MPIGAN: An end-to-end deep based generative framework for high-resolution magnetic particle imaging reconstruction.

BACKGROUND: Magnetic particle imaging (MPI) is a recently developed, non-invasive in vivo imaging technique to map the spatial distribution of superparamagnetic iron oxide nanoparticles (SPIONs) in animal tissues with high sensitivity and speed. It is a challenge to reconstruct images directly from the received signals of MPI device due to the complex physical behavior of the nanoparticles. System matrix and X-space are two commonly used MPI reconstruction methods, where the former is extremely time-consuming and the latter usually produces blurry images. PURPOSE: Currently, we proposed an end-to-end machine learning framework to reconstruct high-resolution MPI images from 1-D voltage signals directly and efficiently. METHODS: The proposed framework, which we termed "MPIGAN", was trained on a large MPI simulation dataset containing 291 597 pairs of high-resolution 2-D phantom images and each image's corresponding voltage signals, so that it was able to accurately capture the nonlinear relationship between the spatial distribution of SPIONs and the received voltage signal, and realized high-resolution MPI image reconstruction. RESULTS: Experiment results showed that, MPIGAN exhibited remarkable abilities in high-resolution MPI image reconstruction. MPIGAN outperformed the traditional methods of system matrix and X-space in recovering the fine-scale structure of magnetic nanoparticles' spatial distribution and achieving enhanced reconstruction performance in both visual effects and quantitative assessments. Moreover, even when the received signals were severely contaminated with noise, MPIGAN could still generate high-quality MPI images. CONCLUSION: Our study provides a promising AI solution for end-to-end, efficient, and high-resolution magnetic particle imaging reconstruction.

Equivalent processing of facial expression and identity by macaque visual system and task-optimized neural network.

Both the primate visual system and artificial deep neural network (DNN) models show an extraordinary ability to simultaneously classify facial expression and identity. However, the neural computations underlying the two systems are unclear. Here, we developed a multi-task DNN model that optimally classified both monkey facial expressions and identities. By comparing the fMRI neural representations of the macaque visual cortex with the best-performing DNN model, we found that both systems: (1) share initial stages for processing low-level face features which segregate into separate branches at later stages for processing facial expression and identity respectively, and (2) gain more specificity for the processing of either facial expression or identity as one progresses along each branch towards higher stages. Correspondence analysis between the DNN and monkey visual areas revealed that the amygdala and anterior fundus face patch (AF) matched well with later layers of the DNN's facial expression branch, while the anterior medial face patch (AM) matched well with later layers of the DNN's facial identity branch. Our results highlight the anatomical and functional similarities between macaque visual system and DNN model, suggesting a common mechanism between the two systems.

The default mode network is affected in the early stage of simian immunodeficiency virus infection: a longitudinal study.

Acquired immune deficiency syndrome infection can lead to cognitive dysfunction represented by changes in the default mode network. Most recent studies have been cross-sectional and thus have not revealed dynamic changes in the default mode network following acquired immune deficiency syndrome infection and antiretroviral therapy. Specifically, when brain imaging data at only one time point are analyzed, determining the duration at which the default mode network is the most effective following antiretroviral therapy after the occurrence of acquired immune deficiency syndrome. However, because infection times and other factors are often uncertain, longitudinal studies cannot be conducted directly in the clinic. Therefore, in this study, we performed a longitudinal study on the dynamic changes in the default mode network over time in a rhesus monkey model of simian immunodeficiency virus infection. We found marked changes in default mode network connectivity in 11 pairs of regions of interest at baseline and 10 days and 4 weeks after virus inoculation. Significant interactions between treatment and time were observed in the default mode network connectivity of regions of interest pairs area 31/V6.R and area 8/frontal eye field (FEF). L, area 8/FEF.L and caudal temporal parietal occipital area (TPOC).R, and area 31/V6.R and TPOC.L. ART administered 4 weeks after infection not only interrupted the progress of simian immunodeficiency virus infection but also preserved brain function to a large extent. These findings suggest that the default mode network is affected in the early stage of simian immunodeficiency virus infection and that it may serve as a potential biomarker for early changes in brain function and an objective indicator for making early clinical intervention decisions.

Dissociation and hierarchy of human visual pathways for simultaneously coding facial identity and expression.

Humans have an extraordinary ability to recognize facial expression and identity from a single face simultaneously and effortlessly, however, the underlying neural computation is not well understood. Here, we optimized a multi-task deep neural network to classify facial expression and identity simultaneously. Under various optimization training strategies, the best-performing model consistently showed 'share-separate' organization. The two separate branches of the best-performing model also exhibited distinct abilities to categorize facial expression and identity, and these abilities increased along the facial expression or identity branches toward high layers. By comparing the representational similarities between the best-performing model and functional magnetic resonance imaging (fMRI) responses in the human visual cortex to the same face stimuli, the face-selective posterior superior temporal sulcus (pSTS) in the dorsal visual cortex was significantly correlated with layers in the expression branch of the model, and the anterior inferotemporal cortex (aIT) and anterior fusiform face area (aFFA) in the ventral visual cortex were significantly correlated with layers in the identity branch of the model. Besides, the aFFA and aIT better matched the high layers of the model, while the posterior FFA (pFFA) and occipital facial area (OFA) better matched the middle and early layers of the model, respectively. Overall, our study provides a task-optimization computational model to better understand the neural mechanism underlying face recognition, which suggest that similar to the best-performing model, the human visual system exhibits both dissociated and hierarchical neuroanatomical organization when simultaneously coding facial identity and expression.

Sex differences in resting state network (RSN) functional connections with mild cognitive impairment (MCI) progression.

OBJECTIVE: Sex plays an important role in many diseases. The purpose of current study is to explore whether there are different lesion patterns in the RSN functional connections between males and females with MCI progression, and identify the differences in brain network changes due to sex. METHODS: Resting state fMRI data included 37 normal controls (NC), 39 early MCI (EMCI) patients and 37 late MCI (LMCI) patients were collected, and network model based on graph theory was performed to compare the differences of brain network at different stages caused by sex from three aspects: functional connectivity between ROIs, intra-functional connectivity within RSN and inter-functional connectivity between RSN and white matter (WM). RESULTS: Sex plays a role in the changes of RSN functional connectivity, including the default mode network (DMN), the sensory-motor network (SMN), the dorsal attention network (DAN) and the executive control network (CON). The female SMN is more vulnerable and the damage of functional connectivity between DAN and WM is more serious. CONCLUSIONS: There are different lesion patterns in the RSN functional connections between males and females in the progression of MCI, which suggests that we should take full account of sex differences when conducting MCI progress studies and developing more effective biomarkers to promote the progress of cognitive impairment and dementia.

Alteration of functional connectivity in patients with Alzheimer's disease revealed by resting-state functional magnetic resonance imaging.

The main symptom of patients with Alzheimer's disease is cognitive dysfunction. Alzheimer's disease is mainly diagnosed based on changes in brain structure. Functional connectivity reflects the synchrony of functional activities between non-adjacent brain regions, and changes in functional connectivity appear earlier than those in brain structure. In this study, we detected resting-state functional connectivity changes in patients with Alzheimer's disease to provide reference evidence for disease prediction. Functional magnetic resonance imaging data from patients with Alzheimer's disease were used to show whether particular white and gray matter areas had certain functional connectivity patterns and if these patterns changed with disease severity. In nine white and corresponding gray matter regions, correlations of normal cognition, early mild cognitive impairment, and late mild cognitive impairment with blood oxygen level-dependent signal time series were detected. Average correlation coefficient analysis indicated functional connectivity patterns between white and gray matter in the resting state of patients with Alzheimer's disease. Functional connectivity pattern variation correlated with disease severity, with some regions having relatively strong or weak correlations. We found that the correlation coefficients of five regions were 0.3-0.5 in patients with normal cognition and 0-0.2 in those developing Alzheimer's disease. Moreover, in the other four regions, the range increased to 0.45-0.7 with increasing cognitive impairment. In some white and gray matter areas, there were specific connectivity patterns. Changes in regional white and gray matter connectivity patterns may be used to predict Alzheimer's disease; however, detailed information on specific connectivity patterns is needed. All study data were obtained from the Alzheimer's Disease Neuroimaging Initiative Library of the Image and Data Archive Database.

Functional connectivity between white matter and gray matter based on fMRI for Alzheimer's disease classification.

INTRODUCTION: Alzheimer's disease (AD) is a chronic neurodegenerative disease that generally starts slowly and leads to deterioration over time. Finding biomarkers more effective to predict AD transition is important for clinical medicine. And current research indicated that the lesion regions occur in both gray matter (GM) and white matter (WM). METHODS: This paper extracted BOLD time series from WM and GM, combined WM and GM together for analysis, constructed functional connectivity (FC) of static (sWGFC) and dynamic (dWGFC) between WM and GM, as well as static (sGFC) and dynamic (dGFC) FC within GM in order to evaluate the methods and areas most useful as feature sets for distinguishing NC from AD. These features will be evaluated using support vector machine (SVM) classifiers. RESULTS: The FC constructed by WM BOLD time series based on fMRI showed widely differences between the AD group and NC group. In terms of the results of the classification, the performance of feature subsets selected from sWGFC was better than sGFC, and the performance of feature subsets selected from dWGFC was better than dGFC. Overall, the feature subsets selected from dWGFC was the best. CONCLUSION: These results indicated that there is a wide range of disconnection between WM and GM in AD, and association between WM and GM based on fMRI only is an effective strategy, and the FC between WM and GM could be a potential biomarker in the process of cognitive impairment and AD.