Multiscale Frame-Based Kernels for Large Deformation Diffeomorphic Metric Mapping

Cortical graph neural network for AD and MCI diagnosis and transfer learning across populations

Combining machine learning with neuroimaging data has a great potential for early diagnosis of mild cognitive impairment (MCI) and Alzheimer's disease (AD). However, it remains unclear how well the classifiers built on one population can predict MCI/AD diagnosis of other populations. This study aimed to employ a spectral graph convolutional neural network (graph-CNN), that incorporated cortical thickness and geometry, to identify MCI and AD based on 3089 T1-weighted MRI data of the ADNI-2 cohort, and to evaluate its feasibility to predict AD in the ADNI-1 cohort (n = 3602) and an Asian cohort (n = 347). For the ADNI-2 cohort, the graph-CNN showed classification accuracy of controls (CN) vs. AD at 85.8% and early MCI (EMCI) vs. AD at 79.2%, followed by CN vs. late MCI (LMCI) (69.3%), LMCI vs. AD (65.2%), EMCI vs. LMCI (60.9%), and CN vs. EMCI (51.8%). We demonstrated the robustness of the graph-CNN among the existing deep learning approaches, such as Euclidean-domain-based multilayer network and 1D CNN on cortical thickness, and 2D and 3D CNNs on T1-weighted MR images of the ADNI-2 cohort. The graph-CNN also achieved the prediction on the conversion of EMCI to AD at 75% and that of LMCI to AD at 92%. The find-tuned graph-CNN further provided a promising CN vs. AD classification accuracy of 89.4% on the ADNI-1 cohort and >90% on the Asian cohort. Our study demonstrated the feasibility to transfer AD/MCI classifiers learned from one population to the other. Notably, incorporating cortical geometry in CNN has the potential to improve classification performance.

Cerebellar development and its mediation role in cognitive planning in childhood

Recent evidence suggests that the cerebellum contributes not only to the planning and execution of movement but also to the high-order cognitive planning. Childhood is a critical period for development of the cerebellum and cognitive planning. This study aimed (a) to examine the development of cerebellar morphology and microstructure and (b) to examine the cerebellar mediation roles in the relationship between age and cognitive planning in 6- to 10-year-old children (n = 126). We used an anatomical parcellation to quantify cerebellar regional gray matter (GM) and white matter (WM) volumes, and WM microstructure, including fractional anisotropy (FA) and mean diffusivity (MD). We assessed planning ability using the Stockings of Cambridge (SOC) task in all children. We revealed (a) a measure-specific anterior-to-posterior gradient of the cerebellar development in childhood, that is, smaller GM volumes and greater WM FA of the anterior segment of the cerebellum but larger GM volumes and lower WM FA in the posterior segment of the cerebellum in older children; (b) an age-related improvement of the SOC performance at the most demanding level of five-move problems; and (c) a mediation role of the lateral cerebellar WM volumes in age-related improvement in the SOC performance in childhood. These results highlight the differential development of the cerebellum during childhood and provide evidence that brain adaptation to the acquisition of planning ability during childhood could partially be achieved through the engagement of the lateral cerebellum.