Rebecca M. E. Steketee

Standardized evaluation of algorithms for computer-aided diagnosis of dementia based on structural MRI: The CADDementia challenge

Algorithms for computer-aided diagnosis of dementia based on structural MRI have demonstrated high performance in the literature, but are difficult to compare as different data sets and methodology were used for evaluation. In addition, it is unclear how the algorithms would perform on previously unseen data, and thus, how they would perform in clinical practice when there is no real opportunity to adapt the algorithm to the data at hand. To address these comparability, generalizability and clinical applicability issues, we organized a grand challenge that aimed to objectively compare algorithms based on a clinically representative multi-center data set. Using clinical practice as the starting point, the goal was to reproduce the clinical diagnosis. Therefore, we evaluated algorithms for multi-class classification of three diagnostic groups: patients with probable Alzheimers disease, patients with mild cognitive impairment and healthy controls. The diagnosis based on clinical criteria was used as reference standard, as it was the best available reference despite its known limitations. For evaluation, a previously unseen test set was used consisting of 354 T1-weighted MRI scans with the diagnoses blinded. Fifteen research teams participated with a total of 29 algorithms. The algorithms were trained on a small training set (n=30) and optionally on data from other sources (e.g., the Alzheimers Disease Neuroimaging Initiative, the Australian Imaging Biomarkers and Lifestyle flagship study of aging). The best performing algorithm yielded an accuracy of 63.0% and an area under the receiver-operating-characteristic curve (AUC) of 78.8%. In general, the best performances were achieved using feature extraction based on voxel-based morphometry or a combination of features that included volume, cortical thickness, shape and intensity. The challenge is open for new submissions via the web-based framework: http://caddementia.grand-challenge.org.

Diagnostic classification of arterial spin labeling and structural MRI in presenile early stage dementia

Because hypoperfusion of brain tissue precedes atrophy in dementia, the detection of dementia may be advanced by the use of perfusion information. Such information can be obtained noninvasively with arterial spin labeling (ASL), a relatively new MR technique quantifying cerebral blood flow (CBF). Using ASL and structural MRI, we evaluated diagnostic classification in 32 prospectively included presenile early stage dementia patients and 32 healthy controls. Patients were suspected of Alzheimers disease (AD) or frontotemporal dementia. Classification was based on CBF as perfusion marker, gray matter (GM) volume as atrophy marker, and their combination. These markers were each examined using six feature extraction methods: a voxel‐wise method and a region of interest (ROI)‐wise approach using five ROI‐sets in the GM. These ROI‐sets ranged in number from 72 brain regions to a single ROI for the entire supratentorial brain. Classification was performed with a linear support vector machine classifier. For validation of the classification method on the basis of GM features, a reference dataset from the AD Neuroimaging Initiative database was used consisting of AD patients and healthy controls. In our early stage dementia population, the voxelwise feature‐extraction approach achieved more accurate results (area under the curve (AUC) range = 86 − 91%) than all other approaches (AUC = 57 − 84%). Used in isolation, CBF quantified with ASL was a good diagnostic marker for dementia. However, our findings indicated only little added diagnostic value when combining ASL with the structural MRI data (AUC = 91%), which did not significantly improve over accuracy of structural MRI atrophy marker by itself. Hum Brain Mapp 35:4916–4931, 2014.

Inter-Vendor Reproducibility of Pseudo-Continuous Arterial Spin Labeling at 3 Tesla

Purpose Prior to the implementation of arterial spin labeling (ASL) in clinical multi-center studies, it is important to establish its status quo inter-vendor reproducibility. This study evaluates and compares the intra- and inter-vendor reproducibility of pseudo-continuous ASL (pCASL) as clinically implemented by GE and Philips. Material and Methods 22 healthy volunteers were scanned twice on both a 3T GE and a 3T Philips scanner. The main difference in implementation between the vendors was the readout module: spiral 3D fast spin echo vs. 2D gradient-echo echo-planar imaging respectively. Mean and variation of cerebral blood flow (CBF) were compared for the total gray matter (GM) and white matter (WM), and on a voxel-level. Results Whereas the mean GM CBF of both vendors was almost equal (p = 1.0), the mean WM CBF was significantly different (p<0.01). The inter-vendor GM variation did not differ from the intra-vendor GM variation (p = 0.3 and p = 0.5 for GE and Philips respectively). Spatial inter-vendor CBF and variation differences were observed in several GM regions and in the WM. Conclusion These results show that total GM CBF-values can be exchanged between vendors. For the inter-vendor comparison of GM regions or WM, these results encourage further standardization of ASL implementation among vendors.

Multiparametric computer-aided differential diagnosis of Alzheimer’s disease and frontotemporal dementia using structural and advanced MRI

ObjectivesTo investigate the added diagnostic value of arterial spin labelling (ASL) and diffusion tensor imaging (DTI) to structural MRI for computer-aided classification of Alzheimers disease (AD), frontotemporal dementia (FTD), and controls.MethodsThis retrospective study used MRI data from 24 early-onset AD and 33 early-onset FTD patients and 34 controls (CN). Classification was based on voxel-wise feature maps derived from structural MRI, ASL, and DTI. Support vector machines (SVMs) were trained to classify AD versus CN (AD-CN), FTD-CN, AD-FTD, and AD-FTD-CN (multi-class). Classification performance was assessed by the area under the receiver-operating-characteristic curve (AUC) and accuracy. Using SVM significance maps, we analysed contributions of brain regions.ResultsCombining ASL and DTI with structural MRI resulted in higher classification performance for differential diagnosis of AD and FTD (AUC = 84%; p = 0.05) than using structural MRI by itself (AUC = 72%). The performance of ASL and DTI themselves did not improve over structural MRI. The classifications were driven by different brain regions for ASL and DTI than for structural MRI, suggesting complementary information.ConclusionsASL and DTI are promising additions to structural MRI for classification of early-onset AD, early-onset FTD, and controls, and may improve the computer-aided differential diagnosis on a single-subject level.Key points• Multiparametric MRI is promising for computer-aided diagnosis of early-onset AD and FTD.• Diagnosis is driven by different brain regions when using different MRI methods.• Combining structural MRI, ASL, and DTI may improve differential diagnosis of dementia.

Concurrent white and gray matter degeneration of disease-specific networks in early-stage Alzheimer's disease and behavioral variant frontotemporal dementia

This study investigates regional coherence between white matter (WM) microstructure and gray matter (GM) volume and perfusion measures in Alzheimers disease (AD) and behavioral variant frontotemporal dementia (bvFTD) using a correlational approach. WM-GM coherence, compared with controls, was stronger between cingulum WM and frontotemporal GM in AD, and temporoparietal GM in bvFTD. In addition, in AD compared with controls, coherence was stronger between inferior fronto-occipital fasciculus WM microstructure and occipital GM perfusion. In this first study assessing regional WM-GM coherence in AD and bvFTD, we show that WM microstructure and GM volume and perfusion measures are coherent, particularly in regions implicated in AD and bvFTD pathology. This indicates concurrent degeneration in disease-specific networks. Our methodology allows for the detection of incipient abnormalities that go undetected in conventional between-group analyses.

Quantitative Functional Arterial Spin Labeling (fASL) MRI--Sensitivity and Reproducibility of Regional CBF Changes Using Pseudo-Continuous ASL Product Sequences.

Arterial spin labeling (ASL) magnetic resonance imaging is increasingly used to quantify task-related brain activation. This study assessed functional ASL (fASL) using pseudo-continuous ASL (pCASL) product sequences from two vendors. By scanning healthy participants twice with each sequence while they performed a motor task, this study assessed functional ASL for 1) its sensitivity to detect task-related cerebral blood flow (CBF) changes, and 2) its reproducibility of resting CBF and absolute CBF changes (delta CBF) in the motor cortex. Whole-brain voxel-wise analyses showed that sensitivity for motor activation was sufficient with each sequence, and comparable between sequences. Reproducibility was assessed with within-subject coefficients of variation (wsCV) and intraclass correlation coefficients (ICC). Reproducibility of resting CBF was reasonably good within (wsCV: 14.1–15.7%; ICC: 0.69–0.77) and between sequences (wsCV: 15.1%; ICC: 0.69). Reproducibility of delta CBF was relatively low, both within (wsCV: 182–297%; ICC: 0.04–0.32) and between sequences (wsCV: 185%; ICC: 0.45), while inter-session variation was low. This may be due to delta CBF’s small mean effect (0.77–1.32 mL/100g gray matter/min). In conclusion, fASL seems sufficiently sensitive to detect task-related changes on a group level, with acceptable inter-sequence differences. Resting CBF may provide a consistent baseline to compare task-related activation to, but absolute regional CBF changes are more variable, and should be interpreted cautiously when acquired with two pCASL product sequences.

Functional connectivity and microstructural white matter changes in phenocopy frontotemporal dementia

AbstractObjectivesPhenocopy frontotemporal dementia (phFTD) is a rare and poorly understood clinical syndrome. PhFTD shows core behavioural variant FTD (bvFTD) symptoms without associated cognitive deficits and brain abnormalities on conventional MRI and without progression. In contrast to phFTD, functional connectivity and white matter (WM) microstructural abnormalities have been observed in bvFTD. We hypothesise that phFTD belongs to the same disease spectrum as bvFTD and investigated whether functional connectivity and microstructural WM changes similar to bvFTD are present in phFTD.MethodsSeven phFTD patients without progression or alternative psychiatric diagnosis, 12 bvFTD patients and 17 controls underwent resting state functional MRI (rs-fMRI) and diffusion tensor imaging (DTI). Default mode network (DMN) connectivity and WM measures were compared between groups.ResultsPhFTD showed subtly increased DMN connectivity and subtle microstructural changes in frontal WM tracts. BvFTD showed abnormalities in similar regions as phFTD, but had lower increased DMN connectivity and more extensive microstructural WM changes.ConclusionsOur findings can be interpreted as neuropathological changes in phFTD and are in support of the hypothesis that phFTD and bvFTD may belong to the same disease spectrum. Advanced MRI techniques, objectively identifying brain abnormalities, would therefore be potentially suited to improve the diagnosis of phFTD.Key points• PhFTD shows brain abnormalities that are similar to bvFTD. • PhFTD shows increased functional connectivity in the parietal default mode network. • PhFTD shows microstructural white matter abnormalities in the frontal lobe. • We hypothesise phFTD and bvFTD may belong to the same disease spectrum.

Structural and functional brain abnormalities place phenocopy frontotemporal dementia (FTD) in the FTD spectrum

Purpose ‘Phenocopy’ frontotemporal dementia (phFTD) patients may clinically mimic the behavioral variant of FTD (bvFTD), but do not show functional decline or abnormalities upon visual inspection of routine neuroimaging. We aimed to identify abnormalities in gray matter (GM) volume and perfusion in phFTD and to assess whether phFTD belongs to the FTD spectrum. We compared phFTD patients with both healthy controls and bvFTD patients. Materials & methods Seven phFTD and 11 bvFTD patients, and 20 age-matched controls underwent structural T1-weighted magnetic resonance imaging (MRI) and 3D pseudo-continuous arterial spin labeling (pCASL) at 3T. Normalized GM (nGM) volumes and perfusion, corrected for partial volume effects, were quantified regionally as well as in the entire supratentorial cortex, and compared between groups taking into account potential confounding effects of gender and scanner. Results PhFTD patients showed cortical atrophy, most prominently in the right temporal lobe. Apart from this regional atrophy, GM volume was generally not different from either controls or from bvFTD. BvFTD however showed extensive frontotemporal atrophy. Perfusion was increased in the left prefrontal cortex compared to bvFTD and to a lesser extent to controls. Conclusion PhFTD and bvFTD show overlapping cortical structural abnormalities indicating a continuum of changes especially in the frontotemporal regions. Together with functional changes suggestive of a compensatory response to incipient pathology in the left prefrontal regions, these findings are the first to support a possible neuropathological etiology of phFTD and suggest that phFTD may be a neurodegenerative disease on the FTD spectrum.

Automatic normative quantification of brain tissue volume to support the diagnosis of dementia: A clinical evaluation of diagnostic accuracy

Objectives To assesses whether automated brain image analysis with quantification of structural brain changes improves diagnostic accuracy in a memory clinic setting. Methods In 42 memory clinic patients, we evaluated whether automated quantification of brain tissue volumes, hippocampal volume and white matter lesion volume improves diagnostic accuracy for Alzheimers disease (AD) and frontotemporal dementia (FTD), compared to visual interpretation. Reference data were derived from a dementia-free aging population (n = 4915, aged >45 years), and were expressed as age- and sex-specific percentiles. Experienced radiologists determined the most likely imaging-based diagnosis based on structural brain MRI using three strategies (visual assessment of MRI only, quantitative normative information only, or a combination of both). Diagnostic accuracy of each strategy was calculated with the clinical diagnosis as the reference standard. Results Providing radiologists with only quantitative data decreased diagnostic accuracy both for AD and FTD compared to conventional visual rating. The combination of quantitative with visual information, however, led to better diagnostic accuracy compared to only visual ratings for AD. This was not the case for FTD. Conclusion Quantitative assessment of structural brain MRI combined with a reference standard in addition to standard visual assessment may improve diagnostic accuracy in a memory clinic setting.

Effects of systematic partial volume errors on the estimation of gray matter cerebral blood flow with arterial spin labeling MRI

ObjectivePartial volume (PV) correction is an important step in arterial spin labeling (ASL) MRI that is used to separate perfusion from structural effects when computing the mean gray matter (GM) perfusion. There are three main methods for performing this correction: (1) GM-threshold, which includes only voxels with GM volume above a preset threshold; (2) GM-weighted, which uses voxel-wise GM contribution combined with thresholding; and (3) PVC, which applies a spatial linear regression algorithm to estimate the flow contribution of each tissue at a given voxel. In all cases, GM volume is obtained using PV maps extracted from the segmentation of the T1-weighted (T1w) image. As such, PV maps contain errors due to the difference in readout type and spatial resolution between ASL and T1w images. Here, we estimated these errors and evaluated their effect on the performance of each PV correction method in computing GM cerebral blood flow (CBF).Materials and methodsTwenty-two volunteers underwent scanning using 2D echo planar imaging (EPI) and 3D spiral ASL. For each PV correction method, GM CBF was computed using PV maps simulated to contain estimated errors due to spatial resolution mismatch and geometric distortions which are caused by the mismatch in readout between ASL and T1w images. Results were analyzed to assess the effect of each error on the estimation of GM CBF from ASL data.ResultsGeometric distortion had the largest effect on the 2D EPI data, whereas the 3D spiral was most affected by the resolution mismatch. The PVC method outperformed the GM-threshold even in the presence of combined errors from resolution mismatch and geometric distortions. The quantitative advantage of PVC was 16% without and 10% with the combined errors for both 2D and 3D ASL. Consistent with theoretical expectations, for error-free PV maps, the PVC method extracted the true GM CBF. In contrast, GM-weighted overestimated GM CBF by 5%, while GM-threshold underestimated it by 16%. The presence of PV map errors decreased the calculated GM CBF for all methods.ConclusionThe quality of PV maps presents no argument for the preferential use of the GM-threshold method over PVC in the clinical application of ASL.