A simulation-driven supervised learning framework to estimate brain microstructure using diffusion MRI.

We propose a framework to train supervised learning models on synthetic data to estimate brain microstructure parameters using diffusion magnetic resonance imaging (dMRI). Although further validation is necessary, the proposed framework aims to seamlessly incorporate realistic simulations into dMRI microstructure estimation. Synthetic data were generated from over 1,000 neuron meshes converted from digital neuronal reconstructions and linked to their neuroanatomical parameters (such as soma volume and neurite length) using an optimized diffusion MRI simulator that produces intracellular dMRI signals from the solution of the Bloch-Torrey partial differential equation. By combining random subsets of simulated neuron signals with a free diffusion compartment signal, we constructed a synthetic dataset containing dMRI signals and 40 tissue microstructure parameters of 1.45 million artificial brain voxels. To implement supervised learning models we chose multilayer perceptrons (MLPs) and trained them on a subset of the synthetic dataset to estimate some microstructure parameters, namely, the volume fractions of soma, neurites, and the free diffusion compartment, as well as the area fractions of soma and neurites. The trained MLPs perform satisfactorily on the synthetic test sets and give promising in-vivo parameter maps on the MGH Connectome Diffusion Microstructure Dataset (CDMD). Most importantly, the estimated volume fractions showed low dependence on the diffusion time, the diffusion time independence of the estimated parameters being a desired property of quantitative microstructure imaging. The synthetic dataset we generated will be valuable for the validation of models that map between the dMRI signals and microstructure parameters. The surface meshes and microstructures parameters of the aforementioned neurons have been made publicly available.

Incorporating interface permeability into the diffusion MRI signal representation while using impermeable Laplace eigenfunctions.

Objective. The complex-valued transverse magnetization due to diffusion-encoding magnetic field gradients acting on a permeable medium can be modeled by the Bloch-Torrey partial differential equation. The diffusion magnetic resonance imaging (MRI) signal has a representation in the basis of the Laplace eigenfunctions of the medium. However, in order to estimate the permeability coefficient from diffusion MRI data, it is desirable that the forward solution can be calculated efficiently for many values of permeability.Approach. In this paper we propose a new formulation of the permeable diffusion MRI signal representation in the basis of the Laplace eigenfunctions of the same medium where the interfaces are made impermeable.Main results.We proved the theoretical equivalence between our new formulation and the original formulation in the case that the full eigendecomposition is used. We validated our method numerically and showed promising numerical results when a partial eigendecomposition is used. Two diffusion MRI sequences were used to illustrate the numerical validity of our new method.Significance.Our approach means that the same basis (the impermeable set) can be used for all permeability values, which reduces the computational time significantly, enabling the study of the effects of the permeability coefficient on the diffusion MRI signal in the future.

Trend in health-related physical fitness for Chinese male first-year college students: 2013-2019.

Introduction: Physical fitness is a health indicator contributing to the prevention of non-communicable diseases that threaten public health. Studies across a number of global populations indicate that physical fitness is generally declining. This study investigated the trend in physical fitness of Chinese male first-year college students from 2013 to 2019 to offer critical information for fostering individual and public health. Methods: This study used archival data and a natural experiment design capturing 4 years of data prior to implementation of the Healthy China 2030 initiative and 3 years following. Physical fitness tests were based on the Chinese national student physical fitness standards for males including body mass index, vital capacity, standing-long-jump, sit-and-reach, pull-ups, 50 m sprint, and 1,000 m run. Because the physical fitness tests set different standards for males and females, female data will be reported separately. Data from a total of 3,185 Chinese male first-year college students from a private university in Hebei Province of China were included in the study. A one-way multivariate analysis of variance was used for analyzing the research data. Results: The results indicated an overall significant difference in health-related physical fitness of Chinese male first-year college students, with scores on health indicators generally declining from 2013 to 2019. Despite improvement on some fitness variables in some years, performance on virtually all indicators was diminished compared to baseline years. Discussion: These findings can contribute to the existing global literature in the field of public health showing general declines in physical fitness. Chinese universities have the opportunity to support Healthy China 2030 goals and cultivate individuals' physical fitness by offering physical education course that encourage college students to participate in moderate-to-vigorous-intensity physical activities in order to support physical fitness development.