Effects of various extracellular matrix proteins on the growth of HL-1 cardiomyocytes.

We present the physical and biochemical effects of extracellular matrixes (ECMs) on HL-1 cardiomyocytes. ECMs play major roles in cell growth, adhesion and the maintenance of native cell functions. We investigated the effects of 6 different cell culture systems: 5 different ECM-treated surfaces (fibronectin, laminin, collagen I, gelatin and a gelatin/fibronectin mixture) and 1 nontreated surface. Surface morphology was scanned and analyzed using atomic force microscopy in order to investigate the physical effects of ECMs. The attachment, growth, viability, proliferation and phenotype of the cells were analyzed using phase-contrast microscopy and immunocytochemistry to elucidate the biochemical effects of ECMs. Our study provides basic information for understanding cell-ECM interactions and should be utilized in future cardiac cell research and tissue engineering.

Deep learning prediction of diffusion MRI data with microstructure-sensitive loss functions.

Deep learning prediction of diffusion MRI (DMRI) data relies on the utilization of effective loss functions. Existing losses typically measure the signal-wise differences between the predicted and target DMRI data without considering the quality of derived diffusion scalars that are eventually utilized for quantification of tissue microstructure. Here, we propose two novel loss functions, called microstructural loss and spherical variance loss, to explicitly consider the quality of both the predicted DMRI data and derived diffusion scalars. We apply these loss functions to the prediction of multi-shell data and enhancement of angular resolution. Evaluation based on infant and adult DMRI data indicates that both microstructural loss and spherical variance loss improve the quality of derived diffusion scalars.

Structural and functional connectome relationships in early childhood.

There is strong evidence that the functional connectome is highly related to the white matter connectome in older children and adults, though little is known about structure-function relationships in early childhood. We investigated the development of cortical structure-function coupling in children longitudinally scanned at 1, 2, 4, and 6 years of age (N = 360) and in a comparison sample of adults (N = 89). We also applied a novel graph convolutional neural network-based deep learning model with a new loss function to better capture inter-subject heterogeneity and predict an individual's functional connectivity from the corresponding structural connectivity. We found regional patterns of structure-function coupling in early childhood that were consistent with adult patterns. In addition, our deep learning model improved the prediction of individual functional connectivity from its structural counterpart compared to existing models.

Rapid Diffusion Magnetic Resonance Imaging Using Slice-Interleaved Encoding.

In this paper, we present a robust reconstruction scheme for diffusion MRI (dMRI) data acquired using slice-interleaved diffusion encoding (SIDE). When combined with SIDE undersampling and simultaneous multi-slice (SMS) imaging, our reconstruction strategy is capable of significantly reducing the amount of data that needs to be acquired, enabling high-speed diffusion imaging for pediatric, elderly, and claustrophobic individuals. In contrast to the conventional approach of acquiring a full diffusion-weighted (DW) volume per diffusion wavevector, SIDE acquires in each repetition time (TR) a volume that consists of interleaved slice groups, each group corresponding to a different diffusion wavevector. This strategy allows SIDE to rapidly acquire data covering a large number of wavevectors within a short period of time. The proposed reconstruction method uses a diffusion spectrum model and multi-dimensional total variation to recover full DW images from DW volumes that are slice-undersampled due to unacquired SIDE volumes. We formulate an inverse problem that can be solved efficiently using the alternating direction method of multipliers (ADMM). Experiment results demonstrate that DW images can be reconstructed with high fidelity even when the acquisition is accelerated by 25 folds.

Vox2Surf: Implicit Surface Reconstruction from Volumetric Data.

Surface reconstruction from volumetric T1-weighted and T2-weighted images is a time-consuming multi-step process that often involves careful parameter fine-tuning, hindering a more wide-spread utilization of surface-based analysis particularly in large-scale studies. In this work, we propose a fast surface reconstruction method that is based on directly learning a continuous-valued signed distance function (SDF) as implicit surface representation. This continuous representation implicitly encodes the boundary of the surface as the zero isosurface. Given the predicted SDF, the target 3D surface is reconstructed by applying the marching cubes algorithm. Our implicit reconstruction method concurrently predicts the surfaces of the brain parenchyma, the white matter and pial surfaces, the subcortical structures, and the ventricles. Evaluation based on data from the Human Connectome Project indicates that surface reconstruction of a total of 22 cortical and subcortical structures can be completed in less than 20 min.

Active Cortex Tractography.

Most existing diffusion tractography algorithms are affected by gyral bias, causing the termination of streamlines at gyral crowns instead of sulcal banks. In this paper, we propose a tractography technique, called active cortex tractography (ACT), to overcome gyral bias by enabling fiber streamlines to curve naturally into the cortex. We show that the cortex can play an active role in cortical tractography by providing anatomical information to overcome orientation ambiguities as the streamlines enter the superficial white matter in gyral blades and approach the cortex. This is achieved by devising a direction scouting mechanism that takes into account the white matter surface normal vectors. The scouting mechanism allows probing of directions further in space to prepare the streamlines to turn at appropriate angles. The surface normal vectors guide the streamlines to turn into the cortex, perpendicular to the white-gray matter interface. Evaluation using synthetic, macaque and human data with different streamline seeding schemes demonstrates that ACT improves cortical tractography.

Tract Dictionary Learning for Fast and Robust Recognition of Fiber Bundles.

In this paper, we propose an efficient framework for parcellation of white matter tractograms using discriminative dictionary learning. Key to our framework is the learning of a compact dictionary for each fiber bundle so that the streamlines within the bundle can be sufficiently represented. Dictionaries for multiple bundles are combined for whole-brain tractogram representation. These dictionaries are learned jointly to encourage inter-bundle incoherence for discriminative power. The proposed method allows tractograms to be assigned to more than one bundle, catering to scenarios where tractograms cannot be clearly separated. Experiments on a bundle-labeled HCP dataset and an infant dataset highlight the ability of our framework in grouping streamlines into anatomically plausible bundles.

Mitigating gyral bias in cortical tractography via asymmetric fiber orientation distributions.

Diffusion tractography in brain connectomics often involves tracing axonal trajectories across gray-white matter boundaries in gyral blades of complex cortical convolutions. To date, gyral bias is observed in most tractography algorithms with streamlines predominantly terminating at gyral crowns instead of sulcal banks. This work demonstrates that asymmetric fiber orientation distribution functions (AFODFs), computed via a multi-tissue global estimation framework, can mitigate the effects of gyral bias, enabling fiber streamlines at gyral blades to make sharper turns into the cortical gray matter. We use ex-vivo data of an adult rhesus macaque and in-vivo data from the Human Connectome Project (HCP) to show that the fiber streamlines given by AFODFs bend more naturally into the cortex than the conventional symmetric FODFs in typical gyral blades. We demonstrate that AFODF tractography improves cortico-cortical connectivity and provides highly consistent outcomes between two different field strengths (3T and 7T).

Globally Optimized Super-Resolution of Diffusion MRI Data via Fiber Continuity.

In this paper, we introduce a technique for super-resolution reconstruction of diffusion MRI, harnessing fiber-continuity (FC) as a constraint in a global whole-brain optimization framework. FC is a biologically-motivated constraint that relates orientation information between neighboring voxels. We show that it can be used to effectively constrain the inverse problem of recovering high-resolution data from low-resolution data. Since voxels are inter-related by FC, we devise a global optimization framework that allows solutions pertaining to all voxels to be solved simultaneously. We demonstrate that the proposed super-resolution framework is effective for diffusion MRI data of a glioma patient, a healthy subject, and a macaque.

Estimating Tissue Microstructure with Undersampled Diffusion Data via Graph Convolutional Neural Networks.

Advanced diffusion models for tissue microstructure are widely employed to study brain disorders. However, these models usually require diffusion MRI (DMRI) data with densely sampled q-space, which is prohibitive in clinical settings. This problem can be resolved by using deep learning techniques, which learn the mapping between sparsely sampled q-space data and the high-quality diffusion microstructural indices estimated from densely sampled data. However, most existing methods simply view the input DMRI data as a vector without considering data structure in the q-space. In this paper, we propose to overcome this limitation by representing DMRI data using graphs and utilizing graph convolutional neural networks to estimate tissue microstructure. Our method makes full use of the q-space angular neighboring information to improve estimation accuracy. Experimental results based on data from the Baby Connectome Project demonstrate that our method outperforms state-of-the-art methods both qualitatively and quantitatively.

Multifold Acceleration of Diffusion MRI via Deep Learning Reconstruction from Slice-Undersampled Data.

Diffusion MRI (dMRI), while powerful for characterization of tissue microstructure, suffers from long acquisition time. In this paper, we present a method for effective diffusion MRI reconstruction from slice-undersampled data. Instead of full diffusion-weighted (DW) image volumes, only a subsample of equally-spaced slices need to be acquired. We show that complementary information from DW volumes corresponding to different diffusion wavevectors can be harnessed using graph convolutional neural networks for reconstruction of the full DW volumes. The experimental results indicate a high acceleration factor of up to 5 can be achieved with minimal information loss.

Reconstructing High-Quality Diffusion MRI Data from Orthogonal Slice-Undersampled Data Using Graph Convolutional Neural Networks.

Diffusion MRI (dMRI), while powerful for the characterization of tissue microstructure, suffers from long acquisition times. In this paper, we propose a super-resolution (SR) reconstruction method based on orthogonal slice-undersampling for accelerated dMRI acquisition. Instead of scanning full diffusion-weighted (DW) image volumes, only a subsample of equally-spaced slices need to be acquired. We show that complementary information from DW volumes corresponding to different diffusion wave-vectors can be harnessed using graph convolutional neural networks for reconstruction of the full DW volumes. We demonstrate that our SR reconstruction method outperforms typical interpolation methods and mitigates partial volume effects. Experimental results indicate that acceleration up to a factor of 5 can be achieved with minimal information loss.

Longitudinal Prediction of Infant Diffusion MRI Data via Graph Convolutional Adversarial Networks.

Missing data is a common problem in longitudinal studies due to subject dropouts and failed scans. We present a graph-based convolutional neural network to predict missing diffusion MRI data. In particular, we consider the relationships between sampling points in the spatial domain and the diffusion wave-vector domain to construct a graph. We then use a graph convolutional network to learn the non-linear mapping from available data to missing data. Our method harnesses a multi-scale residual architecture with adversarial learning for prediction with greater accuracy and perceptual quality. Experimental results show that our method is accurate and robust in the longitudinal prediction of infant brain diffusion MRI data.

Graph-Based Deep Learning for Prediction of Longitudinal Infant Diffusion MRI Data.

Diffusion MRI affords great value for studying brain development, owing to its capability in assessing brain microstructure in association with myelination. With longitudinally acquired pediatric diffusion MRI data, one can chart the temporal evolution of microstructure and white matter connectivity. However, due to subject dropouts and unsuccessful scans, longitudinal datasets are often incomplete. In this work, we introduce a graph-based deep learning approach to predict diffusion MRI data. The relationships between sampling points in spatial domain (x-space) and diffusion wave-vector domain (q-space) are harnessed jointly (x-q space) in the form of a graph. We then implement a residual learning architecture with graph convolution filtering to learn longitudinal changes of diffusion MRI data along time. We evaluate the effectiveness of the spatial and angular components in data prediction. We also investigate the longitudinal trajectories in terms of diffusion scalars computed based on the predicted datasets.

DeepBundle: Fiber Bundle Parcellation with Graph Convolution Neural Networks.

Parcellation of whole-brain tractography streamlines is an important step for tract-based analysis of brain white matter microstructure. Existing fiber parcellation approaches rely on accurate registration between an atlas and the tractograms of an individual, however, due to large individual differences, accurate registration is hard to guarantee in practice. To resolve this issue, we propose a novel deep learning method, called DeepBundle, for registration-free fiber parcellation. Our method utilizes graph convolution neural networks (GCNNs) to predict the parcellation label of each fiber tract. GCNNs are capable of extracting the geometric features of each fiber tract and harnessing the resulting features for accurate fiber parcellation and ultimately avoiding the use of atlases and any registration method. We evaluate DeepBundle using data from the Human Connectome Project. Experimental results demonstrate the advantages of DeepBundle and suggest that the geometric features extracted from each fiber tract can be used to effectively parcellate the fiber tracts.

[Balanced scorecard for performance measurement of a nursing organization in a Korean hospital].

PURPOSE: The purpose of this study was to develop a balanced scorecard (BSC) for performance measurement of a Korean hospital nursing organization and to evaluate the validity and reliability of performance measurement indicators. METHOD: Two hundred fifty-nine nurses in a Korean hospital participated in a survey questionnaire that included 29-item performance evaluation indicators developed by investigators of this study based on the Kaplan and Norton's BSC (1992). Cronbach's alpha was used to test the reliability of the BSC. Exploratory and confirmatory factor analysis with a structure equation model (SEM) was applied to assess the construct validity of the BSC. RESULT: Cronbach's alpha of 29 items was .948. Factor analysis of the BSC showed 5 principal components (eigen value >1.0) which explained 62.7% of the total variance, and it included a new one, community service. The SEM analysis results showed that 5 components were significant for the hospital BSC tool. CONCLUSION: High degree of reliability and validity of this BSC suggests that it may be used for performance measurements of a Korean hospital nursing organization. Future studies may consider including a balanced number of nurse managers and staff nurses in the study. Further data analysis on the relationships among factors is recommended.

Nanoengineered, cell-derived extracellular matrix influences ECM-related gene expression of mesenchymal stem cells.

BACKGROUND: Human mesenchymal stem cells (hMSCs) are, due to their pluripotency, useful sources of cells for stem cell therapy and tissue regeneration. The phenotypes of hMSCs are strongly influenced by their microenvironment, in particular the extracellular matrix (ECM), the composition and structure of which are important in regulating stem cell fate. In reciprocal manner, the properties of ECM are remodeled by the hMSCs, but the mechanism involved in ECM remodeling by hMSCs under topographical stimulus is unclear. In this study, we therefore examined the effect of nanotopography on the expression of ECM proteins by hMSCs by analyzing the quantity and structure of the ECM on a nanogrooved surface. METHODS: To develop the nanoengineered, hMSC-derived ECM, we fabricated the nanogrooves on a coverglass using a UV-curable polyurethane acrylate (PUA). Then, hMSCs were cultivated on the nanogrooves, and the cells at the full confluency were decellularized. To analyze the effect of nanotopography on the hMSCs, the hMSCs were re-seeded on the nanoengineered, hMSC-derived ECM. RESULTS: hMSCs cultured within the nano-engineered hMSC-derived ECM sheet showed a different pattern of expression of ECM proteins from those cultured on ECM-free, nanogrooved surface. Moreover, hMSCs on the nano-engineered ECM sheet had a shorter vinculin length and were less well-aligned than those on the other surface. In addition, the expression pattern of ECM-related genes by hMSCs on the nanoengineered ECM sheet was altered. Interestingly, the expression of genes for osteogenesis-related ECM proteins was downregulated, while that of genes for chondrogenesis-related ECM proteins was upregulated, on the nanoengineered ECM sheet. CONCLUSIONS: The nanoengineered ECM influenced the phenotypic features of hMSCs, and that hMSCs can remodel their ECM microenvironment in the presence of a nanostructured ECM to guide differentiation into a specific lineage.

Microfluidic on-chip immunohistochemistry directly from a paraffin-embedded section.

We present here a novel microfluidic platform that can perform microfluidic on-chip immunohistochemistry (IHC) processes on a formalin-fixed paraffin-embedded section slide. Unlike previous microfluidic IHC studies, our microfluidic chip made of organic solvent-resistant polyurethane acrylate (PUA) is capable of conducting on-chip IHC processes consecutively. A narrow channel wall structure of the PUA chip shows effective sealing by pressure-based reversible assembly with a section slide. We performed both on-chip IHC and conventional IHC processes and compared the IHC results based on the immunostaining intensity. The result showed that the effects of the on-chip deparaffinization, antigen retrieval, and immunoreaction processes on the IHC result were equivalent to conventional methods while reducing the total process time to less than 1/2. The experiment with breast cancer tissue shows that human epidermal growth factor receptor 2 (HER2) classification can be performed by obtaining a clearly distinguishable immunostaining intensity according to the HER2 expression level. We expect our on-chip microfluidic platform to provide a facile technique suitable for miniaturized, automated, and precise diagnostic devices, including a point-of-care device.

Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?

Delineation of the left ventricular cavity, myocardium, and right ventricle from cardiac magnetic resonance images (multi-slice 2-D cine MRI) is a common clinical task to establish diagnosis. The automation of the corresponding tasks has thus been the subject of intense research over the past decades. In this paper, we introduce the "Automatic Cardiac Diagnosis Challenge" dataset (ACDC), the largest publicly available and fully annotated dataset for the purpose of cardiac MRI (CMR) assessment. The dataset contains data from 150 multi-equipments CMRI recordings with reference measurements and classification from two medical experts. The overarching objective of this paper is to measure how far state-of-the-art deep learning methods can go at assessing CMRI, i.e., segmenting the myocardium and the two ventricles as well as classifying pathologies. In the wake of the 2017 MICCAI-ACDC challenge, we report results from deep learning methods provided by nine research groups for the segmentation task and four groups for the classification task. Results show that the best methods faithfully reproduce the expert analysis, leading to a mean value of 0.97 correlation score for the automatic extraction of clinical indices and an accuracy of 0.96 for automatic diagnosis. These results clearly open the door to highly accurate and fully automatic analysis of cardiac CMRI. We also identify scenarios for which deep learning methods are still failing. Both the dataset and detailed results are publicly available online, while the platform will remain open for new submissions.

On-Chip Fabrication of a Cell-Derived Extracellular Matrix Sheet.

The extracellular matrix (ECM) provides physical and chemical support to the surrounding cells. During cell growth, ECM secretion and network formation influence cell morphology, cell adhesion, cell-to-cell interactions, and cell migration. Microfluidics-based cell culture systems are limited by the integration of structural ECM into the device. We report the development of a cell-derived ECM-incorporated microfluidic device that can provide structural characteristics and biochemical components of cell-derived ECM. Using an on-chip decellularization process, we constructed an ECM sheet, secreted and deposited from monolayer-cultured mouse embryonic fibroblasts (NIH/3T3), inside the microfluidic device. ECM components (including collagens, fibronectin, laminin, and elastin) and mesh-type fibronectin fibrous architecture were maintained on the surface of the porous membrane of the microfluidic device after decellularization. To verify the usability of the fibroblast-derived ECM sheet integrated microfluidic device in a cell culture platform, we tested the recellularization of human umbilical vein endothelial cells (HUVEC) and analyzed HUVEC-ECM and HUVEC-HUVEC interactions. On the ECM sheet, HUVECs exhibited morphologies and focal adhesion features that were markedly different from those of other groups. We then explored the effect of the ECM sheet on HUVEC mechanosensitivity. An increase in fluid shear stresses led to focal adhesion and the polymerization and reorganization of HUVEC adherens junctions, similar to natural junctional development, whereas the control group exhibited stimuli-insensitive behaviors. We conclude that the decellularized ECM sheet-incorporated microfluidic device provides an in vivo-like physical and biochemical ECM microenvironment for microfluidics-based cell culture.