No abstract

Purpose To develop a new 3D generative adversarial network that is designed and optimized for the application of multimodal 3D neuroimaging synthesis. Methods We present a 3D conditional generative adversarial network (GAN) that uses spectral normalization and feature matching to stabilize the training process and ensure optimization convergence (called SC‐GAN). A self‐attention module was also added to model the relationships between widely separated image voxels. The performance of the network was evaluated on the data set from ADNI‐3, in which the proposed network was used to predict PET images, fractional anisotropy, and mean diffusivity maps from multimodal MRI. Then, SC‐GAN was applied on a multidimensional diffusion MRI experiment for superresolution application. Experiment results were evaluated by normalized RMS error, peak SNR, and structural similarity. Results In general, SC‐GAN outperformed other state‐of‐the‐art GAN networks including 3D conditional GAN in all three tasks across all evaluation metrics. Prediction error of the SC‐GAN was 18%, 24% and 29% lower compared to 2D conditional GAN for fractional anisotropy, PET and mean diffusivity tasks, respectively. The ablation experiment showed that the major contributors to the improved performance of SC‐GAN are the adversarial learning and the self‐attention module, followed by the spectral normalization module. In the superresolution multidimensional diffusion experiment, SC‐GAN provided superior predication in comparison to 3D Unet and 3D conditional GAN. Conclusion In this work, an efficient end‐to‐end framework for multimodal 3D medical image synthesis (SC‐GAN) is presented. The source code is also made available at https://github.com/Haoyulance/SC-GAN.

Image synthesis is one of the key applications of deep learning in neuroimaging, which enables shortening of the scan time and/or improve image quality; therefore, reducing the imaging cost and improving patient experience. Given the multi-modal and large-scale nature of neuroimaging data, the synthesis task is computationally challenging. 2D image synthesis networks do not take advantage of multi-dimensional spatial information and the 3D implementation has dimensionality problem, negatively affecting the network reliability. These limitations hinder the research and clinical applicability of deep learning-based neuroimaging synthesis. In this paper, we proposed a new network that is designed and optimized for the application of multi-modal 3D synthesis of neuroimaging data. The network is based on 3D conditional generative adversarial network (GAN), and employs spectral normalization and feature matching to stabilize the training process and ensure optimization convergence. We also added a self-attention module to model relationships between widely separated voxels. The performance of the network was evaluated by predicting positron emission tomography (PET) images, Fractional anisotropy (FA) and mean diffusivity (MD) maps from multi-modal magnetic resonance images (MRI) of 265 and 497 individuals correspondingly. The proposed network, called self-attention conditional GAN (SC-GAN), significantly outperformed conventional 2D conditional GAN and the 3D implementation, enabling robust 3D deep learning-based neuroimaging synthesis.

Reef sediments, the home for microbes with high abundances, provide an important source of carbonates and nutrients for the growth and maintenance of coral reefs. However, there is a lack of systematic research on the composition of microbial community in sediments of different coral reef sites and the effect of microbial functional capabilities on the coral reef ecosystem. In combination of biogeochemical measurements and metagenomics, we assessed microbial community compositions and functional diversity, as well as pro les of antibiotic resistance genes in surface sediments of 16 coral reef sites from the Xisha islands in the South China Sea. Reef sediment microbiomes are diverse and novel at lower taxonomic ranks, dominated by Proteobacteria and Planctomycetota. Most reef sediment bacteria potentially participate in biogeochemical cycling via oxidizing various organic and inorganic compounds as energy sources. High abundances of Proteobacteria (mostly Rhizobiales and Woeseiales) are metabolically exible and contain rhodopsin genes. Various classes of antibiotic resistance genes, hosted by diverse bacterial lineages, were identi ed to confer resistance to multidrug, aminoglycoside, and other antibiotics. Overall, by establishing a compressive microbial genome database, our ndings expanded the understanding of reef sediment microbial ecology and provided insights for their link to the coral reef ecosystem health.

To develop a weakly supervised 3D perivascular spaces (PVS) segmentation model that combines the filter-based image processing algorithm and the convolutional neural network. Methods: We present a weakly supervised learning method for PVS segmentation by combing a rule-based image processing approach Frangi filter with a canonical deep learning algorithm Unet using conditional random field theory. The weighted cross entropy loss function and the training patch selection were implemented for the optimization and to alleviate the class imbalance issue. The performance of the model was evaluated on the Human Connectome Project data. Results: The proposed method increases the true positive rate compared to the rule-based method and reduces the false positive rate by 36% in the weakly supervised training experiment and 39.4% in the supervised training experiment compared to Unet, which results in superior overall performance. In addition, by training the model on manually quality controlled and annotated data which includes the subjects with the presence of white matter hyperintensities, the proposed method differentiates between PVS and white matter hyperintensities, which reduces the false positive rate by 78.5% compared to weakly supervised trained model. Conclusions: Combing the filter-based image processing algorithm and the convolutional neural network algorithm could improve the model's segmentation accuracy, while reducing the training dependence on the large scale annotated PVS mask data by the trained physician. Compared to the filter-based image processing algorithm, the data driven PVS segmentation model using quality-controlled data as the training target could differentiate the white matter hyperintensity from PVS resulting low false positive rate.