanced Brain Imaging Lab" (ABrIL) cloud neurocomputing platform. The automated procedure is 77% (on average) faster to compute vs. the manual volumetry segmentation performed by an experienced physician.

Increased central microglial activation associated with peripheral cytokine levels in premanifest Huntington's disease gene carriers

Previous studies have shown activation of the immune system and altered immune response in Huntington's disease (HD) gene carriers. Here, we hypothesized that peripheral and central immune responses could be concurrent pathophysiological events and represent a global innate immune response to the toxic effects of mutant huntingtin in HD gene carriers. We sought to investigate our hypothesis using [(11)C]PK11195 PET as a translocator protein (TSPO) marker of central microglial activation, together with assessment of peripheral plasma cytokine levels in a cohort of premanifest HD gene carriers who were more than a decade from predicted symptomatic conversion. Data were also compared to those from a group of healthy controls matched for age and gender. We found significantly increased peripheral plasma IL-1β levels in premanifest HD gene carriers compared to the group of normal controls (P=0.018). Premanifest HD gene carriers had increased TSPO levels in cortical, basal ganglia and thalamic brain regions (P<0.001). Increased microglial activation in somatosensory cortex correlated with higher plasma levels of IL-1β (rs=0.87, P=0.013), IL-6 (rs=0.85, P=0.013), IL-8 (rs=0.68, P=0.045) and TNF-α (rs=0.79; P=0.013). Our findings provide first in vivo evidence for an association between peripheral and central immune responses in premanifest HD gene carriers, and provide further supporting evidence for the role of immune dysfunction in the pathogenesis of HD.

Multi-atlas segmentation of biomedical images: A survey

Multi-atlas segmentation (MAS), first introduced and popularized by the pioneering work of Rohlfing, et al. (2004), Klein, et al. (2005), and Heckemann, et al. (2006), is becoming one of the most widely-used and successful image segmentation techniques in biomedical applications. By manipulating and utilizing the entire dataset of "atlases" (training images that have been previously labeled, e.g., manually by an expert), rather than some model-based average representation, MAS has the flexibility to better capture anatomical variation, thus offering superior segmentation accuracy. This benefit, however, typically comes at a high computational cost. Recent advancements in computer hardware and image processing software have been instrumental in addressing this challenge and facilitated the wide adoption of MAS. Today, MAS has come a long way and the approach includes a wide array of sophisticated algorithms that employ ideas from machine learning, probabilistic modeling, optimization, and computer vision, among other fields. This paper presents a survey of published MAS algorithms and studies that have applied these methods to various biomedical problems. In writing this survey, we have three distinct aims. Our primary goal is to document how MAS was originally conceived, later evolved, and now relates to alternative methods. Second, this paper is intended to be a detailed reference of past research activity in MAS, which now spans over a decade (2003-2014) and entails novel methodological developments and application-specific solutions. Finally, our goal is to also present a perspective on the future of MAS, which, we believe, will be one of the dominant approaches in biomedical image segmentation.

Mesial Temporal Sclerosis: Accuracy of NeuroQuant versus Neuroradiologist

BACKGROUND AND PURPOSE

We sought to compare the accuracy of a volumetric fully automated computer assessment of hippocampal volume asymmetry versus neuroradiologists' interpretations of the temporal lobes for mesial temporal sclerosis. Detecting mesial temporal sclerosis (MTS) is important for the evaluation of patients with temporal lobe epilepsy as it often guides surgical intervention. One feature of MTS is hippocampal volume loss.

MATERIALS AND METHODS

Electronic medical record and researcher reports of scans of patients with proved mesial temporal sclerosis were compared with volumetric assessment with an FDA-approved software package, NeuroQuant, for detection of mesial temporal sclerosis in 63 patients. The degree of volumetric asymmetry was analyzed to determine the neuroradiologists' threshold for detecting right-left asymmetry in temporal lobe volumes.

RESULTS

Thirty-six patients had left-lateralized MTS, 25 had right-lateralized MTS, and 2 had bilateral MTS. The estimated accuracy of the neuroradiologist was 72.6% with a κ statistic of 0.512 (95% CI, 0.315-0.710) [moderate agreement, P < 3 × 10(-6)]), whereas the estimated accuracy of NeuroQuant was 79.4% with a κ statistic of 0.588 (95% CI, 0.388-0.787) [moderate agreement, P < 2 × 10(-6)]). This discrepancy in accuracy was not statistically significant. When at least a 5%-10% volume discrepancy between temporal lobes was present, the neuroradiologists detected it 75%-80% of the time.

CONCLUSIONS

As a stand-alone fully automated software program that can process temporal lobe volume in 5-10 minutes, NeuroQuant compares favorably with trained neuroradiologists in predicting the side of mesial temporal sclerosis. Neuroradiologists can often detect even small temporal lobe volumetric changes visually.

3T MRI quantification of hippocampal volume and signal in mesial temporal lobe epilepsy improves detection of hippocampal sclerosis

BACKGROUND AND PURPOSE

In mesial temporal lobe epilepsy, MR imaging quantification of hippocampal volume and T2 signal can improve the sensitivity for detecting hippocampal sclerosis. However, the current contributions of these analyses for the diagnosis of hippocampal sclerosis in 3T MRI are not clear. Our aim was to compare visual analysis, volumetry, and signal quantification of the hippocampus for detecting hippocampal sclerosis in 3T MRI.

MATERIALS AND METHODS

Two hundred three patients with mesial temporal lobe epilepsy defined by clinical and electroencephalogram criteria had 3T MRI visually analyzed by imaging epilepsy experts. As a second step, we performed automatic quantification of hippocampal volumes with FreeSurfer and T2 relaxometry with an in-house software. MRI of 79 healthy controls was used for comparison.

RESULTS

Visual analysis classified 125 patients (62%) as having signs of hippocampal sclerosis and 78 (38%) as having normal MRI findings. Automatic volumetry detected atrophy in 119 (95%) patients with visually detected hippocampal sclerosis and in 10 (13%) with visually normal MR imaging findings. Relaxometry analysis detected hyperintense T2 signal in 103 (82%) patients with visually detected hippocampal sclerosis and in 15 (19%) with visually normal MR imaging findings. Considered together, volumetry plus relaxometry detected signs of hippocampal sclerosis in all except 1 (99%) patient with visually detected hippocampal sclerosis and in 22 (28%) with visually normal MR imaging findings.

CONCLUSIONS

In 3T MRI visually inspected by experts, quantification of hippocampal volume and signal can increase the detection of hippocampal sclerosis in 28% of patients with mesial temporal lobe epilepsy.

Automated hippocampal segmentation in patients with epilepsy: available free online

PURPOSE

Hippocampal sclerosis, a common cause of refractory focal epilepsy, requires hippocampal volumetry for accurate diagnosis and surgical planning. Manual segmentation is time-consuming and subject to interrater/intrarater variability. Automated algorithms perform poorly in patients with temporal lobe epilepsy. We validate and make freely available online a novel automated method.

METHODS

Manual hippocampal segmentation was performed on 876, 3T MRI scans and 202, 1.5T scans. A template database of 400 high-quality manual segmentations was used to perform automated segmentation of all scans with a multi-atlas-based segmentation propagation method adapted to perform label fusion based on local similarity to ensure accurate segmentation regardless of pathology. Agreement between manual and automated segmentations was assessed by degree of overlap (Dice coefficient) and comparison of hippocampal volumes.

KEY FINDINGS

The automated segmentation algorithm provided robust delineation of the hippocampi on 3T scans with no more variability than that seen between different human raters (Dice coefficients: interrater 0.832, manual vs. automated 0.847). In addition, the algorithm provided excellent results with the 1.5T scans (Dice coefficient 0.827), and automated segmentation remained accurate even in small sclerotic hippocampi. There was a strong correlation between manual and automated hippocampal volumes (Pearson correlation coefficient 0.929 on the left and 0.941 on the right in 3T scans).

SIGNIFICANCE

We demonstrate reliable identification of hippocampal atrophy in patients with hippocampal sclerosis, which is crucial for clinical management of epilepsy, particularly if surgical treatment is being contemplated. We provide a free online Web-based service to enable hippocampal volumetry to be available globally, with consequent greatly improved evaluation of those with epilepsy.

Magnetic resonance volumetry reveals focal brain atrophy in transient epileptic amnesia

Transient epileptic amnesia (TEA) is a recently described epilepsy syndrome characterized by recurrent episodes of isolated memory loss. It is associated with two unusual forms of interictal memory impairment: accelerated long-term forgetting (ALF) and autobiographical amnesia. We investigated the neural basis of TEA using manual volumetry and automated multi-atlas-based segmentation of whole-brain magnetic resonance imaging data from 40 patients with TEA and 20 healthy controls. Both methods confirmed the presence of subtle, bilateral hippocampal atrophy. Additional atrophy was revealed in perirhinal and orbitofrontal cortices. The volumes of these regions correlated with anterograde memory performance. No structural correlates were found for ALF or autobiographical amnesia. The results support the hypothesis that TEA is a focal medial temporal lobe epilepsy syndrome but reveal additional pathology in connected brain regions. The unusual interictal memory deficits of TEA remain unexplained by structural pathology and may reflect physiological disruption of memory networks by subclinical epileptiform activity.

Bayesian Parameter Estimation and Segmentation in the Multi-Atlas Random Orbit Model

This paper examines the multiple atlas random diffeomorphic orbit model in Computational Anatomy (CA) for parameter estimation and segmentation of subcortical and ventricular neuroanatomy in magnetic resonance imagery. We assume that there exist multiple magnetic resonance image (MRI) atlases, each atlas containing a collection of locally-defined charts in the brain generated via manual delineation of the structures of interest. We focus on maximum a posteriori estimation of high dimensional segmentations of MR within the class of generative models representing the observed MRI as a conditionally Gaussian random field, conditioned on the atlas charts and the diffeomorphic change of coordinates of each chart that generates it. The charts and their diffeomorphic correspondences are unknown and viewed as latent or hidden variables. We demonstrate that the expectation-maximization (EM) algorithm arises naturally, yielding the likelihood-fusion equation which the a posteriori estimator of the segmentation labels maximizes. The likelihoods being fused are modeled as conditionally Gaussian random fields with mean fields a function of each atlas chart under its diffeomorphic change of coordinates onto the target. The conditional-mean in the EM algorithm specifies the convex weights with which the chart-specific likelihoods are fused. The multiple atlases with the associated convex weights imply that the posterior distribution is a multi-modal representation of the measured MRI. Segmentation results for subcortical and ventricular structures of subjects, within populations of demented subjects, are demonstrated, including the use of multiple atlases across multiple diseased groups.

A direct morphometric comparison of five labeling protocols for multi-atlas driven automatic segmentation of the hippocampus in Alzheimer's disease

Hippocampal volumetry derived from structural MRI is increasingly used to delineate regions of interest for functional measurements, assess efficacy in therapeutic trials of Alzheimer's disease (AD) and has been endorsed by the new AD diagnostic guidelines as a radiological marker of disease progression. Unfortunately, morphological heterogeneity in AD can prevent accurate demarcation of the hippocampus. Recent developments in automated volumetry commonly use multi-template fusion driven by expert manual labels, enabling highly accurate and reproducible segmentation in disease and healthy subjects. However, there are several protocols to define the hippocampus anatomically in vivo, and the method used to generate atlases may impact automatic accuracy and sensitivity - particularly in pathologically heterogeneous samples. Here we report a fully automated segmentation technique that provides a robust platform to directly evaluate both technical and biomarker performance in AD among anatomically unique labeling protocols. For the first time we test head-to-head the performance of five common hippocampal labeling protocols for multi-atlas based segmentation, using both the Sunnybrook Longitudinal Dementia Study and the entire Alzheimer's Disease Neuroimaging Initiative 1 (ADNI-1) baseline and 24-month dataset. We based these atlas libraries on the protocols of (Haller et al., 1997; Killiany et al., 1993; Malykhin et al., 2007; Pantel et al., 2000; Pruessner et al., 2000), and a single operator performed all manual tracings to generate de facto "ground truth" labels. All methods distinguished between normal elders, mild cognitive impairment (MCI), and AD in the expected directions, and showed comparable correlations with measures of episodic memory performance. Only more inclusive protocols distinguished between stable MCI and MCI-to-AD converters, and had slightly better associations with episodic memory. Moreover, we demonstrate that protocols including more posterior anatomy and dorsal white matter compartments furnish the best voxel-overlap accuracies (Dice Similarity Coefficient=0.87-0.89), compared to expert manual tracings, and achieve the smallest sample sizes required to power clinical trials in MCI and AD. The greatest distribution of errors was localized to the caudal hippocampus and the alveus-fimbria compartment when these regions were excluded. The definition of the medial body did not significantly alter accuracy among more comprehensive protocols. Voxel-overlap accuracies between automatic and manual labels were lower for the more pathologically heterogeneous Sunnybrook study in comparison to the ADNI-1 sample. Finally, accuracy among protocols appears to significantly differ the most in AD subjects compared to MCI and normal elders. Together, these results suggest that selection of a candidate protocol for fully automatic multi-template based segmentation in AD can influence both segmentation accuracy when compared to expert manual labels and performance as a biomarker in MCI and AD.

Temporal lobe epilepsy: quantitative MR volumetry in detection of hippocampal atrophy

PURPOSE

To determine the ability of fully automated volumetric magnetic resonance (MR) imaging to depict hippocampal atrophy (HA) and to help correctly lateralize the seizure focus in patients with temporal lobe epilepsy (TLE).

MATERIALS AND METHODS

This study was conducted with institutional review board approval and in compliance with HIPAA regulations. Volumetric MR imaging data were analyzed for 34 patients with TLE and 116 control subjects. Structural volumes were calculated by using U.S. Food and Drug Administration-cleared software for automated quantitative MR imaging analysis (NeuroQuant). Results of quantitative MR imaging were compared with visual detection of atrophy, and, when available, with histologic specimens. Receiver operating characteristic analyses were performed to determine the optimal sensitivity and specificity of quantitative MR imaging for detecting HA and asymmetry. A linear classifier with cross validation was used to estimate the ability of quantitative MR imaging to help lateralize the seizure focus.

RESULTS

Quantitative MR imaging-derived hippocampal asymmetries discriminated patients with TLE from control subjects with high sensitivity (86.7%-89.5%) and specificity (92.2%-94.1%). When a linear classifier was used to discriminate left versus right TLE, hippocampal asymmetry achieved 94% classification accuracy. Volumetric asymmetries of other subcortical structures did not improve classification. Compared with invasive video electroencephalographic recordings, lateralization accuracy was 88% with quantitative MR imaging and 85% with visual inspection of volumetric MR imaging studies but only 76% with visual inspection of clinical MR imaging studies.

CONCLUSION

Quantitative MR imaging can depict the presence and laterality of HA in TLE with accuracy rates that may exceed those achieved with visual inspection of clinical MR imaging studies. Thus, quantitative MR imaging may enhance standard visual analysis, providing a useful and viable means for translating volumetric analysis into clinical practice.

The effects of FreeSurfer version, workstation type, and Macintosh operating system version on anatomical volume and cortical thickness measurements

FreeSurfer is a popular software package to measure cortical thickness and volume of neuroanatomical structures. However, little if any is known about measurement reliability across various data processing conditions. Using a set of 30 anatomical T1-weighted 3T MRI scans, we investigated the effects of data processing variables such as FreeSurfer version (v4.3.1, v4.5.0, and v5.0.0), workstation (Macintosh and Hewlett-Packard), and Macintosh operating system version (OSX 10.5 and OSX 10.6). Significant differences were revealed between FreeSurfer version v5.0.0 and the two earlier versions. These differences were on average 8.8 ± 6.6% (range 1.3-64.0%) (volume) and 2.8 ± 1.3% (1.1-7.7%) (cortical thickness). About a factor two smaller differences were detected between Macintosh and Hewlett-Packard workstations and between OSX 10.5 and OSX 10.6. The observed differences are similar in magnitude as effect sizes reported in accuracy evaluations and neurodegenerative studies.The main conclusion is that in the context of an ongoing study, users are discouraged to update to a new major release of either FreeSurfer or operating system or to switch to a different type of workstation without repeating the analysis; results thus give a quantitative support to successive recommendations stated by FreeSurfer developers over the years. Moreover, in view of the large and significant cross-version differences, it is concluded that formal assessment of the accuracy of FreeSurfer is desirable.

Classification and lateralization of temporal lobe epilepsies with and without hippocampal atrophy based on whole-brain automatic MRI segmentation

Brain images contain information suitable for automatically sorting subjects into categories such as healthy controls and patients. We sought to identify morphometric criteria for distinguishing controls (n = 28) from patients with unilateral temporal lobe epilepsy (TLE), 60 with and 20 without hippocampal atrophy (TLE-HA and TLE-N, respectively), and for determining the presumed side of seizure onset. The framework employs multi-atlas segmentation to estimate the volumes of 83 brain structures. A kernel-based separability criterion was then used to identify structures whose volumes discriminate between the groups. Next, we applied support vector machines (SVM) to the selected set for classification on the basis of volumes. We also computed pairwise similarities between all subjects and used spectral analysis to convert these into per-subject features. SVM was again applied to these feature data. After training on a subgroup, all TLE-HA patients were correctly distinguished from controls, achieving an accuracy of 96 ± 2% in both classification schemes. For TLE-N patients, the accuracy was 86 ± 2% based on structural volumes and 91 ± 3% using spectral analysis. Structures discriminating between patients and controls were mainly localized ipsilaterally to the presumed seizure focus. For the TLE-HA group, they were mainly in the temporal lobe; for the TLE-N group they included orbitofrontal regions, as well as the ipsilateral substantia nigra. Correct lateralization of the presumed seizure onset zone was achieved using hippocampi and parahippocampal gyri in all TLE-HA patients using either classification scheme; in the TLE-N patients, lateralization was accurate based on structural volumes in 86 ± 4%, and in 94 ± 4% with the spectral analysis approach. Unilateral TLE has imaging features that can be identified automatically, even when they are invisible to human experts. Such morphometric image features may serve as classification and lateralization criteria. The technique also detects unsuspected distinguishing features like the substantia nigra, warranting further study.

Hippocampal atrophy in temporal lobe epilepsy: the 'generator' and 'receiver'

OBJECTIVE

Some patients with unilateral medial temporal lobe epilepsy (MTLE) display bilateral hippocampal atrophy on MRI, even though seizures originate in only one hippocampus. The correct identification of the epileptogenic hippocampus (the 'generator') vs the non-epileptogenic (the 'receiver') may lead to better surgical planning and results.

MATERIALS AND METHODS

We studied 14 patients with MTLE (eight left and six right) who became seizure free after unilateral hippocampal resection, with hippocampal sclerosis confirmed by histology. Hippocampal tridimensional morphometry was performed comparing patients and healthy controls employing a voxel-wise Wilcoxon test. Results were corrected for multiple comparisons with the application of a False Discovery Rate (FDR)-corrected threshold for q < 0.05.

RESULTS

Patients with MTLE showed atrophy involving the ipsilateral hippocampus and the contralateral hippocampus, more pronouncedly within the ipsilateral hippocampus in the anterior-inferior aspect of the hippocampal head (left MTLE, left hippocampus x = -28, y = -16, z = -24, Z = 3.6; right MTLE, right hippocampus x = 22, y = -11, z = -27, Z = 2.9). On the contralateral hippocampus, the atrophy was more noticeable in the posterior head and body areas.

CONCLUSION

The epileptogenic hippocampal atrophy has an anatomically distinct pattern compared with the contralateral hippocampus. This information may help guide the presurgical assessment of MTLE.

Automatic hippocampal segmentation in temporal lobe epilepsy: impact of developmental abnormalities

In drug-resistant temporal lobe epilepsy (TLE), detecting hippocampal atrophy on MRI is important as it allows defining the surgical target. The performance of automatic segmentation in TLE has so far been considered unsatisfactory. In addition to atrophy, about 40% of patients present with developmental abnormalities (referred to as malrotation) characterized by atypical morphologies of the hippocampus and collateral sulcus. Our purpose was to evaluate the impact of malrotation and atrophy on the performance of three state-of-the-art automated algorithms. We segmented the hippocampus in 66 patients and 35 sex- and age-matched healthy subjects using a region-growing algorithm constrained by anatomical priors (SACHA), a freely available atlas-based software (FreeSurfer) and a multi-atlas approach (ANIMAL-multi). To quantify malrotation, we generated 3D models from manual hippocampal labels and automatically extracted collateral sulci. The accuracy of automated techniques was evaluated relative to manual labeling using the Dice similarity index and surface-based shape mapping, for which we computed vertex-wise displacement vectors between automated and manual segmentations. We then correlated segmentation accuracy with malrotation features and atrophy. ANIMAL-multi demonstrated similar accuracy in patients and healthy controls (p > 0.1), whereas SACHA and FreeSurfer were less accurate in patients (p < 0.05). Surface-based analysis of contour accuracy revealed that SACHA over-estimated the lateral border of malrotated hippocampi (r = 0.61; p < 0.0001), but performed well in the presence of atrophy (|r |< 0.34; p > 0.2). Conversely, FreeSurfer and ANIMAL-multi were affected by both malrotation (FreeSurfer: r = 0.57; p = 0.02, ANIMAL-multi: r = 0.50; p = 0.05) and atrophy (FreeSurfer: r = 0.78, p < 0.0001, ANIMAL-multi: r = 0.61; p < 0.0001). Compared to manual volumetry, automated procedures underestimated the magnitude of atrophy (Cohen's d: manual: 1.68; ANIMAL-multi: 1.11; SACHA: 1.10; FreeSurfer: 0.90, p < 0.0001). In addition, they tended to lateralize the seizure focus less accurately in the presence of malrotation (manual: 64%; ANIMAL-multi: 55%, p = 0.4; SACHA: 50%, p = 0.1; FreeSurfer: 41%, p = 0.05). Hippocampal developmental anomalies and atrophy had a negative impact on the segmentation performance of three state-of-the-art automated methods. These shape variants should be taken into account when designing segmentation algorithms.

Hippocampal sclerosis in temporal lobe epilepsy: findings at 7 T¹

PURPOSE

To determine if ultrahigh-field-strength magnetic resonance (MR) imaging can be used to detect subregional hippocampal alterations.

MATERIALS AND METHODS

Subjects provided written consent to participate in this prospective institutional review board-approved HIPAA-compliant study. T1- and T2-weighted 7-T brain MR images were acquired in 11 healthy subjects and eight patients with temporal lobe epilepsy (TLE). In all subjects, images were qualitatively examined for evidence of hippocampal atrophy, signal change, and malrotation with the Bernasconi definition, and digitations of the hippocampal heads were counted (agreement was measured with the κ statistic). Data were analyzed quantitatively with manual subregional hippocampal body segmentation. Subregional data in individual subjects with TLE were compared with data in control subjects to detect deviation from the control range for volume measures on each side and with asymmetry indexes.

RESULTS

All eight patients with TLE had hippocampal abnormalities on the epileptogenic side. Subregional analysis revealed selective lateral Ammon horn atrophy in six patients and diffuse Ammon horn and dentate gyrus atrophy in one patient. Paucity of hippocampal digitations occurred on the epileptogenic side in all patients with TLE and also on the contralateral side in three patients (interrater κ value, 0.80). Hippocampal malrotation was observed in three patients with TLE and four control subjects.

CONCLUSION

Ultrahigh-field-strength MR imaging permitted detection of selectively greater Ammon horn atrophy in patients with TLE and hippocampal sclerosis. Paucity of digitations is a deformity of the hippocampal head that was detected independent of hippocampal atrophy in patients with mesial TLE.

Automatic morphometry in Alzheimer's disease and mild cognitive impairment

This paper presents a novel, publicly available repository of anatomically segmented brain images of healthy subjects as well as patients with mild cognitive impairment and Alzheimer's disease. The underlying magnetic resonance images have been obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. T1-weighted screening and baseline images (1.5T and 3T) have been processed with the multi-atlas based MAPER procedure, resulting in labels for 83 regions covering the whole brain in 816 subjects. Selected segmentations were subjected to visual assessment. The segmentations are self-consistent, as evidenced by strong agreement between segmentations of paired images acquired at different field strengths (Jaccard coefficient: 0.802±0.0146). Morphometric comparisons between diagnostic groups (normal; stable mild cognitive impairment; mild cognitive impairment with progression to Alzheimer's disease; Alzheimer's disease) showed highly significant group differences for individual regions, the majority of which were located in the temporal lobe. Additionally, significant effects were seen in the parietal lobe. Increased left/right asymmetry was found in posterior cortical regions. An automatically derived white-matter hypointensities index was found to be a suitable means of quantifying white-matter disease. This repository of segmentations is a potentially valuable resource to researchers working with ADNI data.

A learning-based wrapper method to correct systematic errors in automatic image segmentation: consistently improved performance in hippocampus, cortex and brain segmentation

We propose a simple but generally applicable approach to improving the accuracy of automatic image segmentation algorithms relative to manual segmentations. The approach is based on the hypothesis that a large fraction of the errors produced by automatic segmentation are systematic, i.e., occur consistently from subject to subject, and serves as a wrapper method around a given host segmentation method. The wrapper method attempts to learn the intensity, spatial and contextual patterns associated with systematic segmentation errors produced by the host method on training data for which manual segmentations are available. The method then attempts to correct such errors in segmentations produced by the host method on new images. One practical use of the proposed wrapper method is to adapt existing segmentation tools, without explicit modification, to imaging data and segmentation protocols that are different from those on which the tools were trained and tuned. An open-source implementation of the proposed wrapper method is provided, and can be applied to a wide range of image segmentation problems. The wrapper method is evaluated with four host brain MRI segmentation methods: hippocampus segmentation using FreeSurfer (Fischl et al., 2002); hippocampus segmentation using multi-atlas label fusion (Artaechevarria et al., 2009); brain extraction using BET (Smith, 2002); and brain tissue segmentation using FAST (Zhang et al., 2001). The wrapper method generates 72%, 14%, 29% and 21% fewer erroneously segmented voxels than the respective host segmentation methods. In the hippocampus segmentation experiment with multi-atlas label fusion as the host method, the average Dice overlap between reference segmentations and segmentations produced by the wrapper method is 0.908 for normal controls and 0.893 for patients with mild cognitive impairment. Average Dice overlaps of 0.964, 0.905 and 0.951 are obtained for brain extraction, white matter segmentation and gray matter segmentation, respectively.

Nonlocal patch-based label fusion for hippocampus segmentation

Quantitative magnetic resonance analysis often requires accurate, robust and reliable automatic extraction of anatomical structures. Recently, template-warping methods incorporating a label fusion strategy have demonstrated high accuracy in segmenting cerebral structures. In this study, we propose a novel patch-based method using expert segmentation priors to achieve this task. Inspired by recent work in image denoising, the proposed nonlocal patch-based label fusion produces accurate and robust segmentation. During our experiments, the hippocampi of 80 healthy subjects were segmented. The influence on segmentation accuracy of different parameters such as patch size or number of training subjects was also studied. Moreover, a comparison with an appearance-based method and a template-based method was carried out. The highest median kappa value obtained with the proposed method was 0.884, which is competitive compared with recently published methods.

Patch-based segmentation using expert priors: application to hippocampus and ventricle segmentation

Quantitative magnetic resonance analysis often requires accurate, robust, and reliable automatic extraction of anatomical structures. Recently, template-warping methods incorporating a label fusion strategy have demonstrated high accuracy in segmenting cerebral structures. In this study, we propose a novel patch-based method using expert manual segmentations as priors to achieve this task. Inspired by recent work in image denoising, the proposed nonlocal patch-based label fusion produces accurate and robust segmentation. Validation with two different datasets is presented. In our experiments, the hippocampi of 80 healthy subjects and the lateral ventricles of 80 patients with Alzheimer's disease were segmented. The influence on segmentation accuracy of different parameters such as patch size and number of training subjects was also studied. A comparison with an appearance-based method and a template-based method was also carried out. The highest median kappa index values obtained with the proposed method were 0.884 for hippocampus segmentation and 0.959 for lateral ventricle segmentation.

Update on neuroimaging in epilepsy

Neuroimaging in epilepsy is a very large and growing field. Researchers in this area have quickly adopted new methods, resulting in a lively literature. Basic features of common epilepsies are well known, but, outside of the specific area of epilepsy surgery evaluation, new methods evolving in the last few years have had limited new beneficial clinical impact. Here, an overview of the epilepsy neuroimaging literature of the last 5 years, with an emphasis on mesial temporal lobe epilepsy, idiopathic generalized epilepsies, presurgical evaluation and new developments in functional MRI is presented. The need for attention to clinical translation, as well as immediate opportunities and future trends in this field, are discussed.

Towards accurate, automatic segmentation of the hippocampus and amygdala from MRI by augmenting ANIMAL with a template library and label fusion

We describe progress towards fully automatic segmentation of the hippocampus (HC) and amygdala (AG) in human subjects from MRI data. Three methods are described and tested with a set of MRIs from 80 young normal controls, using manual labeling of the HC and AG as a gold standard. The methods include: 1) our ANIMAL atlas-based method that uses non-linear registration to a pre-labeled non-linear average template (ICBM152). HC and AG labels, defined on the template are mapped through the inverse transformation to segment these structures on the subject's MRI. 2) We select the most similar MRI from the set of 80 labeled datasets to use as a template in the standard ANIMAL segmentation scheme. 3) We use label fusion techniques to combine segmentations from the 'n' most similar templates. The label fusion technique yields an optimal median Dice Kappa of 0.886 and similarity of 0.795 for HC, and 0.826 and 0.703 respectively for AG.

A time-saving and facilitating approach for segmentation of anatomically defined cortical regions: MRI volumetry

In this study, we present an accurate, reliable, robust, and time-efficient technique for a semi-automatic segmentation of neuroanatomically defined cortical structures in Magnetic Resonance Imaging (MRI) scans. It involves manual drawing of the border of a region of interest (ROI), supported by three-dimensional (3D) visualization techniques (rendering), and a subsequent automatic tracing of the gray matter voxels inside the ROI by means of an automatic tissue classifier. The approach has been evaluated on a set of MRI scans of 75 participants selected from the Maastricht Aging Study (MAAS) and applied to cortical brain structures for both the left and right hemispheres, viz., the inferior prefrontal cortex (PFC); the orbital PFC; the dorsolateral PFC; the anterior cingulate cortex; and the posterior cingulate cortex. The use of a 3D surface-rendered brain can be rotated in any direction was invaluable in identifying anatomical landmarks on the basis of gyral and sulcal topography. This resulted in a high accuracy (anatomical correctness) and reliability: the intra-rater intra-class correlation coefficient (ICC) was between 0.96 and 0.99. Furthermore, the obtained time savings were substantial, i.e., up to a factor of 7.5 compared with fully manual segmentations.

Hippocampal volumetry for lateralization of temporal lobe epilepsy: automated versus manual methods

The hippocampus has been the primary region of interest in the preoperative imaging investigations of mesial temporal lobe epilepsy (mTLE). Hippocampal imaging and electroencephalographic features may be sufficient in several cases to declare the epileptogenic focus. In particular, hippocampal atrophy, as appreciated on T1-weighted (T1W) magnetic resonance (MR) images, may suggest a mesial temporal sclerosis. Qualitative visual assessment of hippocampal volume, however, is influenced by head position in the magnet and the amount of atrophy in different parts of the hippocampus. An entropy-based segmentation algorithm for subcortical brain structures (LocalInfo) was developed and supplemented by both a new multiple atlas strategy and a free-form deformation step to capture structural variability. Manually segmented T1-weighted magnetic resonance (MR) images of 10 non-epileptic subjects were used as atlases for the proposed automatic segmentation protocol which was applied to a cohort of 46 mTLE patients. The segmentation and lateralization accuracies of the proposed technique were compared with those of two other available programs, HAMMER and FreeSurfer, in addition to the manual method. The Dice coefficient for the proposed method was 11% (p<10(-5)) and 14% (p<10(-4)) higher in comparison with the HAMMER and FreeSurfer, respectively. Mean and Hausdorff distances in the proposed method were also 14% (p<0.2) and 26% (p<10(-3)) lower in comparison with HAMMER and 8% (p<0.8) and 48% (p<10(-5)) lower in comparison with FreeSurfer, respectively. LocalInfo proved to have higher concordance (87%) with the manual segmentation method than either HAMMER (85%) or FreeSurfer (83%). The accuracy of lateralization by volumetry in this study with LocalInfo was 74% compared to 78% with the manual segmentation method. LocalInfo yields a closer approximation to that of manual segmentation and may therefore prove to be more reliable than currently published automatic segmentation algorithms.

Automated cross-sectional and longitudinal hippocampal volume measurement in mild cognitive impairment and Alzheimer's disease

Volume and change in volume of the hippocampus are both important markers of Alzheimer's disease (AD). Delineation of the structure on MRI is time-consuming and therefore reliable automated methods are required. We describe an improvement (multiple-atlas propagation and segmentation (MAPS)) to our template library-based segmentation technique. The improved technique uses non-linear registration of the best-matched templates from our manually segmented library to generate multiple segmentations and combines them using the simultaneous truth and performance level estimation (STAPLE) algorithm. Change in volume over 12months (MAPS-HBSI) was measured by applying the boundary shift integral using MAPS regions. Methods were developed and validated against manual measures using subsets from Alzheimer's Disease Neuroimaging Initiative (ADNI). The best method was applied to 682 ADNI subjects, at baseline and 12-month follow-up, enabling assessment of volumes and atrophy rates in control, mild cognitive impairment (MCI) and AD groups, and within MCI subgroups classified by subsequent clinical outcome. We compared our measures with those generated by Surgical Navigation Technologies (SNT) available from ADNI. The accuracy of our volumes was one of the highest reported (mean(SD) Jaccard Index 0.80(0.04) (N=30)). Both MAPS baseline volume and MAPS-HBSI atrophy rate distinguished between control, MCI and AD groups. Comparing MCI subgroups (reverters, stable and converters): volumes were lower and rates higher in converters compared with stable and reverter groups (p< or =0.03). MAPS-HBSI required the lowest sample sizes (78 subjects) for a hypothetical trial. In conclusion, the MAPS and MAPS-HBSI methods give accurate and reliable volumes and atrophy rates across the clinical spectrum from healthy aging to AD.