Publications by authors named "Weili Lin"

352 Publications

S3Reg: Superfast Spherical Surface Registration Based on Deep Learning.

IEEE Trans Med Imaging 2021 Mar 30;PP. Epub 2021 Mar 30.

Cortical surface registration is an essential step and prerequisite for surface-based neuroimaging analysis. It aligns cortical surfaces across individuals and time points to establish cross-sectional and longitudinal cortical correspondences to facilitate neuroimaging studies. Though achieving good performance, available methods are either time consuming or not flexible to extend to multiple or high dimensional features. Considering the explosive availability of large-scale and multimodal brain MRI data, fast surface registration methods that can flexibly handle multimodal features are desired. In this study, we develop a Superfast Spherical Surface Registration (S3Reg) framework for the cerebral cortex. Leveraging an end-to-end unsupervised learning strategy, S3Reg offers great flexibility in the choice of input feature sets and output similarity measures for registration, and meanwhile reduces the registration time significantly. Specifically, we exploit the powerful learning capability of spherical Convolutional Neural Network (CNN) to directly learn the deformation fields in spherical space and implement diffeomorphic design with "scaling and squaring" layers to guarantee topology-preserving deformations. To handle the polar-distortion issue, we construct a novel spherical CNN model using three orthogonal Spherical U-Nets. Experiments are performed on two different datasets to align both adult and infant multimodal cortical features. Results demonstrate that our S3Reg shows superior or comparable performance with state-of-the-art methods, while improving the registration time from 1 min to 10 sec.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2021.3069645DOI Listing
March 2021

Genome assembly and transcriptome analysis provide insights into the antischistosome mechanism of Microtus fortis.

J Genet Genomics 2021 Feb 9. Epub 2021 Feb 9.

Bio-Med Big Data Center, CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai 200031, China; Shanghai Center for Bioinformation Technology, Shanghai Academy of Science and Technology, Shanghai 201203, China; Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou, 330106, China. Electronic address:

Microtus fortis is the only mammalian host that exhibits intrinsic resistance against Schistosoma japonicum infection. However, the underlying molecular mechanisms of this resistance are not yet known. Here, we performed the first de novo genome assembly of M. fortis, comprehensive gene annotation analysis, and evolution analysis. Furthermore, we compared the recovery rate of schistosomes, pathological changes, and liver transcriptomes between M. fortis and mice at different time points after infection. We observed that the time and type of immune response in M. fortis were different from those in mice. M. fortis activated immune and inflammatory responses on the 10th day post infection, such as leukocyte extravasation, antibody activation, Fc-gamma receptor-mediated phagocytosis, and the interferon signaling cascade, which played important roles in preventing the development of schistosomes. In contrast, an intense immune response occurred in mice at the late stages of infection and could not eliminate schistosomes. Infected mice suffered severe pathological injury and continuous decreases in cell cycle, lipid metabolism, and other functions. Our findings offer new insights into the intrinsic resistance mechanism of M. fortis against schistosome infection. The genome sequence also provides the basis for future studies of other important traits in M. fortis.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jgg.2020.11.009DOI Listing
February 2021

Aerosol Promotes Peroxyacetyl Nitrate Formation During Winter in the North China Plain.

Environ Sci Technol 2021 03 3;55(6):3568-3581. Epub 2021 Mar 3.

State Key Laboratory of Severe Weather & Key Laboratory for Atmospheric Chemistry of CMA, Institute of Atmospheric Composition, Chinese Academy of Meteorological Sciences, Beijing 100081, China.

Peroxyacetyl nitrate (PAN) is an important indicator for photochemical pollution, formed similar to ozone in the photochemistry of certain volatile organic compounds (VOCs) in the presence of nitrogen oxides, and has displayed surprisingly high concentrations during wintertime that were better correlated to particulate rather than ozone concentrations, for which the reasons remained unknown. In this study, wintertime observations of PAN, VOCs, PM, HONO, and various trace gases were investigated to find the relationship between aerosols and wintertime PAN formation. Wintertime photochemical pollution was affirmed by the high PAN concentrations (average: 1.2 ± 1.1 ppb, maximum: 7.1 ppb), despite low ozone concentrations. PAN concentrations were determined by its oxygenated VOC (OVOC) precursor concentrations and the NO/NO ratios and can be well parameterized based on the understanding of their chemical relationship. Data analysis and box modeling results suggest that PAN formation was mostly contributed by VOC aging processes involving OH oxidation or photolysis rather than ozonolysis pathways. Heterogeneous reactions on aerosols have supplied key photochemical oxidants such as HONO, which produced OH radicals upon photolysis, promoting OVOC formation and thereby enhancing PAN production, explaining the observed PM-OVOC-PAN intercorrelation. In turn, parts of these OVOCs might participate in the formation of secondary organic aerosol, further aggravating haze pollution as a feedback. Low wintertime temperatures enable the long-range transport of PAN to downwind regions, and how that will impact their oxidation capacity and photochemical pollution requires further assessment in future studies.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1021/acs.est.0c08157DOI Listing
March 2021

Semi-supervised Transfer Learning for Infant Cerebellum Tissue Segmentation.

Mach Learn Med Imaging 2020 Oct 29;12436:663-673. Epub 2020 Sep 29.

Department of Radiology and Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, USA.

To characterize early cerebellum development, accurate segmentation of the cerebellum into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) tissues is one of the most pivotal steps. However, due to the weak tissue contrast, extremely folded tiny structures, and severe partial volume effect, infant cerebellum tissue segmentation is especially challenging, and the manual labels are hard to obtain and correct for learning-based methods. To the best of our knowledge, there is no work on the cerebellum segmentation for infant subjects less than 24 months of age. In this work, we develop a semi-supervised transfer learning framework guided by a confidence map for tissue segmentation of cerebellum MR images from 24-month-old to 6-month-old infants. Note that only 24-month-old subjects have reliable manual labels for training, due to their high tissue contrast. Through the proposed semi-supervised transfer learning, the labels from 24-month-old subjects are gradually propagated to the 18-, 12-, and 6-month-old subjects, which have a low tissue contrast. Comparison with the state-of-the-art methods demonstrates the superior performance of the proposed method, especially for 6-month-old subjects.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-59861-7_67DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7885085PMC
October 2020

Infant Cognitive Scores Prediction with Multi-stream Attention-Based Temporal Path Signature Features.

Med Image Comput Comput Assist Interv 2020 Oct 29;12267:134-144. Epub 2020 Sep 29.

Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, USA.

There is stunning rapid development of human brains in the first year of life. Some studies have revealed the tight connection between cognition skills and cortical morphology in this period. Nonetheless, it is still a great challenge to predict cognitive scores using brain morphological features, given issues like small sample size and missing data in longitudinal studies. In this work, for the first time, we introduce the path signature method to explore hidden analytical and geometric properties of longitudinal cortical morphology features. A novel BrainPSNet is proposed with a differentiable temporal path signature layer to produce informative representations of different time points and various temporal granules. Further, a two-stream neural network is included to combine groups of raw features and path signature features for predicting the cognitive score. More importantly, considering different influences of each brain region on the cognitive function, we design a learning-based attention mask generator to automatically weight regions correspondingly. Experiments are conducted on an in-house longitudinal dataset. By comparing with several recent algorithms, the proposed method achieves the state-of-the-art performance. The relationship between morphological features and cognitive abilities is also analyzed.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-59728-3_14DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7882905PMC
October 2020

Unsupervised Learning for Spherical Surface Registration.

Mach Learn Med Imaging 2020 Oct 29;12436:373-383. Epub 2020 Sep 29.

Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.

Current spherical surface registration methods achieve good performance on alignment and spatial normalization of cortical surfaces across individuals in neuroimaging analysis. However, they are computationally intensive, since they have to optimize an objective function independently for each pair of surfaces. In this paper, we present a fast learning-based algorithm that makes use of the recent development in spherical Convolutional Neural Networks (CNNs) for spherical cortical surface registration. Given a set of surface pairs without supervised information such as ground truth deformation fields or anatomical landmarks, we formulate the registration as a parametric function and learn its parameters by enforcing the feature similarity between one surface and the other one warped by the estimated deformation field using the function. Then, given a new pair of surfaces, we can quickly infer the spherical deformation field registering one surface to the other one. We model this parametric function using three orthogonal Spherical U-Nets and use spherical transform layers to warp the spherical surfaces, while imposing smoothness constraints on the deformation field. All the layers in the network are well-defined and differentiable, thus the parameters can be effectively learned. We show that our method achieves accurate cortical alignment results on 102 subjects, comparable to two state-of-the-art methods: Spherical Demons and MSM, while runs much faster.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-59861-7_38DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7871893PMC
October 2020

A Deep Spatial Context Guided Framework for Infant Brain Subcortical Segmentation.

Med Image Comput Comput Assist Interv 2020 Oct 29;12267:646-656. Epub 2020 Sep 29.

Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.

Accurate subcortical segmentation of infant brain magnetic resonance (MR) images is crucial for studying early subcortical structural growth patterns and related diseases diagnosis. However, dynamic intensity changes, low tissue contrast, and small subcortical size of infant brain MR images make subcortical segmentation a challenging task. In this paper, we propose a spatial context guided, coarse-to-fine deep convolutional neural network (CNN) based framework for accurate infant subcortical segmentation. At the coarse stage, we propose a signed distance map (SDM) learning UNet (SDM-UNet) to predict SDMs from the original multi-modal images, including T1w, T2w, and T1w/T2w images. By doing this, the spatial context information, including the relative position information across different structures and the shape information of the segmented structures contained in the ground-truth SDMs, is used for supervising the SDM-UNet to remedy the bad influence from the low tissue contrast in infant brain MR images and generate high-quality SDMs. To improve the robustness to outliers, a Correntropy based loss is introduced in SDM-UNet to penalize the difference between the ground-truth SDMs and predicted SDMs in training. At the fine stage, the predicted SDMs, which contains spatial context information of subcortical structures, are combined with the multi-modal images, and then fed into a multi-source and multi-path UNet (M2-UNet) for delivering refined segmentation. We validate our method on an infant brain MR image dataset with 24 scans by evaluating the Dice ratio between our segmentation and the manual delineation. Compared to four state-of-the-art methods, our method consistently achieves better performances in both qualitative and quantitative evaluations.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-59728-3_63DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7868770PMC
October 2020

Multi-Site Infant Brain Segmentation Algorithms: The iSeg-2019 Challenge.

IEEE Trans Med Imaging 2021 Jan 28;PP. Epub 2021 Jan 28.

To better understand early brain development in health and disorder, it is critical to accurately segment infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF). Deep learning-based methods have achieved state-of-the-art performance; however, one of the major limitations is that the learning-based methods may suffer from the multi-site issue, that is, the models trained on a dataset from one site may not be applicable to the datasets acquired from other sites with different imaging protocols/scanners. To promote methodological development in the community, the iSeg-2019 challenge (http://iseg2019.web.unc.edu) provides a set of 6-month infant subjects from multiple sites with different protocols/scanners for the participating methods. Training/validation subjects are from UNC (MAP) and testing subjects are from UNC/UMN (BCP), Stanford University, and Emory University. By the time of writing, there are 30 automatic segmentation methods participated in the iSeg-2019. In this article, 8 top-ranked methods were reviewed by detailing their pipelines/implementations, presenting experimental results, and evaluating performance across different sites in terms of whole brain, regions of interest, and gyral landmark curves. We further pointed out their limitations and possible directions for addressing the multi-site issue. We find that multi-site consistency is still an open issue. We hope that the multi-site dataset in the iSeg-2019 and this review article will attract more researchers to address the challenging and critical multi-site issue in practice.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2021.3055428DOI Listing
January 2021

Anomalous Phylogenetic Behavior of Ribosomal Proteins in Metagenome-Assembled Asgard Archaea.

Genome Biol Evol 2021 Jan;13(1)

Institute for Molecular Evolution, Heinrich Heine University Düsseldorf, Germany.

Metagenomic studies permit the exploration of microbial diversity in a defined habitat, and binning procedures enable phylogenomic analyses, taxon description, and even phenotypic characterizations in the absence of morphological evidence. Such lineages include asgard archaea, which were initially reported to represent archaea with eukaryotic cell complexity, although the first images of such an archaeon show simple cells with prokaryotic characteristics. However, these metagenome-assembled genomes (MAGs) might suffer from data quality problems not encountered in sequences from cultured organisms due to two common analytical procedures of bioinformatics: assembly of metagenomic sequences and binning of assembled sequences on the basis of innate sequence properties and abundance across samples. Consequently, genomic sequences of distantly related taxa, or domains, can in principle be assigned to the same MAG and result in chimeric sequences. The impacts of low-quality or chimeric MAGs on phylogenomic and metabolic prediction remain unknown. Debates that asgard archaeal data are contaminated with eukaryotic sequences are overshadowed by the lack of evidence indicating that individual asgard MAGs stem from the same chromosome. Here, we show that universal proteins including ribosomal proteins of asgard archaeal MAGs fail to meet the basic phylogenetic criterion fulfilled by genome sequences of cultured archaea investigated to date: These proteins do not share common evolutionary histories to the same extent as pure culture genomes do, pointing to a chimeric nature of asgard archaeal MAGs. Our analysis suggests that some asgard archaeal MAGs represent unnatural constructs, genome-like patchworks of genes resulting from assembly and/or the binning process.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/gbe/evaa238DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7813640PMC
January 2021

Spherical Deformable U-Net: Application to Cortical Surface Parcellation and Development Prediction.

IEEE Trans Med Imaging 2021 Apr 1;40(4):1217-1228. Epub 2021 Apr 1.

Convolutional Neural Networks (CNNs) have achieved overwhelming success in learning-related problems for 2D/3D images in the Euclidean space. However, unlike in the Euclidean space, the shapes of many structures in medical imaging have an inherent spherical topology in a manifold space, e.g., the convoluted brain cortical surfaces represented by triangular meshes. There is no consistent neighborhood definition and thus no straightforward convolution/pooling operations for such cortical surface data. In this paper, leveraging the regular and hierarchical geometric structure of the resampled spherical cortical surfaces, we create the 1-ring filter on spherical cortical triangular meshes and accordingly develop convolution/pooling operations for constructing Spherical U-Net for cortical surface data. However, the regular nature of the 1-ring filter makes it inherently limited to model fixed geometric transformations. To further enhance the transformation modeling capability of Spherical U-Net, we introduce the deformable convolution and deformable pooling to cortical surface data and accordingly propose the Spherical Deformable U-Net (SDU-Net). Specifically, spherical offsets are learned to freely deform the 1-ring filter on the sphere to adaptively localize cortical structures with different sizes and shapes. We then apply the SDU-Net to two challenging and scientifically important tasks in neuroimaging: cortical surface parcellation and cortical attribute map prediction. Both applications validate the competitive performance of our approach in accuracy and computational efficiency in comparison with state-of-the-art methods.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2021.3050072DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8016713PMC
April 2021

Multi-Regression based supervised sample selection for predicting baby connectome evolution trajectory from neonatal timepoint.

Med Image Anal 2021 02 17;68:101853. Epub 2020 Oct 17.

BASIRA lab, Faculty of Computer and Informatics, Istanbul Technical University, Istanbul, Turkey; School of Science and Engineering, Computing, University of Dundee, UK. Electronic address:

The connectional map of the baby brain undergoes dramatic changes over the first year of postnatal development, which makes its mapping a challenging task, let alone learning how to predict its evolution. Currently, learning models for predicting brain connectomic developmental trajectories remain broadly absent despite their great potential in spotting atypical neurodevelopmental disorders early. This is most likely due to the scarcity and often incompleteness of longitudinal infant neuroimaging studies for training such models. In this paper, we propose the first approach for progressively predicting longitudinal development of brain networks during the postnatal period solely from a baseline connectome around birth. To this end, a supervised multi-regression sample selection strategy is designed to learn how to identify the best set of neighbors of a testing baseline connectome to eventually predict its evolution trajectory at follow-up timepoints. However, given that the training dataset may have missing samples (connectomes) at certain timepoints, this may affect the training of the predictive model. To overcome this problem, we perform a low-rank tensor completion based on a robust principal component analysis to impute the missing training connectomes by linearly approximating similar complete training networks. In the prediction step, our sample selection strategy aims to preserve spatiotemporal relationships between consecutive timepoints. Therefore, the proposed method learns how to identify the set of the local closest neighbors to a target network by training an ensemble of bidirectional regressors leveraging temporal dependency between consecutive timepoints with a recall to the baseline observations to progressively predict the evolution of a testing network over time. Our method achieves the best prediction results and better captures the dynamic changes of each brain connectome over time in comparison to its ablated versions using leave-one-out cross-validation strategy.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.media.2020.101853DOI Listing
February 2021

The emergence of a functionally flexible brain during early infancy.

Proc Natl Acad Sci U S A 2020 09 31;117(38):23904-23913. Epub 2020 Aug 31.

Biomedical Research Imaging Center, The University of North Carolina at Chapel Hill, Chapel Hill, NC 27599;

Adult brains are functionally flexible, a unique characteristic that is thought to contribute to cognitive flexibility. While tools to assess cognitive flexibility during early infancy are lacking, we aimed to assess the spatiotemporal developmental features of "neural flexibility" during the first 2 y of life. Fifty-two typically developing children 0 to 2 y old were longitudinally imaged up to seven times during natural sleep using resting-state functional MRI. Using a sliding window approach, MR-derived neural flexibility, a quantitative measure of the frequency at which brain regions change their allegiance from one functional module to another during a given time period, was used to evaluate the temporal emergence of neural flexibility during early infancy. Results showed that neural flexibility of whole brain, motor, and high-order brain functional networks/regions increased significantly with age, while visual regions exhibited a temporally stable pattern, suggesting spatially and temporally nonuniform developmental features of neural flexibility. Additionally, the neural flexibility of the primary visual network at 3 mo of age was significantly and negatively associated with cognitive ability evaluated at 5/6 y of age. The "flexible club," comprising brain regions with neural flexibility significantly higher than whole-brain neural flexibility, were consistent with brain regions known to govern cognitive flexibility in adults and exhibited unique characteristics when compared to the functional hub and diverse club regions. Thus, MR-derived neural flexibility has the potential to reveal the underlying neural substrates for developing a cognitively flexible brain during early infancy.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1073/pnas.2002645117DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7519318PMC
September 2020

Regional transport and urban emissions are important ammonia contributors in Beijing, China.

Environ Pollut 2020 Oct 20;265(Pt A):115062. Epub 2020 Jun 20.

Environmental Meteorological Forecast Center of Beijing-Tianjin-Hebei, China Meteorological Administration, Beijing, 100089, China.

Measuring ammonia (NH) is important for understanding the role of NH in secondary aerosol formation and the atmospheric deposition of reactive N. In this study, NH was measured in an urban area, a background region, and a tunnel in Beijing. The average NH concentrations between September 2017 and August 2018 were 24.8 ± 14.8 ppb and 11.6 ± 10.3 ppb in the urban area and background region, respectively. Higher NH concentrations at both the urban and background sites, relative to some earlier measurements indicated a likely increase in the NH concentrations in these regions. The urban NH level in Beijing was much higher than that typically observed at urban and industrial sites in other domestic and foreign cities, suggesting that the Beijing urban area was affected by greater NH emissions than other regions. Based on the relationship among NH, wind direction, and wind speed, the urban area was affected by both local emissions and air transported from North China Plain (NCP). Potential source contribution function analyses suggested that regional transport from the NCP could greatly affect local concentrations of NH in both urban and background areas in spring and autumn; however, in addition to the NCP, urban emissions could also affect NH levels in the background region in summer and winter. The average NH concentration at the Fenshuiling Tunnel was 8.5 ± 7.7 ppb from December 2017 to February 2018. The NH:CO emission ratio measured in the tunnel test was 0.022 ± 0.038 ppb/ppb, which was lower than values in the USA and South Korea. The contribution of traffic to NH in Beijing did not agree well with the available emission inventories, suggesting that vehicular emissions were underestimated and further evaluation is necessary.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.envpol.2020.115062DOI Listing
October 2020

Disentangled-Multimodal Adversarial Autoencoder: Application to Infant Age Prediction With Incomplete Multimodal Neuroimages.

IEEE Trans Med Imaging 2020 12 30;39(12):4137-4149. Epub 2020 Nov 30.

Effective fusion of structural magnetic resonance imaging (sMRI) and functional magnetic resonance imaging (fMRI) data has the potential to boost the accuracy of infant age prediction thanks to the complementary information provided by different imaging modalities. However, functional connectivity measured by fMRI during infancy is largely immature and noisy compared to the morphological features from sMRI, thus making the sMRI and fMRI fusion for infant brain analysis extremely challenging. With the conventional multimodal fusion strategies, adding fMRI data for age prediction has a high risk of introducing more noises than useful features, which would lead to reduced accuracy than that merely using sMRI data. To address this issue, we develop a novel model termed as disentangled-multimodal adversarial autoencoder (DMM-AAE) for infant age prediction based on multimodal brain MRI. Specifically, we disentangle the latent variables of autoencoder into common and specific codes to represent the shared and complementary information among modalities, respectively. Then, cross-reconstruction requirement and common-specific distance ratio loss are designed as regularizations to ensure the effectiveness and thoroughness of the disentanglement. By arranging relatively independent autoencoders to separate the modalities and employing disentanglement under cross-reconstruction requirement to integrate them, our DMM-AAE method effectively restrains the possible interference cross modalities, while realizing effective information fusion. Taking advantage of the latent variable disentanglement, a new strategy is further proposed and embedded into DMM-AAE to address the issue of incompleteness of the multimodal neuroimages, which can also be used as an independent algorithm for missing modality imputation. By taking six types of cortical morphometric features from sMRI and brain functional connectivity from fMRI as predictors, the superiority of the proposed DMM-AAE is validated on infant age (35 to 848 days after birth) prediction using incomplete multimodal neuroimages. The mean absolute error of the prediction based on DMM-AAE reaches 37.6 days, outperforming state-of-the-art methods. Generally, our proposed DMM-AAE can serve as a promising model for prediction with multimodal data.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2020.3013825DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7773223PMC
December 2020

Hierarchical Nonlocal Residual Networks for Image Quality Assessment of Pediatric Diffusion MRI With Limited and Noisy Annotations.

IEEE Trans Med Imaging 2020 11 28;39(11):3691-3702. Epub 2020 Oct 28.

Fast and automated image quality assessment (IQA) of diffusion MR images is crucial for making timely decisions for rescans. However, learning a model for this task is challenging as the number of annotated data is limited and the annotation labels might not always be correct. As a remedy, we will introduce in this paper an automatic image quality assessment (IQA) method based on hierarchical non-local residual networks for pediatric diffusion MR images. Our IQA is performed in three sequential stages, i.e., 1) slice-wise IQA, where a nonlocal residual network is first pre-trained to annotate each slice with an initial quality rating (i.e., pass/questionable/fail), which is subsequently refined via iterative semi-supervised learning and slice self-training; 2) volume-wise IQA, which agglomerates the features extracted from the slices of a volume, and uses a nonlocal network to annotate the quality rating for each volume via iterative volume self-training; and 3) subject-wise IQA, which ensembles the volumetric IQA results to determine the overall image quality pertaining to a subject. Experimental results demonstrate that our method, trained using only samples of modest size, exhibits great generalizability, and is capable of conducting rapid hierarchical IQA with near-perfect accuracy.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2020.3002708DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7606371PMC
November 2020

Probing Tissue Microarchitecture of the Baby Brain via Spherical Mean Spectrum Imaging.

IEEE Trans Med Imaging 2020 11 28;39(11):3607-3618. Epub 2020 Oct 28.

During the first years of life, the human brain undergoes dynamic spatially-heterogeneous changes, invo- lving differentiation of neuronal types, dendritic arbori- zation, axonal ingrowth, outgrowth and retraction, synaptogenesis, and myelination. To better quantify these changes, this article presents a method for probing tissue microarchitecture by characterizing water diffusion in a spectrum of length scales, factoring out the effects of intra-voxel orientation heterogeneity. Our method is based on the spherical means of the diffusion signal, computed over gradient directions for a set of diffusion weightings (i.e., b -values). We decompose the spherical mean profile at each voxel into a spherical mean spectrum (SMS), which essentially encodes the fractions of spin packets undergoing fine- to coarse-scale diffusion proce- sses, characterizing restricted and hindered diffusion stemming respectively from intra- and extra-cellular water compartments. From the SMS, multiple orientation distribution invariant indices can be computed, allowing for example the quantification of neurite density, microscopic fractional anisotropy ( μ FA), per-axon axial/radial diffusivity, and free/restricted isotropic diffusivity. We show that these indices can be computed for the developing brain for greater sensitivity and specificity to development related changes in tissue microstructure. Also, we demonstrate that our method, called spherical mean spectrum imaging (SMSI), is fast, accurate, and can overcome the biases associated with other state-of-the-art microstructure models.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TMI.2020.3001175DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7688284PMC
November 2020

Corrigendum to "Antiapoptosis and Antifibrosis Effects of Granules on Heart Failure Rats via Hippo Pathway".

Biomed Res Int 2020 1;2020:8569251. Epub 2020 Jul 1.

School of Life Science, Beijing University of Chinese Medicine, Beijing 100029, China.

[This corrects the article DOI: 10.1155/2019/1642575.].
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1155/2020/8569251DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7368950PMC
July 2020

Young Brain - Big Appetite.

Authors:
Weili Lin

Ann Nutr Metab 2019 19;75 Suppl 1:5-6. Epub 2020 Jun 19.

Biomedical Research Imaging Center, University of North Carolina at Chapel Hill, Chapel Hill, North Carolina, USA,

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1159/000508056DOI Listing
June 2020

Development of Dynamic Functional Architecture during Early Infancy.

Cereb Cortex 2020 Oct;30(11):5626-5638

Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.

Uncovering the moment-to-moment dynamics of functional connectivity (FC) in the human brain during early development is crucial for understanding emerging complex cognitive functions and behaviors. To this end, this paper leveraged a longitudinal resting-state functional magnetic resonance imaging dataset from 51 typically developing infants and, for the first time, thoroughly investigated how the temporal variability of the FC architecture develops at the "global" (entire brain), "mesoscale" (functional system), and "local" (brain region) levels in the first 2 years of age. Our results revealed that, in such a pivotal stage, 1) the whole-brain FC dynamic is linearly increased; 2) the high-order functional systems tend to display increased FC dynamics for both within- and between-network connections, while the primary systems show the opposite trajectories; and 3) many frontal regions have increasing FC dynamics despite large heterogeneity in developmental trajectories and velocities. All these findings indicate that the brain is gradually reconfigured toward a more flexible, dynamic, and adaptive system with globally increasing but locally heterogeneous trajectories in the first 2 postnatal years, explaining why infants have rapidly developing high-order cognitive functions and complex behaviors.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/cercor/bhaa128DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7898958PMC
October 2020

Morphology of perivascular spaces and enclosed blood vessels in young to middle-aged healthy adults at 7T: Dependences on age, brain region, and breathing gas.

Neuroimage 2020 09 21;218:116978. Epub 2020 May 21.

Biomedical Research Imaging Center, Chapel Hill, NC, USA; Department of Radiology, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.

Perivascular spaces (PVSs) are fluid-filled spaces surrounding penetrating blood vessels in the brain and are an integral pathway of the glymphatic system. A PVS and the enclosed blood vessel are commonly visualized as a single vessel-like complex (denoted as PVSV) in high-resolution MRI images. Quantitative characterization of the PVSV morphology in MRI images in healthy subjects may serve as a reference for detecting disease related PVS and/or blood vessel alterations in patients with brain diseases. To this end, we evaluated the age dependences, spatial heterogeneities, and dynamic properties of PVSV morphological features in 45 healthy subjects (21-55 years old), using an ultra-high-resolution three-dimensional transverse relaxation time weighted MRI sequence (0.41 ​× ​0.41 ​× ​0.4 ​mm) at 7T. Quantitative PVSV parameters, including apparent diameter, count, volume fraction (VF), and relative contrast to noise ratio (rCNR) were calculated in the white matter and subcortical structures. Dynamic changes were induced by carbogen breathing which are known to induce vasodilation and increase the blood oxygenation level in the brain. PVSV count and VF significantly increased with age in basal ganglia (BG), so did rCNR in BG, midbrain, and white matter (WM). Apparent PVSV diameter also showed a positive association with age in the three brain regions, although it did not reach statistical significance. The PVSV VF and count showed large inter-subject variations, with coefficients of variation ranging from 0.17 to 0.74 after regressing out age and gender effects. Both apparent diameter and VF exhibited significant spatial heterogeneity, which cannot be explained solely by radio-frequency field inhomogeneities. Carbogen breathing significantly increased VF in BG and WM, and rCNR in thalamus, BG, and WM compared to air breathing. Our results are consistent with gradual dilation of PVSs with age in healthy adults. The PVSV morphology exhibited spatial heterogeneity and large inter-subject variations and changed during carbogen breathing compared to air breathing.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.neuroimage.2020.116978DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7485170PMC
September 2020

Real-Time Quality Assessment of Pediatric MRI via Semi-Supervised Deep Nonlocal Residual Neural Networks.

IEEE Trans Image Process 2020 May 8. Epub 2020 May 8.

In this paper, we introduce an image quality assessment (IQA) method for pediatric T1- and T2-weighted MR images. IQA is first performed slice-wise using a nonlocal residual neural network (NR-Net) and then volume-wise by agglomerating the slice QA results using random forest. Our method requires only a small amount of quality-annotated images for training and is designed to be robust to annotation noise that might occur due to rater errors and the inevitable mix of good and bad slices in an image volume. Using a small set of quality-assessed images, we pre-train NR-Net to annotate each image slice with an initial quality rating (i.e., pass, questionable, fail), which we then refine by semi-supervised learning and iterative self-training. Experimental results demonstrate that our method, trained using only samples of modest size, exhibit great generalizability, capable of real-time (milliseconds per volume) large-scale IQA with nearperfect accuracy.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TIP.2020.2992079DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7648726PMC
May 2020

Revealing Developmental Regionalization of Infant Cerebral Cortex Based on Multiple Cortical Properties.

Med Image Comput Comput Assist Interv 2019 Oct 10;11765:841-849. Epub 2019 Oct 10.

Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.

The human brain develops dynamically and regionally heterogeneously during the first two postnatal years. Cortical developmental regionalization, i.e., the landscape of cortical heterogeneity in development, reflects the organization of underlying microstructures, which are closely related to the functional principles of the cortex. Therefore, prospecting early cortical developmental regionalization can provide neurobiologically meaningful units for precise region localization, which will advance our understanding on brain development in this critical period. However, due to the absence of dedicated computational tools and large-scale datasets, our knowledge on early cortical developmental regionalization still remains intact. To fill both the methodological and knowledge gaps, we propose to explore the cortical developmental regionalization using a novel method based on nonnegative matrix factorization (NMF), due to its ability in analyzing complex high-dimensional data by representing data using several bases in a data-driven way. Specifically, a novel multi-view NMF (MV-NMF) method is proposed, in which multiple distinct and complementary cortical properties (i.e., multiple views) are jointly considered to provide comprehensive observation of cortical regionalization process. To ensure the sparsity of the discovered regions, an orthogonal constraint defined in Stiefel manifold is imposed in our MV-NMF method. Meanwhile, a graph-induced constraint is also included to improve the compactness of the discovered regions. Capitalizing on an unprecedentedly large dataset with 1,560 longitudinal MRI scans from 887 infants, we delineate the first neurobiologically meaningful representation of early cortical regionalization, providing a valuable reference for brain development studies.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-32245-8_93DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7079741PMC
October 2019

Deep Granular Feature-Label Distribution Learning for Neuroimaging-based Infant Age Prediction.

Med Image Comput Comput Assist Interv 2019 Oct 10;11767:149-157. Epub 2019 Oct 10.

Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, 27599, USA.

Neuroimaging-based infant age prediction is important for brain development analysis but often suffers insufficient data. To address this challenge, we introduce label distribution learning (LDL), a popular machine learning paradigm focusing on the small sample problem, for infant age prediction. As directly applying LDL yields dramatically increased number of day-to-day age labels and also extremely scarce data describing each label, we propose a new strategy, called granular label distribution (GLD). Particularly, by assembling the adjacent labels to granules and designing granular distributions, GLD makes each brain MRI contribute to not only its own age but also its neighboring ages at a scale, which effectively keeps the information augmentation superiority of LDL and reduces the number of labels. Furthermore, to extremely augment the information supplied by the small data, we propose a novel method named (GFD). GFD leverages the variability of the brain images at the same age, thus significantly increasing the learning effectiveness. Moreover, deep neural network is exploited to approximate the GLD. These strategies constitute a new model: deep granular feature-label distribution learning (DGFLDL). By taking 8 types of cortical morphometric features from structural MRI as predictors, the proposed DGFLDL is validated on infant age prediction using 384 brain MRI scans from 35 to 848 days after birth. Our proposed method, approaching the mean absolute error as 36.1 days, significantly outperforms the baseline methods. Besides, the permutation importance analysis of features based on our method reveals important biomarkers of infant brain development.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-32251-9_17DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7074927PMC
October 2019

Spherical U-Net on Cortical Surfaces: Methods and Applications.

Inf Process Med Imaging 2019 Jun 22;11492:855-866. Epub 2019 May 22.

Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.

Convolutional Neural Networks (CNNs) have been providing the state-of-the-art performance for learning-related problems involving 2D/3D images in Euclidean space. However, unlike in the Euclidean space, the shapes of many structures in medical imaging have a spherical topology in a manifold space, e.g., brain cortical or subcortical surfaces represented by triangular meshes, with large inter-subject and intra-subject variations in vertex number and local connectivity. Hence, there is no consistent neighborhood definition and thus no straightforward convolution/transposed convolution operations for cortical/subcortical surface data. In this paper, by leveraging the regular and consistent geometric structure of the resampled cortical surface mapped onto the spherical space, we propose a novel convolution filter analogous to the standard convolution on the image grid. Accordingly, we develop corresponding operations for convolution, pooling, and transposed convolution for spherical surface data and thus construct spherical CNNs. Specifically, we propose the Spherical U-Net architecture by replacing all operations in the standard U-Net with their spherical operation counterparts. We then apply the Spherical U-Net to two challenging and neuroscientifically important tasks in infant brains: cortical surface parcellation and cortical attribute map development prediction. Both applications demonstrate the competitive performance in the accuracy, computational efficiency, and effectiveness of our proposed Spherical U-Net, in comparison with the state-of-the-art methods.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-20351-1_67DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7074928PMC
June 2019

RCA-U-Net: Residual Channel Attention U-Net for Fast Tissue Quantification in Magnetic Resonance Fingerprinting.

Med Image Comput Comput Assist Interv 2019 Oct 10;11766:101-109. Epub 2019 Oct 10.

Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC 27599, USA.

Magnetic resonance fingerprinting (MRF) is a relatively new imaging framework which allows rapid and simultaneous quantification of multiple tissue properties, such as T1 and T2 relaxation times, in one acquisition. To accelerate the data sampling in MRF, a variety of methods have been proposed to extract tissue properties from highly accelerated MRF signals. While these methods have demonstrated promising results, further improvement in the accuracy, especially for T2 quantification, is needed. In this paper, we present a novel deep learning approach, namely residual channel attention U-Net (RCA-U-Net), to perform the tissue quantification task in MRF. The RCA-U-Net combines the U-Net structure with residual channel attention blocks, to make the network focus on more informative features and produce better quantification results. In addition, we improved the preprocessing of MRF data by masking out the noisy signals in the background for improved quantification at tissue boundaries. Our experimental results on two brain datasets with different spatial resolutions demonstrate that the proposed method improves the accuracy of T2 quantification with MRF under high acceleration rates (i.e., 8 and 16) as compared to the state-of-the-art methods.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-32248-9_12DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7065675PMC
October 2019

Pilot Study of [F] Fluorodeoxyglucose Positron Emission Tomography (FDG-PET)/Magnetic Resonance Imaging (MRI) for Staging of Muscle-invasive Bladder Cancer (MIBC).

Clin Genitourin Cancer 2020 10 6;18(5):378-386.e1. Epub 2020 Mar 6.

Division of Hematology/Oncology, Department of Medicine, University of North Carolina School of Medicine, Chapel Hill, NC; Lineberger Comprehensive Cancer Center, University of North Carolina, Chapel Hill, NC. Electronic address:

Introduction: Computed tomography (CT) has limited diagnostic accuracy for staging of muscle-invasive bladder cancer (MIBC). [F] Fluorodeoxyglucose positron emission tomography (FDG-PET)/magnetic resonance imaging (MRI) is a novel imaging modality incorporating functional imaging with improved soft tissue characterization. This pilot study evaluated the use of preoperative FDG-PET/MRI for staging of MIBC.

Patients And Methods: Twenty-one patients with MIBC with planned radical cystectomy were enrolled. Two teams of radiologists reviewed FDG-PET/MRI scans to determine: (1) presence of primary bladder tumor; and (2) lymph node involvement and distant metastases. FDG-PET/MRI was compared with cystectomy pathology and computed tomography (CT).

Results: Eighteen patients were included in the final analysis, most (72.2%) of whom received neoadjuvant chemotherapy. Final pathology revealed 10 (56%) patients with muscle invasion and only 3 (17%) patients with lymph node involvement. Clustered analysis of FDG-PET/MRI radiology team reads revealed a sensitivity of 0.80 and a specificity of 0.56 for detection of the primary tumor with a sensitivity of 0 and a specificity of 1.00 for detection of lymph node involvement when compared with cystectomy pathology. CT imaging demonstrated similar rates in evaluation of the primary tumor (sensitivity, 0.91; specificity, 0.43) and lymph node involvement (sensitivity, 0; specificity, 0.93) when compared with pathology.

Conclusions: This pilot single-institution experience of FDG-PET/MRI for preoperative staging of MIBC performed similar to CT for the detection of the primary tumor; however, the determination of lymph node status was limited by few patients with true pathologic lymph node involvement. Further studies are needed to evaluate the potential role for FDG-PET/MRI in the staging of MIBC.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.clgc.2020.02.008DOI Listing
October 2020

Harmonization of Infant Cortical Thickness Using Surface-to-Surface Cycle-Consistent Adversarial Networks.

Med Image Comput Comput Assist Interv 2019 Oct 10;11767:475-483. Epub 2019 Oct 10.

Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, NC, USA.

Increasing multi-site infant neuroimaging datasets are facilitating the research on understanding early brain development with larger sample size and bigger statistical power. However, a joint analysis of cortical properties (e.g., cortical thickness) is unavoidably facing the problem of non-biological variance introduced by differences in MRI scanners. To address this issue, in this paper, we propose cycle-consistent adversarial networks based on spherical cortical surface to harmonize cortical thickness maps between different scanners. We combine the spherical U-Net and CycleGAN to construct a surface-to-surface CycleGAN (S2SGAN). Specifically, we model the harmonization from scanner to scanner as a surface-to-surface translation task. The first goal of harmonization is to learn a mapping : → such that the distribution of surface thickness maps from () is indistinguishable from . Since this mapping is highly under-constrained, with the second goal of harmonization to preserve individual differences, we utilize the inverse mapping : and the cycle consistency loss to enforce ( ()) (and vice versa). Furthermore, we incorporate the correlation coefficient loss to guarantee the structure consistency between the original and the generated surface thickness maps. Quantitative evaluation on both synthesized and real infant cortical data demonstrates the superior ability of our method in removing unwanted scanner effects and preserving individual differences simultaneously, compared to the state-of-the-art methods.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-32251-9_52DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7052700PMC
October 2019

Intrinsic Patch-Based Cortical Anatomical Parcellation Using Graph Convolutional Neural Network on Surface Manifold.

Med Image Comput Comput Assist Interv 2019 Oct 10;11766:492-500. Epub 2019 Oct 10.

Department of Radiology and BRIC, University of North Carolina at Chapel Hill, Chapel Hill, USA.

Automatic parcellation of cortical surfaces into anatomically meaningful regions of interest (ROIs) is of great importance in brain analysis. Due to the complex shape of the convoluted cerebral cortex, conventional methods generally require three steps to obtain the parcellations. , the original cortical surface is iteratively inflated and mapped onto a spherical surface with minimal metric distortion, for providing a simpler shape for analysis. , a registration or learning-based labeling method is adopted to parcellate ROIs on the mapped spherical surface. , parcellation labels on the spherical surface are mapped back to the original cortical surface. Despite great success, spherical mapping of the original cortical surface is inherently sensitive to topological noise and cannot deal with the impaired brains that violate spherical topology. To address these issues, in this paper, we propose to directly parcellate the cerebral cortex on the original cortical surface manifold without requiring spherical mapping, by leveraging the strong learning ability of the graph convolutional neural networks. Also, we extend the convolution to the surface manifold using the kernel strategy, which enables us to over-come the notorious shape difference issue (e.g., different vertex number and connections) across different subjects. Our method aims to learn the highly nonlinear mapping between cortical attribute patterns (on local intrinsic surface patches) and parcellation labels. We have validated our method on a normal cortical surface dataset and a synthetic dataset with impaired brains, which shows that our method achieves comparable accuracy to the methods using spherical mapping, and works well on cortical surfaces violating the spherical topology.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-32248-9_55DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7052684PMC
October 2019

Surface-Volume Consistent Construction of Longitudinal Atlases for the Early Developing Brain.

Med Image Comput Comput Assist Interv 2019 Oct 10;11765:815-822. Epub 2019 Oct 10.

Department of Radiology and Biomedical Research Imaging Center (BRIC), University of North Carolina, Chapel Hill, USA.

Infant brain atlases are essential for characterizing structural changes in the developing brain. Volumetric and cortical atlases are typically constructed independently, potentially causing discrepancies between tissue boundaries and cortical surfaces. In this paper, we present a method for surface-volume consistent construction of longitudinal brain atlases of infants from 2 weeks to 12 months of age. We first construct the 12-month atlas via groupwise surface-constrained volumetric registration. The longitudinal displacements of each subject with respect to different time points are then transported parallelly to the 12-month atlas space. The 12-month cortico-volumetric atlas is finally warped temporally to each month prior to the 12th month using the transported displacements. Experimental results indicate that the longitudinal atlases generated are consistent in terms of tissue boundaries and cortical surfaces, hence allowing joint surface-volume analysis to be performed in a common space.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/978-3-030-32245-8_90DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7052685PMC
October 2019