Chronological age of healthy people is able to be predicted accurately using deep neural networks from neuroimaging data, and the predicted brain age could serve as a biomarker for detecting aging-related diseases. In this paper, a novel 3D convolutional network, called two-stage-age-network (TSAN), is proposed to estimate brain age from T1-weighted MRI data. Compared with existing methods, TSAN has the following improvements. First, TSAN uses a two-stage cascade network architecture, where the first-stage network estimates a rough brain age, then the second-stage network estimates the brain age more accurately from the discretized brain age by the first-stage network. Second, to our knowledge, TSAN is the first work to apply novel ranking losses in brain age estimation, together with the traditional mean square error (MSE) loss. Third, densely connected paths are used to combine feature maps with different scales. The experiments with 6586 MRIs showed that TSAN could provide accurate brain age estimation, yielding mean absolute error (MAE) of 2.428 and Pearson’s correlation coefficient (PCC) of 0.985, between the estimated and chronological ages. Furthermore, using the brain age gap between brain age and chronological age as a biomarker, Alzheimer’s disease (AD) and Mild Cognitive Impairment (MCI) can be distinguished from healthy control (HC) subjects by support vector machine (SVM). Classification AUC in AD/HC and MCI/HC was 0.904 and 0.823, respectively. It showed that brain age gap is an effective biomarker associated with risk of dementia, and has potential for early-stage dementia risk screening. The codes and trained models have been released on GitHub: https://github.com/Milan-BUAA/TSAN-brain-age-estimation .

The accurate evaluation of operators’ mental workload in human-machine systems plays an important role in ensuring the correct execution of tasks and the safety of operators. However, the performance of cross-task mental workload evaluation based on physiological metrics remains unsatisfactory. To explore the changes in dynamic functional connectivity properties with varying mental workload in different tasks, four mental workload tasks with different types of information were designed and a newly proposed dynamic brain network analysis method based on EEG microstate was applied in this paper. Six microstate topographies labeled as Microstate A-F were obtained to describe the task-state EEG dynamics, which was highly consistent with previous studies. Dynamic brain network analysis revealed that 15 nodes and 68 pairs of connectivity from the Frontal-Parietal region were sensitive to mental workload in all four tasks, indicating that these nodal metrics had potential to effectively evaluate mental workload in the cross-task scenario. The characteristic path length of Microstate D brain network in both Theta and Alpha bands decreased whereas the global efficiency increased significantly when the mental workload became higher, suggesting that the cognitive control network of brain tended to have higher function integration property under high mental workload state. Furthermore, by using a SVM classifier, an averaged classification accuracy of 95.8% for within-task and 80.3% for cross-task mental workload discrimination were achieved. Results implies that it is feasible to evaluate the cross-task mental workload using the dynamic functional connectivity metrics under specific microstate, which provided a new insight for understanding the neural mechanism of mental workload with different types of information.

Objective This study aims to investigate the associations of glymphatic system with the presence, severity and neuroimaging phenotypes of cerebral small vessel disease (CSVD) in a community-based population. Method This report included 2219 community-dwelling people aged 50–75 years who participated in the PolyvasculaR Evaluation for Cognitive Impairment and vaScular Events cohort. The diffusivity along perivascular spaces based on diffusion tensor imaging (DTI-ALPS index) was measured to assess glymphatic pathway. The presence and severity of CSVD were estimated using a CSVD score (points from 0 to 4) and a modified CSVD score (points from 0 to 4), which were driven by 4 neuroimaging features of CSVD, including white matter hyperintensity (WMH), enlarged perivascular spaces (EPVS), lacunes, cerebral microbleeds. Brain atrophy (BA) was also evaluated. Binary or ordinal logistic regression analyses were carried out to investigate the relationships of DTI-ALPS index with CSVD. Result The mean age was 61.3 (SD 6.6) years, and 1019 (45.9%) participants were men. The average DTI-ALPS index was 1.67±0.14. Individuals in the first quartile (Q1) of the DTI-ALPS index had higher risks of the presence of CSVD (OR 1.77, 95% CI 1.33 to 2.35, p<0.001), modified presence of CSVD (odds ratio (OR) 1.80, 95% CI 1.38 to 2.34, p<0.001), total burden of CSVD (common OR (cOR) 1.89, 95% CI 1.43 to 2.49, p<0.001) and modified total burden of CSVD (cOR 1.95, 95% CI 1.51 to 2.50, p<0.001) compared with those in the fourth quartile (Q4). Additionally, individuals in Q1 of the DTI-ALPS index had increased risks of WMH burden, modified WMH burden, lacunes, basal ganglia-EPVS and BA (all p<0.05). Conclusion A lower DTI-ALPS index underlay the presence, severity and typical neuroimaging markers of CSVD, implying that glymphatic impairment may interact with CSVD-related pathology in the general ageing population. Trial registration number NCT03178448.

Medical image segmentation methods normally perform poorly when there is a domain shift between training and testing data. Unsupervised Domain Adaptation (UDA) addresses the domain shift problem by training the model using both labeled data from the source domain and unlabeled data from the target domain. Source-Free UDA (SFUDA) was recently proposed for UDA without requiring the source data during the adaptation, due to data privacy or data transmission issues, which normally adapts the pre-trained deep model in the testing stage. However, in real clinical scenarios of medical image segmentation, the trained model is normally frozen in the testing stage. In this paper, we propose Fourier Visual Prompting (FVP) for SFUDA of medical image segmentation. Inspired by prompting learning in natural language processing, FVP steers the frozen pre-trained model to perform well in the target domain by adding a visual prompt to the input target data. In FVP, the visual prompt is parameterized using only a small amount of low-frequency learnable parameters in the input frequency space, and is learned by minimizing the segmentation loss between the predicted segmentation of the prompted target image and reliable pseudo segmentation label of the target image under the frozen model. To our knowledge, FVP is the first work to apply visual prompts to SFUDA for medical image segmentation. The proposed FVP is validated using three public datasets, and experiments demonstrate that FVP yields better segmentation results, compared with various existing methods.