Protocol for a machine learning algorithm predicting depressive disorders using the T1w/T2w ratio.
Ontology highlight
ABSTRACT:
SUBMITTER: Baranger DAA
PROVIDER: S-EPMC8720909 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Myelination is a key developmental process that promotes rapid and efficient information transfer. Myelin also stabilizes existing brain networks and thus may constrain neuroplasticity, defined here as the brain's potential to change in response to experiences rather than the canonical definition as the process of change. Characterizing individual differences in neuroplasticity may shed light on mechanisms by which early experiences shape learning, brain and body development, and response to interventions. The T1-weighted/T2-weighted (T1w/T2w) MRI signal ratio is a proxy measure of cortical microstructure and thus neuroplasticity. Here, in pre-registered analyses, we investigated individual differences in T1w/T2w ratios in children (ages 4-10, n = 157). T1w/T2w ratios were positively associated with age within early-developing sensorimotor and attention regions. We also tested whether socioeconomic status, cognition (crystallized knowledge or fluid reasoning), and biological age (as measured with molar eruption) were related to T1w/T2w signal but found no significant effects. Associations among T1w/T2w ratios, early experiences, and cognition may emerge later in adolescence and may not be strong enough to detect in moderate sample sizes.
| S-EPMC10439503 | biostudies-literature
Project description:OBJECTIVE:Newer magnetic resonance imaging (MRI) techniques have shown promise in capturing early Parkinson disease (PD)-related changes in the substantia nigra pars compacta (SNc), the key pathological loci. Their translational value, however, is hindered by technical complexity and inconsistent results. METHODS:A novel yet simple MRI contrast, the T1w/T2w ratio, was used to study 76 PD patients and 70 controls. The T1w/T2w ratio maps were analyzed using both voxel-based and region-of-interest approaches in normalized space. The sensitivity and specificity of the SNc T1w/T2w ratio in discriminating between PD and controls also were assessed. In addition, its diagnostic performance was tested in a subgroup of PD patients with disease duration??2 years (PDE). A second independent cohort of 73 PD patients and 49 controls was used for validation. RESULTS:Compared to controls, PD patients showed a higher T1w/T2w ratio in both the right (cluster size?=?164mm3 , p?<?0.0001) and left (cluster size?=?213mm3 , p?<?0.0001) midbrain that was located ventrolateral to the red nucleus and corresponded to the SNc. The region-of-interest approach confirmed the group difference in the SNc T1w/T2w ratio between PD and controls (p?<?0.0001). The SNc T1w/T2w ratio had high sensitivity (0.908) and specificity (0.80) to separate PD and controls (area under the curve [AUC]?=?0.926), even for PDE patients (AUC?=?0.901, sensitivity?=?0.857, specificity?=?0.857). These results were validated in the second cohort. INTERPRETATION:The T1w/T2w ratio can detect PD-related changes in the SNc and may be used as a novel, parsimonious in vivo biomarker for the disease, particularly for early stage patients, with high translational value for clinical practice and research. ANN NEUROL 2019;85:96-104.
| S-EPMC6342624 | biostudies-literature
Project description:Diagnosis of multiple system atrophy (MSA) may be improved by using multimodal imaging approaches. We investigated the use of T1-weighted/T2-weighted (T1w/T2w) images ratio combined with voxel-based morphometry to evaluate brain tissue integrity in MSA compared to Parkinson's disease (PD) and healthy controls (HC). Twenty-six patients with MSA, 43 patients with PD and 56 HC were enrolled. Whole brain voxel-based and local regional analyses were performed to evaluate gray and white matter (GM and WM) tissue integrity and mean regional values were used for patients classification using logistic regression. Increased mean regional values of T1w/T2w in bilateral putamen were detected in MSA-P compared to PD and HC. The combined use of regional GM and T1w/T2w values in the right and left putamen showed the highest accuracy in discriminating MSA-P from PD and good accuracy in discriminating MSA from PD and HC. A good accuracy was also found in discriminating MSA from PD and HC by either combining regional GM and T1w/T2w values in the cerebellum or regional WM and T1w/T2w in the cerebellum and brainstem. The T1w/T2w image ratio alone or combined with validated MRI parameters can be further considered as a potential candidate biomarker for differential diagnosis of MSA.
| S-EPMC8569168 | biostudies-literature
Project description:One of the challenges in glioblastoma (GBM) imaging is to visualize non-enhancing tumor (NET) lesions. The ratio of T1- and T2-weighted images (rT1/T2) is reported as a helpful imaging surrogate of microstructures of the brain. This research study investigated the possibility of using rT1/T2 as a surrogate for the T1- and T2-relaxation time of GBM to visualize NET effectively. The data of thirty-four histologically confirmed GBM patients whose T1-, T2- and contrast-enhanced T1-weighted MRI and 11C-methionine positron emission tomography (Met-PET) were available were collected for analysis. Two of them also underwent MR relaxometry with rT1/T2 reconstructed for all cases. Met-PET was used as ground truth with T2-FLAIR hyperintense lesion, with >1.5 in tumor-to-normal tissue ratio being NET. rT1/T2 values were compared with MR relaxometry and Met-PET. rT1/T2 values significantly correlated with both T1- and T2-relaxation times in a logarithmic manner (p < 0.05 for both cases). The distributions of rT1/T2 from Met-PET high and low T2-FLAIR hyperintense lesions were different and a novel metric named Likeliness of Methionine PET high (LMPH) deriving from rT1/T2 was statistically significant for detecting Met-PET high T2-FLAIR hyperintense lesions (mean AUC = 0.556 ± 0.117; p = 0.01). In conclusion, this research study supported the hypothesis that rT1/T2 could be a promising imaging marker for NET identification.
| S-EPMC8774070 | biostudies-literature
Project description:Loss of myelin in the brain may lead to cognitive decline in Alzheimer's disease (AD). The ratio of T1 weighted/T2 weighted (T1w/T2w) on magnetic resonance imaging has been used as a proxy for myelin content in the brain. Using this approach, we investigated the correlation between the white matter (WM) T1w/T2w ratio and both cognitive scores and disease progression in AD. A total of 93 participants who were cognitively unimpaired or diagnosed with mild cognitive impairment or AD dementia were recruited between March 2021 and November 2022. All participants were assessed using neuropsychological tests, and a subset of the participants was assessed every 1 year to monitor disease progression. We observed significant positive associations between the WM T1w/T2w ratio and executive function within the fornix, sagittal stratum, anterior internal capsule, and body of the corpus callosum (False discovery rate [FDR]-corrected P-value < 0.05). There was a marginal interaction between the WM T1w/T2w ratio of the left anterior internal capsule and the longitudinal change in sum of boxes of the Clinical Dementia Rating Scale (FDR-corrected P-value = 0.05). The present study demonstrated that the WM T1w/T2w ratio was associated with executive function and disease progression, suggesting that it may be a novel neuroimaging marker for AD.
| S-EPMC10973518 | biostudies-literature
Project description:BackgroundCross-sectional studies suggest normal appearing white matter (NAWM) integrity loss may lead to cortical atrophy in late-stage relapsing-remitting multiple sclerosis (MS).ObjectiveTo investigate the relationship between NAWM integrity and cortical thickness from first clinical presentation longitudinally.MethodsNAWM integrity and cortical thickness were assessed with 3T magnetic resonance imaging (MRI) in 102 patients with clinically isolated syndrome or early MS (33.2 (20.1-60.1) years old, 68% female) from first clinical presentation over 2.8 ± 1.6 years. Fifty healthy controls (HCs) matched for age and sex were included. NAWM integrity was evaluated using the standardized T1w/T2w ratio (sT1w/T2w). The association between sT1w/T2w and cortical thickness was assessed using linear mixed models. The effect of disease activity was investigated using the No Evidence of Disease Activity (NEDA-3) criteria.ResultsAt baseline, sT1w/T2w (p = 0.152) and cortical thickness (p = 0.489) did not differ from HCs. Longitudinally, decreasing sT1w/T2w was associated with cortical thickness and increasing lesion burden (marginal R2 = 0.061). The association was modulated by failing NEDA-3 (marginal R2 = 0.097).ConclusionsT1w/T2w may be a useful MRI biomarker for early MS, detecting relevant NAWM damage over time using conventional MRI scans, although with less sensitivity compared to quantitative measures.
| S-EPMC8597181 | biostudies-literature
Project description:Several MRI techniques have become available to support the early diagnosis of multiple system atrophy (MSA), but few longitudinal studies on both MSA variants have been performed, and there are no established MRI markers of disease progression. We aimed to characterize longitudinal brain changes in 26 patients with MSA (14 MSA-P and 12 MSA-C) over a 1-year follow-up period in terms of local tissue density and T1w/T2w ratio in a-priori regions, namely, bilateral putamen, cerebellar gray matter (GM), white matter (WM), and substantia nigra (SN). A significant GM density decrease was found in cerebellum and left putamen in the entire group (10.7 and 33.1% variation, respectively) and both MSA subtypes (MSA-C: 15.4 and 33.0% variation; MSA-P: 7.7 and 33.2%) and in right putamen in the entire group (19.8% variation) and patients with MSA-C (20.9% variation). A WM density decrease was found in the entire group (9.3% variation) and both subtypes in cerebellum-brainstem (MSA-C: 18.0% variation; MSA-P: 5% variation). The T1w/T2w ratio increase was found in the cerebellar and left putamen GM (6.6 and 24.9% variation), while a significant T1w/T2w ratio decrease was detected in SN in the entire MSA group (31% variation). We found a more progressive atrophy of the cerebellum in MSA-C with a similar progression of putaminal atrophy in the two variants. T1w/T2w ratio can be further studied as a potential marker of disease progression, possibly reflecting decreased neuronal density or iron accumulation.
| S-EPMC9626981 | biostudies-literature
Project description:The restructuring and optimization of the cerebral cortex from early childhood and through adolescence is an essential feature of human brain development, underlying immense cognitive improvements. Beyond established morphometric cortical assessments, the T1w/T2w ratio quantifies partly separate biological processes, and might inform models of typical neurocognitive development and developmental psychopathology. In the present study, we computed vertex-wise T1w/T2w ratio across the cortical surface in 621 youths (3-21 years) sampled from the Pediatric Imaging, Neurocognition, and Genetics (PING) study and tested for associations with individual differences in age, sex, and both general and specific cognitive abilities. The results showed a near global linear age-related increase in T1w/T2w ratio across the brain surface, with a general posterior to anterior increasing gradient in association strength. Moreover, results indicated that boys in late adolescence had regionally higher T1w/T2w ratio as compared to girls. Across individuals, T1w/T2w ratio was negatively associated with general and several specific cognitive abilities mainly within anterior cortical regions. Our study indicates age-related differences in T1w/T2w ratio throughout childhood, adolescence, and young adulthood, in line with the known protracted myelination of the cortex. Moreover, the study supports T1w/T2w ratio as a promising surrogate measure of individual differences in intracortical brain structure in neurodevelopment.
| S-EPMC7555087 | biostudies-literature
Project description:Predicting crash injury severity is a crucial constituent of reducing the consequences of traffic crashes. This study developed machine learning (ML) models to predict crash injury severity using 15 crash-related parameters. Separate ML models for each cluster were obtained using fuzzy c-means, which enhanced the predicting capability. Finally, four ML models were developed: feed-forward neural networks (FNN), support vector machine (SVM), fuzzy C-means clustering based feed-forward neural network (FNN-FCM), and fuzzy c-means based support vector machine (SVM-FCM). Features that were easily identified with little investigation on crash sites were used as an input so that the trauma center can predict the crash severity level based on the initial information provided from the crash site and prepare accordingly for the treatment of the victims. The input parameters mainly include vehicle attributes and road condition attributes. This study used the crash database of Great Britain for the years 2011-2016. A random sample of crashes representing each year was used considering the same share of severe and non-severe crashes. The models were compared based on injury severity prediction accuracy, sensitivity, precision, and harmonic mean of sensitivity and precision (i.e., F1 score). The SVM-FCM model outperformed the other developed models in terms of accuracy and F1 score in predicting the injury severity level of severe and non-severe crashes. This study concluded that the FCM clustering algorithm enhanced the prediction power of FNN and SVM models.
| S-EPMC7432564 | biostudies-literature
Project description:Finding the ground state of a quantum many-body system is a fundamental problem in quantum physics. In this work, we give a classical machine learning (ML) algorithm for predicting ground state properties with an inductive bias encoding geometric locality. The proposed ML model can efficiently predict ground state properties of an n-qubit gapped local Hamiltonian after learning from only [Formula: see text] data about other Hamiltonians in the same quantum phase of matter. This improves substantially upon previous results that require [Formula: see text] data for a large constant c. Furthermore, the training and prediction time of the proposed ML model scale as [Formula: see text] in the number of qubits n. Numerical experiments on physical systems with up to 45 qubits confirm the favorable scaling in predicting ground state properties using a small training dataset.
| S-EPMC10828424 | biostudies-literature