Fabian Wenzel

Differences in Regional Brain Volumes Two Months and One Year after Mild Traumatic Brain Injury

Conventional structural imaging is often normal after mild traumatic brain injury (mTBI). There is a need for structural neuroimaging biomarkers that facilitate detection of milder injuries, allow recovery trajectory monitoring, and identify those at risk for poor functional outcome and disability. We present a novel approach to quantifying volumes of candidate brain regions at risk for injury. Compared to controls, patients with mTBI had significantly smaller volumes in several regions including the caudate, putamen, and thalamus when assessed 2 months after injury. These differences persisted but were reduced in magnitude 1 year after injury, suggesting the possibility of normalization over time in the affected regions. More pronounced differences, however, were found in the amygdala and hippocampus, suggesting the possibility of regionally specific responses to injury.

Construction and comparative evaluation of different activity detection methods in brain FDG‑PET

AimWe constructed and evaluated reference brain FDG-PET databases for usage by three software programs (Computer-aided diagnosis for dementia (CAD4D), Statistical Parametric Mapping (SPM) and NEUROSTAT), which allow a user-independent detection of dementia-related hypometabolism in patients’ brain FDG-PET.MethodsThirty-seven healthy volunteers were scanned in order to construct brain FDG reference databases, which reflect the normal, age-dependent glucose consumption in human brain, using either software. Databases were compared to each other to assess the impact of different stereotactic normalization algorithms used by either software package. In addition, performance of the new reference databases in the detection of altered glucose consumption in the brains of patients was evaluated by calculating statistical maps of regional hypometabolism in FDG-PET of 20 patients with confirmed Alzheimer’s dementia (AD) and of 10 non-AD patients. Extent (hypometabolic volume referred to as cluster size) and magnitude (peak z-score) of detected hypometabolism was statistically analyzed.ResultsDifferences between the reference databases built by CAD4D, SPM or NEUROSTAT were observed. Due to the different normalization methods, altered spatial FDG patterns were found. When analyzing patient data with the reference databases created using CAD4D, SPM or NEUROSTAT, similar characteristic clusters of hypometabolism in the same brain regions were found in the AD group with either software. However, larger z-scores were observed with CAD4D and NEUROSTAT than those reported by SPM. Better concordance with CAD4D and NEUROSTAT was achieved using the spatially normalized images of SPM and an independent z-score calculation. The three software packages identified the peak z-scores in the same brain region in 11 of 20 AD cases, and there was concordance between CAD4D and SPM in 16 AD subjects.ConclusionThe clinical evaluation of brain FDG-PET of 20 AD patients with either CAD4D-, SPM- or NEUROSTAT-generated databases from an identical reference dataset showed similar patterns of hypometabolism in the brain regions known to be involved in AD. The extent of hypometabolism and peak z-score appeared to be influenced by the calculation method used in each software package rather than by different spatial normalization parameters.

Optimal feature selection for automated classification of FDG-PET in patients with suspected dementia

FDG-PET is increasingly used for the evaluation of dementia patients, as major neurodegenerative disorders, such as Alzheimers disease (AD), Lewy body dementia (LBD), and Frontotemporal dementia (FTD), have been shown to induce specific patterns of regional hypo-metabolism. However, the interpretation of FDG-PET images of patients with suspected dementia is not straightforward, since patients are imaged at different stages of progression of neurodegenerative disease, and the indications of reduced metabolism due to neurodegenerative disease appear slowly over time. Furthermore, different diseases can cause rather similar patterns of hypo-metabolism. Therefore, classification of FDG-PET images of patients with suspected dementia may lead to misdiagnosis. This work aims to find an optimal subset of features for automated classification, in order to improve classification accuracy of FDG-PET images in patients with suspected dementia. A novel feature selection method is proposed, and performance is compared to existing methods. The proposed approach adopts a combination of balanced class distributions and feature selection methods. This is demonstrated to provide high classification accuracy for classification of FDG-PET brain images of normal controls and dementia patients, comparable with alternative approaches, and provides a compact set of features selected.

Rapid fully automatic segmentation of subcortical brain structures by shape-constrained surface adaptation

HIGHLIGHTSRapid segmentation of clinically relevant sub‐cortical brain structures is proposed.Proposed approach does not require pre‐processing, such as bias‐field correction, and requires about 30 s per scan.Extensive evaluation demonstrates superior performance (accuracy, reproducibility) of the proposed approach over FSL FIRST or FreeSurfer.Segmentation results of hippocampus highly coincide with ADNI‐EANM ground truth. ABSTRACT This work presents a novel approach for the rapid segmentation of clinically relevant subcortical brain structures in T1‐weighted MRI by utilizing a shape‐constrained deformable surface model. In contrast to other approaches for segmenting brain structures, its design allows for parallel segmentation of individual brain structures within a flexible and robust hierarchical framework such that accurate adaptation and volume computation can be achieved within a minute of processing time. Furthermore, adaptation is driven by local and not global contrast, potentially relaxing requirements with respect to preprocessing steps such as bias‐field correction. Detailed evaluation experiments on more than 1000 subjects, including comparisons to FSL FIRST and FreeSurfer as well as a clinical assessment, demonstrate high accuracy and test‐retest consistency of the presented segmentation approach, leading, for example, to an average segmentation error of less than 0.5 mm. The presented approach might be useful in both, research as well as clinical routine, for automated segmentation and volume quantification of subcortical brain structures in order to increase confidence in the diagnosis of neuro‐degenerative disorders, such as Alzheimers disease, Parkinsons disease, Multiple Sclerosis, or clinical applications for other neurologic and psychiatric diseases.

Combination of predictors to classify cognitive decline in individual subjects with mild cognitive impairment

Background: The combination of biomarkers and risk factors has been shown to improve the prediction of cognitive decline in mild cognitive impairment (MCI) (Devanand et al, 2008). Most studies have relied on logistic regression (LR) to combine predictors. However, multivariate LR has known shortcomings if predictors are correlated and if sample sizes are small. The objective of this study was to investigate partial least squares (PLS) regression as an alternative to LR for combining predictors of cognitive decline in individual subjects with MCI. Methods: 140 MCI subjects with MMSE 25, FDG PET at baseline and 24 months follow-up were included from the Alzheimer’s Disease Neuroimaging Initiative ADNI (age 1⁄4 75 6 7y, MMSE 1⁄4 27.5 6 1.4). Subjects were divided into two categories: Cognitively ‘stable’ (MMSE 25 after 24 months, n 1⁄4 99), and ‘progressive’ (MMSE<25 at follow-up, n 1⁄4 41). The following measures at baseline were considered as predictors a priori: 4 FDG PET regional values, MMSE, ADAS-cog, APOE4 status, age, gender, and education. Observerindependent classifications of ‘stable’ vs ‘progressive’ were obtained using LR and PLS for various combinations of predictors. Leave-one-out cross validation was performed to obtain unbiased measures of accuracies. Results: For single predictors, PLS classification of stable vs progressive MCI yielded an area under the ROC curve (AUC) between 0.55(frontal region FDG) and 0.80(ADAS-cog). AUC of LR was on average 0.04 (7%) lower. Age, gender, and APOE4 were not included in these results as they were not predictive individually (AUC<0.5). For all 13 tested combinations of predictors, AUC of LR was lower than that of PLS, on average 0.02 (3%). Combining all 10 predictors gave AUC of 0.84 for PLS and 0.82 for LR, with maximum classification accuracies of 84% and 81%, respectively. For this combination, LR found MMSE, ADAS-cog, and posterior cingulate hypometabolism most significant (p < 0.05). MMSE, ADAS-cog, and parietal hypometabolism were most discriminative with PLS. Conclusions: Combination of several predictors improves individual classification of stable vs progressive MCI. PLS consistently showed slightly better discrimination than logistic regression. Next to MMSE and ADAS-cog, hypometabolism in brain regions known to be affected by Alzheimer’s Disease were most predictive of cognitive decline.

Design of a synthetic database for the validation of non-linear registration and segmentation of magnetic resonance brain images

Image registration and segmentation are two important tasks in medical image analysis. However, the validation of algorithms for non-linear registration in particular often poses significant challenges:1, 2 Anatomical labeling based on scans for the validation of segmentation algorithms is often not available, and is tedious to obtain. One possibility to obtain suitable ground truth is to use anatomically labelled atlas images. Such atlas images are, however, generally limited to single subjects, and the displacement field of the registration between the template and an arbitrary data set is unknown. Therefore, the precise registration error cannot be determined, and approximations of a performance measure like the consistency error must be adapted. Thus, validation requires that some form of ground truth is available. In this work, an approach to generate a synthetic ground truth database for the validation of image registration and segmentation is proposed. Its application is illustrated using the example of the validation of a registration procedure, using 50 magnetic resonance images from different patients and two atlases. Three different non-linear image registration methods were tested to obtain a synthetic validation database consisting of 50 anatomically labelled brain scans.