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 Alzheimer's 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.
Many medical image segmentation methods are based on supervised classification of voxels. Such methods generally perform well when provided with a training set that is representative of the test images to segment. However, problems may arise when training and test data follow different distributions, for example due to differences in scanners, scanning protocols, or patient groups. Under such conditions, weighting training images according to distribution similarity has been shown to greatly improve performance. However, this assumes that part of the training data is representative of the test data; it does not make unrepresentative data more similar. We therefore investigate kernel learning as a way to reduce differences between training and test data and explore the added value of kernel learning for image weighting. We also propose a new image weighting method that minimizes maximum mean discrepancy (MMD) between training and test data, which enables the joint optimization of image weights and kernel. Experiments on brain tissue, white matter lesion, and hippocampus segmentation show that both kernel learning and image weighting, when used separately, greatly improve performance on heterogeneous data. Here, MMD weighting obtains similar performance to previously proposed image weighting methods. Combining image weighting and kernel learning, optimized either individually or jointly, can give a small additional improvement in performance.
Previous studies have shown that hippocampal volume is an early marker for dementia. We investigated whether hippocampal shape characteristics extracted from MRI scans are predictive for the development of dementia during follow up in subjects who were nondemented at baseline. Furthermore, we assessed whether hippocampal shape provides additional predictive value independent of hippocampal volume. Five hundred eleven brain MRI scans from elderly nondemented participants of a prospective population-based imaging study were used. During the 10-year follow-up period, 52 of these subjects developed dementia. For training and evaluation independent of age and gender, a subset of 50 cases and 150 matched controls was selected. The hippocampus was segmented using an automated method. From the segmentation, the volume was determined and a statistical shape model was constructed. We trained a classifier to distinguish between subjects who developed dementia and subjects who stayed cognitively healthy. For all subjects the a posteriori probability to develop dementia was estimated using the classifier in a cross-validation experiment. The area under the ROC curve for volume, shape, and the combination of both were, respectively, 0.724, 0.743, and 0.766. A logistic regression model showed that adding shape to a model using volume corrected for age and gender increased the global model-fit significantly (P = 0.0063). We conclude that hippocampal shape derived from MRI scans is predictive for dementia before clinical symptoms arise, independent of age and gender. Furthermore, the results suggest that hippocampal shape provides additional predictive value over hippocampal volume and that combining shape and volume leads to better prediction.
Background The prevalence of end-stage renal disease (ESRD) is increasing worldwide, with the majority of new ESRD cases diagnosed in patients aged >60 years. These older patients are at increased risk for impaired cognitive functioning, potentially through cerebral small vessel disease (SVD). Novel markers of vascular integrity may be of clinical value for identifying patients at high risk for cognitive impairment. Methods We aimed to associate the levels of Angiopoietin-2 (Ang-2), asymmetric dimethylarginine (ADMA), and a selection of eight circulating angiogenic miRNAs with SVD and cognitive impairment in older patients reaching ESRD that did not initiate renal replacement therapy yet (n = 129; mean age 75.3 years; mean eGFR 16.4 mL/min). We assessed brain MRI changes of SVD (white matter hyperintensity volume, microbleeds and presence of lacunes) and measures of cognition in domains of memory, psychomotor speed and executive function, comprised in a neuropsychological test battery. Results Older patients reaching ESRD showed an unfavorable angiogenic profile, as indicated by aberrant levels of Ang-2 and five angiogenic miRNAs (miR-27a, miR-126, miR-132, miR-223, miR-326), compared to healthy persons and patients with diabetic nephropathy. Moreover, Ang-2 associated with SVD and with the domains of psychomotor speed and executive function, while miR-223 and miR-29a associated with memory function. Conclusions Taken together, these novel angiogenic markers might serve to identify older patients with ESRD at risk of cognitive decline, as well as give insight into the underlying (vascular) pathophysiology.
Background To analyze the effect of treatment on neurocognitive functioning and the association of neurocognition with radiological abnormalities in primary central nervous system lymphoma (PCNSL). Methods 199 patients from a phase III trial (HOVON 105/ALLG NHL 24), randomized to standard chemotherapy with or without rituximab, followed in patients ≤60 years-old by 30Gy WBRT, were asked to participate in a neuropsychological evaluation before and during treatment, and up to 2 years post-treatment. Scores were transformed into a standardized z-score; clinically relevant changes were defined as a change in z-score of ≥1 standard deviation. The effect of WBRT was analyzed in irradiated patients. All MRIs were centrally assessed for white matter abnormalities and cerebral atrophy, and their relation with neurocognitive scores over time in each domain was calculated. Results 125/199 patients consented to neurocognitive evaluation. Statistically significant improvements in neurocognition were seen in all domains. A clinically relevant improvement was seen only in the motor speed domain, without differences between the arms. In the follow-up of irradiated patients (n=43), no change was observed in any domain score, compared to after WBRT. Small but significant inverse correlations were found between neurocognitive scores over time and changes in white matter abnormalities (regression coefficients: -0.048 to -0.347) and cerebral atrophy (-0.212 to -1.774). Conclusions Addition of rituximab to standard treatment in PCNSL patients did not impact neurocognitive functioning up to two years post-treatment, nor did treatment with 30Gy WBRT in patients ≤60 years-old. Increased white matter abnormalities and brain atrophy showed weak associations with neurocognition.
With the increasing number of datasets encountered in imaging studies, the increasing complexity of processing workflows, and a growing awareness for data stewardship, there is a need for managed, automated workflows. In this paper, we introduce Fastr, an automated workflow engine with support for advanced data flows. Fastr has built-in data provenance for recording processing trails and ensuring reproducible results. The extensible plugin-based design allows the system to interface with virtually any image archive and processing infrastructure. This workflow engine is designed to consolidate quantitative imaging biomarker pipelines in order to enable easy application to new data.
Many successful approaches in MR brain segmentation use supervised voxel classification, which requires manually labeled training images that are representative of the test images to segment. However, the performance of such methods often deteriorates if training and test images are acquired with different scanners or scanning parameters, since this leads to differences in feature representations between training and test data.In this paper we propose a feature-space transformation (FST) to overcome such differences in feature representations. The proposed FST is derived from unlabeled images of a subject that was scanned with both the source and the target scan protocol. After an affine registration, these images give a mapping between source and target voxels in the feature space. This mapping is then used to map all training samples to the feature representation of the test samples.We evaluated the benefit of the proposed FST on hippocampus segmentation. Experiments were performed on two datasets: one with relatively small differences between training and test images and one with large differences. In both cases, the FST significantly improved the performance compared to using only image normalization. Additionally, we showed that our FST can be used to improve the performance of a state-of-the-art patch-based-atlas-fusion technique in case of large differences between scanners.
Chronic silent brain infarctions, detected as new white matter hyperintensities on magnetic resonance imaging (MRI) following transcatheter aortic valve implantation (TAVI), are associated with long-term cognitive deterioration. This is the first study to investigate to which extent the calcification volume of the native aortic valve (AV) measured with cardiac computed tomography angiography (CTA) predicts the increase in chronic white matter hyperintensity volume after TAVI. A total of 36 patients (79 ± 5 years, median EuroSCORE II 1.9%, Q1–Q3 1.5–3.4%) with severe AV stenosis underwent fluid attenuation inversion recovery (FLAIR) MRI < 24 h prior to TAVI and at 3 months follow-up for assessment of cerebral white matter hyperintensity volume (mL). Calcification volumes (mm3) of the AV, aortic arch, landing zone and left ventricle were measured on the CTA pre-TAVI. The largest calcification volumes were found in the AV (median 692 mm3) and aortic arch (median 633 mm3), with a large variation between patients (Q1–Q3 482–1297 mm3 and 213–1727 mm3, respectively). The white matter hyperintensity volume increased in 72% of the patients. In these patients the median volume increase was of 1.1 mL (Q1–Q3 0.3–4.6 mL), corresponding with a 27% increase from baseline (Q1–Q3 7–104%). The calcification volume in the AV predicted the increase of white matter hyperintensity volume (Δ%), with a 35% increase of white matter hyperintensity volume, per 100 mm3 of AV calcification volume (SE 8.5, p < 0.001). The calcification volumes in the aortic arch, landing zone and left ventricle were not associated with the increase in white matter hyperintensity volume. In 72% of the patients new chronic white matter hyperintensities developed 3 months after TAVI, with a median increase of 27%. A higher calcification volume in the AV was associated with a larger increase in the white matter hyperintensity volume. These findings show the potential for automated AV calcium screening as an imaging biomarker to predict chronic silent brain infarctions.Electronic supplementary materialThe online version of this article (10.1007/s10554-019-01663-0) contains supplementary material, which is available to authorized users.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.