Generative adversarial networks (GAN) can produce images of improved quality but their ability to augment image-based classification is not fully explored. We evaluated if a modified GAN can learn ...from magnetic resonance imaging (MRI) scans of multiple magnetic field strengths to enhance Alzheimer's disease (AD) classification performance.
T1-weighted brain MRI scans from 151 participants of the Alzheimer's Disease Neuroimaging Initiative (ADNI), who underwent both 1.5-Tesla (1.5-T) and 3-Tesla imaging at the same time were selected to construct a GAN model. This model was trained along with a three-dimensional fully convolutional network (FCN) using the generated images (3T*) as inputs to predict AD status. Quality of the generated images was evaluated using signal to noise ratio (SNR), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) and Natural Image Quality Evaluator (NIQE). Cases from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL, n = 107) and the National Alzheimer's Coordinating Center (NACC, n = 565) were used for model validation.
The 3T*-based FCN classifier performed better than the FCN model trained using the 1.5-T scans. Specifically, the mean area under curve increased from 0.907 to 0.932, from 0.934 to 0.940, and from 0.870 to 0.907 on the ADNI test, AIBL, and NACC datasets, respectively. Additionally, we found that the mean quality of the generated (3T*) images was consistently higher than the 1.5-T images, as measured using SNR, BRISQUE, and NIQE on the validation datasets.
This study demonstrates a proof of principle that GAN frameworks can be constructed to augment AD classification performance and improve image quality.
Abstract Changes in several regions within the brain have been associated with progression from healthy aging to Alzheimer's disease (AD), including the hippocampus, entorhinal cortex, and the ...inferior parietal lobule (IPL). In this study, the IPL was divided into three subregions: the gyrus, the banks of the sulcus, and the fundus to determine if these regions are independent of medial temporal regions in the progression of AD. Participants of the Alzheimer's disease Neuroimaging Initiative (Alzheimer's disease Neuroimaging initiative (ADNI); n = 54) underwent a structural magnetic resonance imaging (MRI) scan and neuropsychological examination, and were categorized as normal controls, mild cognitively impaired (MCI), or AD. FreeSurfer was initially used to identify the boundaries of the IPL. Each subregion was then manually traced based on FreeSurfer curvature intensities. Multivariate analyses of variance were used to compare groups. Results suggest that changes in thickness of the banks of the inferior parietal lobule are occurring early in the progression from normal to MCI, followed by changes in the gyrus and fundus, and these measures are related to neuropsychological performance.
•Gulf War Illness model developed for the mouse can be extended to the rat.•Corticosterone enhances DFP-induced neuroinflammation in the rat model.•High order diffusion MRI successfully ...differentiates the different exposure conditions.
Veterans of the 1991 Gulf War were potentially exposed to a variety of toxic chemicals, including sarin nerve agent and pesticides, which have been suspected to be involved in the development of Gulf War Illness (GWI). Several of these exposures cause a neuroinflammatory response in mice, which may serve as a basis for the sickness behavior-like symptoms seen in veterans with GWI. Furthermore, conditions mimicking the physiological stress experienced during the war can exacerbate this effect. While neuroinflammation has been observed post-exposure using animal models, it remains a challenge to evaluate neuroinflammation and its associated cellular and molecular changes in vivo in veterans with GWI. Here, we evaluated neuroimmune-associated alterations in intact brains, applying our existing GWI mouse model to rats, by exposing them to 4days of corticosterone (CORT; 200mg/L in the drinking water), to mimic high physiological stress, followed by a single injection of the sarin nerve agent surrogate, diisopropyl fluorophosphate (DFP; 1.5mg/kg, i.p.). Then, we evaluated the neuroinflammatory responses using qPCR of cytokine mRNA and also examined brain structure with a novel high-order diffusion MRI. We found a CORT-enhancement of DFP-induced neuroinflammation, extending our mouse GWI model to the rat. High order diffusion MRI revealed different patterns among the different treatment groups. Particularly, while the CORT+DFP rats had more restricted spatial patterns in the hippocampus and the hypothalamus, the highest and most wide-spread differences were shown in DFP-treated rats compared to the controls in the thalamus, the amygdala, the piriform cortex and the ventral tegmental area. The association of these diffusion changes with neuroinflammatory cytokine expression indicates the potential for GW-relevant exposures to result in connectivity changes in the brain. By transferring this high order diffusion MRI into in vivo imaging in veterans with GWI, we can achieve further insights on the trajectories of the neuroimmune response over time and its impacts on behavior and potential neurological damage.
In this study, we have assessed the validity and reliability of an automated labeling system that we have developed for subdividing the human cerebral cortex on magnetic resonance images into gyral ...based regions of interest (ROIs). Using a dataset of 40 MRI scans we manually identified 34 cortical ROIs in each of the individual hemispheres. This information was then encoded in the form of an atlas that was utilized to automatically label ROIs. To examine the validity, as well as the intra- and inter-rater reliability of the automated system, we used both intraclass correlation coefficients (ICC), and a new method known as mean distance maps, to assess the degree of mismatch between the manual and the automated sets of ROIs. When compared with the manual ROIs, the automated ROIs were highly accurate, with an average ICC of 0.835 across all of the ROIs, and a mean distance error of less than 1 mm. Intra- and inter-rater comparisons yielded little to no difference between the sets of ROIs. These findings suggest that the automated method we have developed for subdividing the human cerebral cortex into standard gyral-based neuroanatomical regions is both anatomically valid and reliable. This method may be useful for both morphometric and functional studies of the cerebral cortex as well as for clinical investigations aimed at tracking the evolution of disease-induced changes over time, including clinical trials in which MRI-based measures are used to examine response to treatment.
Brain age of rhesus macaques over the lifespan Liu, Yang S.; Baxi, Madhura; Madan, Christopher R. ...
Neurobiology of aging,
July 2024, 2024-Jul, 2024-07-00, 20240701, Volume:
139
Journal Article
Peer reviewed
Open access
Through the application of machine learning algorithms to neuroimaging data the brain age methodology was shown to provide a useful individual-level biological age prediction and identify key brain ...regions responsible for the prediction. In this study, we present the methodology of constructing a rhesus macaque brain age model using a machine learning algorithm and discuss the key predictive brain regions in comparison to the human brain, to shed light on cross-species primate similarities and differences. Structural information of the brain (e.g., parcellated volumes) from brain magnetic resonance imaging of 43 rhesus macaques were used to develop brain atlas-based features to build a brain age model that predicts biological age. The best-performing model used 22 selected features and achieved an R2 of 0.72. We also identified interpretable predictive brain features including Right Fronto-orbital Cortex, Right Frontal Pole, Right Inferior Lateral Parietal Cortex, and Bilateral Posterior Central Operculum. Our findings provide converging evidence of the parallel and comparable brain regions responsible for both non-human primates and human biological age prediction.
•Machine-learning based rhesus macaques’ Brain age index was developed.•Volume of white and gray matter regions could predict chronological age.•Age-sensitive regions that most contribute to the prediction were identified.•Age-sensitive brain regions in rhesus macaque were comparable to humans.
Majority of dementia research is conducted in non-Hispanic White participants despite a greater prevalence of dementia in other racial groups. To obtain a better understanding of biomarker ...presentation of Alzheimer’s disease (AD) in the non-Hispanic White population, this study exclusively examined AD biomarker abnormalities in 85 Black and/or African American participants within the Alzheimer’s Disease Neuroimaging Initiative (ADNI). Participants were classified by the ADNI into 3 clinical groups: cognitively normal, mild cognitive impairment, or dementia. Data examined included demographics, apolipoprotein E (APOE) ε4, cerebrospinal fluid (CSF) Aβ1-42, CSF total tau (t-tau), CSF phosphorylated tau (p-tau), 3T magnetic resonance imaging (MRI), and measures of cognition and function. Analyses of variance and covariance showed lower cortical thickness in 5 of 7 selected MRI regions, lower hippocampal volume, greater volume of white matter hyperintensities, lower measures of cognition and function, lower measures of CSF Aβ1-42, and greater measures of CSF t-tau and p-tau between clinical groups. Our findings confirmed greater AD biomarker abnormalities between clinical groups in this sample.
Introduction
Previous Alzheimer's disease and related dementias (AD/ADRD) research studies have illustrated the significance of studying alterations in white matter (WM). Fewer studies have examined ...how WM integrity, measured with diffusion tensor imaging (DTI), is associated with volume of gray matter (GM) regions and measures of cognitive function in aged participants spanning the dementia continuum.
Methods
Magnetic resonance imaging and cognitive data were collected from 241 Boston University Alzheimer's Disease Research Center participants who spanned from cognitively normal controls to amnestic mild cognitive impairment to having dementia. Primary DTI tracts of interest were the cingulum ventral (CV) and cingulum dorsal (CD) pathways. GM regions of interest (ROIs) were in the medial temporal lobe (MTL), prefrontal cortex, and retrosplenial cortex. Analyses of covariance models were used to assess differences in WM integrity across groups (control, amnestic mild cognitive impairment, and dementia). Multiple linear regression models were used to assess associations between WM integrity and GM volume, and with measures of memory and executive function.
Results
Differences in WM integrity were shown in both cingulum pathways in participants across the dementia continuum. Associations between WM integrity of both cingulum pathways and volume of selected GM ROIs were widespread. Functionally significant associations were found between WM of the CV pathway and memory, independent of MTL GM volume.
Discussion
Differences in WM integrity of the cingulum bundle and surrounding GM ROI are likely related to the progression of AD/ADRD. Such differences should continue to be studied, particularly in association with memory performance.
Key Findings:
Differences exist in the white matter integrity of the cingulum bundle between participants who are on the dementia continuum.
White matter integrity of the cingulum is associated with gray matter volume.
White matter integrity of the cingulum ventral, independent of gray matter volume, may be predictive of memory performance.
Abstract The Alzheimer’s Disease Neuroimaging Initiative (ADNI) three-dimensional T1 -weighted magnetic resonance imaging (MRI) acquisitions provide a rich data set for developing and testing ...analysis techniques for extracting structural endpoints. To promote greater rigor in analysis and meaningful comparison of different algorithms, the ADNI MRI Core has created standardized analysis sets of data comprising scans that met minimum quality control requirements. We encourage researchers to test and report their techniques against these data. Standard analysis sets of volumetric scans from ADNI-1 have been created, comprising screening visits, 1-year completers (subjects who all have screening, 6- and 12-month scans), 2-year annual completers (screening, 1-year and 2-year scans), 2-year completers (screening, 6-months, 1-year, 18-months mild cognitive impaired (MCI) only, and 2-year scans), and complete visits (screening, 6-month, 1-year, 18-month MCI only, 2-year, and 3-year normal and MCI only scans). As the ADNI-GO/ADNI-2 data become available, updated standard analysis sets will be posted regularly.
Abstract Functions of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) magnetic resonance imaging (MRI) core fall into three categories: (1) those of the central MRI core laboratory at Mayo ...Clinic, Rochester, Minnesota, needed to generate high quality MRI data in all subjects at each time point; (2) those of the funded ADNI MRI core imaging analysis groups responsible for analyzing the MRI data; and (3) the joint function of the entire MRI core in designing and problem solving MR image acquisition, pre-processing, and analyses methods. The primary objective of ADNI was and continues to be improving methods for clinical trials in Alzheimer's disease. Our approach to the present (“ADNI-GO”) and future (“ADNI-2,” if funded) MRI protocol will be to maintain MRI methodological consistency in the previously enrolled “ADNI-1” subjects who are followed up longitudinally in ADNI-GO and ADNI-2. We will modernize and expand the MRI protocol for all newly enrolled ADNI-GO and ADNI-2 subjects. All newly enrolled subjects will be scanned at 3T with a core set of three sequence types: 3D T1-weighted volume, FLAIR, and a long TE gradient echo volumetric acquisition for micro hemorrhage detection. In addition to this core ADNI-GO and ADNI-2 protocol, we will perform vendor-specific pilot sub-studies of arterial spin-labeling perfusion, resting state functional connectivity, and diffusion tensor imaging. One of these sequences will be added to the core protocol on systems from each MRI vendor. These experimental sub-studies are designed to demonstrate the feasibility of acquiring useful data in a multicenter (but single vendor) setting for these three emerging MRI applications.