Deep learning can provide rapid brain age estimation based on brain magnetic resonance imaging (MRI). However, most studies use one neural network to extract the global information from the whole input image, ignoring the local fine-grained details. In this paper, we propose a global-local transformer, which consists of a global-pathway to extract the global-context information from the whole input image and a local-pathway to extract the local fine-grained details from local patches. The fine-grained information from the local patches are fused with the global-context information by the attention mechanism, inspired by the transformer, to estimate the brain age. We evaluate the proposed method on 8 public datasets with 8,379 healthy brain MRIs with the age range of 0-97 years. 6 datasets are used for cross-validation and 2 datasets are used for evaluating the generality. Comparing with other state-of-the-art methods, the proposed global-local transformer reduces the mean absolute error of the estimated ages to 2.70 years and increases the correlation coefficient of the estimated age and the chronological age to 0.9853. In addition, our proposed method provides regional information of which local patches are most informative for brain age estimation. Our source code is available on: https://github.com/shengfly/global-local-transformer.

Pregnancy and lactation can change the maternal nutrient reserve. Non-invasive, quantitative markers of maternal nutrient intake could enable personalized dietary recommendations that improve health outcomes in mothers and infants. Macular pigment optical density (MPOD) is a candidate marker, as MPOD values generally reflect carotenoid intake. We evaluated the association of MPOD with dietary and breastmilk carotenoids in postpartum women. MPOD measurements and dietary intake of five carotenoids were obtained from 80 mothers in the first three months postpartum. Breastmilk samples from a subset of mothers were analyzed to determine their nutrient composition. The association between MPOD and dietary or breastmilk carotenoids was quantitatively assessed to better understand the availability and mobilization of carotenoids. Our results showed that dietary α-carotene was positively correlated with MPOD. Of the breastmilk carotenoids, 13-cis-lutein and trans-lutein were correlated with MPOD when controlled for the total lutein in breastmilk. Other carotenoids in breastmilk were not associated with MPOD. Maternal MPOD is positively correlated with dietary intake of α-carotene in the early postpartum period, as well as with the breastmilk content of lutein. MPOD may serve as a potential marker for the intake of carotenoids, especially α-carotene, in mothers in the early postpartum period.

Background: Substantial variations in the prevalence of mild cognitive impairment (MCI) and its subtypes have been reported, although mostly in geographically defined developed countries and regions. Less is known about MCI and its subtypes in rural areas of less developed central China. Aims: The study aimed to compare the prevalence of MCI and its subtypes in residents aged 65 years or older in urban and rural areas of Hubei Province, China. Methods: Participants aged 65 years or older were recruited between 2018 and 2019. Inperson structured interviews and clinical and neuropsychological assessments were performed at city health community centres and township hospitals. Results: Among 2644 participants without dementia, 735 had MCI, resulting in a prevalence of 27.8% for total MCI, 20.9% for amnestic MCI (aMCI) and 6.9% for non-amnestic MCI (naMCI). The prevalence of MCI in urban and rural areas was 20.2% and 44.1%, respectively. After adjusting for demographic factors, the prevalence of total MCI, aMCI and naMCI differed significantly between rural and urban areas (adjusted odds ratio (OR) 2.10, 1.44 and 3.76, respectively). Subgroup analysis revealed an association between rural socioeconomic and lifestyle disadvantage and MCI and its subtypes. Conclusions: Our findings suggest that the prevalence of MCI among urban residents in central China is consistent with that in other metropolis areas, such as Shanghai, but the prevalence in rural areas is twice that in urban areas. Prospective studies and dementia prevention in China should focus on rural areas.

BACKGROUND: The prevalence of dementia in China, particularly in rural areas, is consistently increasing; however, research on population-attributable fractions (PAFs) of risk factors for dementia is scarce. METHODS: We conducted a cross-sectional survey, namely, the China Multicentre Dementia Survey (CMDS) in selected rural and urban areas from 2018 to 2020. We performed face-to-face interviews and neuropsychological and clinical assessments to reach a consensus on dementia diagnosis. Prevalence and weighted PAFs of eight modifiable risk factors (six classical: less childhood education, hearing impairment, depression, physical inactivity, diabetes, and social isolation, and two novels: olfactory decline and being unmarried) for all-cause dementia were estimated. RESULTS: Overall, CMDS included 17,589 respondents aged ≥ 65 years, 55.6% of whom were rural residents. The age- and sex-adjusted prevalence for all-cause dementia was 9.11% (95% CI 8.96-9.26), 5.19% (5.07-5.31), and 11.98% (11.8-12.15) in the whole, urban, and rural areas of China, respectively. Further, the overall weighted PAFs of the eight potentially modifiable risk factors were 53.72% (95% CI 52.73-54.71), 50.64% (49.4-51.89), and 56.54% (55.62-57.46) in the whole, urban, and rural areas of China, respectively. The eight risk factors' prevalence differed between rural and urban areas. Lower childhood education (PAF: 13.92%) and physical inactivity (16.99%) were primary risk factors in rural and urban areas, respectively. CONCLUSIONS: The substantial urban-rural disparities in the prevalence of dementia and its risk factors exist, suggesting the requirement of resident-specific dementia-prevention strategies.

The accurate prediction of fetal brain age using magnetic resonance imaging (MRI) may contribute to the identification of brain abnormalities and the risk of adverse developmental outcomes. This study aimed to propose a method for predicting fetal brain age using MRIs from 220 healthy fetuses between 15.9 and 38.7 weeks of gestational age (GA). We built a 2D single-channel convolutional neural network (CNN) with multiplanar MRI slices in different orthogonal planes without correction for interslice motion. In each fetus, multiple age predictions from different slices were generated, and the brain age was obtained using the mode that determined the most frequent value among the multiple predictions from the 2D single-channel CNN. We obtained a mean absolute error (MAE) of 0.125 weeks (0.875 days) between the GA and brain age across the fetuses. The use of multiplanar slices achieved significantly lower prediction error and its variance than the use of a single slice and a single MRI stack. Our 2D single-channel CNN with multiplanar slices yielded a significantly lower stack-wise MAE (0.304 weeks) than the 2D multi-channel (MAE = 0.979, p < 0.001) and 3D (MAE = 1.114, p < 0.001) CNNs. The saliency maps from our method indicated that the anatomical information describing the cortex and ventricles was the primary contributor to brain age prediction. With the application of the proposed method to external MRIs from 21 healthy fetuses, we obtained an MAE of 0.508 weeks. Based on the external MRIs, we found that the stack-wise MAE of the 2D single-channel CNN (0.743 weeks) was significantly lower than those of the 2D multi-channel (1.466 weeks, p < 0.001) and 3D (1.241 weeks, p < 0.001) CNNs. These results demonstrate that our method with multiplanar slices accurately predicts fetal brain age without the need for increased dimensionality or complex MRI preprocessing steps.

Functional connectivity (FC) techniques can delineate brain organization as early as infancy, enabling the characterization of early brain characteristics associated with subsequent behavioral outcomes. Previous studies have identified specific functional networks in infant brains that underlie cognitive abilities and pathophysiology subsequently observed in toddlers and preschoolers. However, it is unknown whether and how functional networks emerging within the first 18 months of life contribute to the development of higher order, complex functions of language/literacy at school-age. This 5-year longitudinal imaging project starting in infancy, utilized resting-state functional magnetic resonance imaging and demonstrated prospective associations between FC in infants/toddlers and subsequent language and foundational literacy skills at 6.5 years old. These longitudinal associations were shown independently of key environmental influences and further present in a subsample of infant imaging data (≤12 months), suggesting early emerged functional networks specifically linked to high-order language and preliteracy skills. Moreover, emergent language skills in infancy and toddlerhood contributed to the prospective associations, implicating a role of early linguistic experiences in shaping the FC correlates of long-term oral language skills. The current results highlight the importance of functional organization established in infancy and toddlerhood as a neural scaffold underlying the learning process of complex cognitive functions.

Quantification of proton magnetic resonance spectroscopy (1 H-MRS) data is commonly performed by referencing the ratio of the signal from one metabolite, or metabolite group, to that of another, or to the water signal. Both approaches have drawbacks: ratios of two metabolites can be difficult to interpret because study effects may be driven by either metabolite, and water-referenced data must be corrected for partial volume and relaxation effects in the water signal. Here, we introduce combined reference (CRef) analysis, which compensates for both limitations. In this approach, metabolites are referenced to the combined signal of several reference metabolites or metabolite groups. The approach does not require the corrections necessary for water scaling and produces results that are less sensitive to the variation of any single reference signal, thereby aiding the interpretation of results. We demonstrate CRef analysis using 202 1 H-MRS acquisitions from the brains of 140 infants, scanned at approximately 1 and 3 months of age. We show that the combined signal of seven reference metabolites or metabolite groups is highly correlated with the water signal, corrected for partial volume and relaxation effects associated with cerebral spinal fluid. We also show that the combined reference signal is equally or more uniform across subjects than the reference signals from single metabolites or metabolite groups. We use CRef analysis to quantify metabolite concentration changes during the first several months of life in typically developing infants.

Brain age estimated by machine learning from T1-weighted magnetic resonance images (T1w MRIs) can reveal how brain disorders alter brain aging and can help in the early detection of such disorders. A fundamental step is to build an accurate age estimator from healthy brain MRIs. We focus on this step, and propose a framework to improve the accuracy, generality, and interpretation of age estimation in healthy brain MRIs. For accuracy, we used one of the largest sample sizes (N = 16,705). For each subject, our proposed algorithm first explicitly splits the T1w image, which has been commonly treated as a single-channel 3D image in other studies, into two 3D image channels representing contrast and morphometry information. We further proposed a "fusion-with-attention" deep learning convolutional neural network (FiA-Net) to learn how to best fuse the contrast and morphometry image channels. FiA-Net recognizes varying contributions across image channels at different brain anatomy and different feature layers. In contrast, multi-channel fusion does not exist for brain age estimation, and is mostly attention-free in other medical image analysis tasks (e.g., image synthesis, or segmentation), where treating channels equally may not be optimal. For generality, we used lifespan data 0-97 years of age for real-world utility; and we thoroughly tested FiA-Net for multi-site and multi-scanner generality by two phases of cross-validations in discovery and replication data, compared to most other studies with only one phase of cross-validation. For interpretation, we directly measured each artificial neuron's correlation with the chronological age, compared to other studies looking at the saliency of features where salient features may or may not predict age. Overall, FiA-Net achieved a mean absolute error (MAE) of 3.00 years and Pearson correlation r=0.9840 with known chronological ages in healthy brain MRIs 0-97 years of age, comparing favorably with state-of-the-art algorithms and studies for accuracy and generality across sites and datasets. We also provided interpretations on how different artificial neurons and real neuroanatomy contribute to the age estimation.

Background A framework for understanding rapid diffusion changes from 0 to 6 years of age is important in the detection of neurodevelopmental disorders. Purpose To quantify patterns of normal apparent diffusion coefficient (ADC) development from 0 to 6 years of age. Materials and Methods Previously constructed age-specific ADC atlases from 201 healthy full-term children (108 male; age range, 0-6 years) with MRI scans acquired from 2006 to 2013 at one large academic hospital were analyzed to quantify four patterns: ADC trajectory, rate of ADC change, age of ADC maturation, and hemispheric asymmetries of maturation ages. Patterns were quantified in whole-brain, segmented regional, and voxelwise levels by fitting a two-term exponential model. Hemispheric asymmetries in ADC maturation ages were assessed using t tests with Bonferroni correction. Results The posterior limb of the internal capsule (mean ADC: left hemisphere, 1.18 ×103μm2/sec; right hemisphere, 1.17 ×103μm2/sec), anterior limb of the internal capsule (left, 1.11 ×103μm2/sec; right, 1.09 ×103μm2/sec), vermis (1.26 ×103μm2/sec), thalami (left, 1.17 ×103μm2/sec; right, 1.15 ×103μm2/sec), and basal ganglia (left, 1.26 ×103μm2/sec; right, 1.23 ×103μm2/sec) demonstrate low initial ADC values, indicating an earlier prenatal time course of development. ADC maturation was completed between 1.3 and 2.4 years of age, depending on the region. The vermis and left thalamus matured earliest (1.3 years). The frontolateral gray matter matured latest (right, 2.3 years; left, 2.4 years). ADC maturation occurred earlier in the left hemisphere (P < .001) in several regions, including the frontal (mean ± standard deviation) (left, 2.16 years ± 0.29; right, 2.19 years ± 0.31), temporal (left, 1.93 years ± 0.22; right, 1.99 years ± 0.22), and parietal (left, 1.92 years ± 0.30; right, 2.03 years ± 0.28) white matter. Maturation occurred earlier in the right hemisphere (P < .001) in several regions, including the thalami (left, 1.63 years ± 0.32; right, 1.45 years ± 0.33), basal ganglia (left, 1.79 years ± 0.31; right, 1.70 years ± 0.37), and hippocampi (left, 1.93 years ± 0.34; right, 1.78 years ± 0.33). Conclusion Normative apparent diffusion coefficient developmental patterns on diffusion-weighted MRI scans were quantified in children aged 0 to 6 years. This work provides knowledge about early brain development and may guide the detection of abnormal patterns of maturation. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Rollins in this issue.

Nasopharyngeal carcinoma (NPC) is the most common malignant tumor of the nasopharynx. The delicate nature of the nasopharyngeal structures means that noninvasive magnetic resonance imaging (MRI) is the preferred diagnostic technique for NPC. However, NPC is a typically infiltrative tumor, usually with a small volume, and thus, it remains challenging to discriminate it from tightly connected surrounding tissues. To address this issue, this study proposes a voxel-wise discriminate method for locating and segmenting NPC from normal tissues in MRI sequences. The located NPC is refined to obtain its accurate segmentation results by an original multiviewed collaborative dictionary classification (CODL) model. The proposed CODL reconstructs a latent intact space and equips it with discriminative power for the collective multiview analysis task. Experiments on synthetic data demonstrate that CODL is capable of finding a discriminative space for multiview orthogonal data. We then evaluated the method on real NPC. Experimental results show that CODL could accurately discriminate and localize NPCs of different volumes. This method achieved superior performances in segmenting NPC compared with benchmark methods. Robust segmentation results show that CODL can effectively assist clinicians in locating NPC.