Diagnostic Performance of a Deep Learning Model Deployed at a National COVID-19 Screening Facility for Detection of Pneumonia on Frontal Chest Radiographs.

(1) Background: Chest radiographs are the mainstay of initial radiological investigation in this COVID-19 pandemic. A reliable and readily deployable artificial intelligence (AI) algorithm that detects pneumonia in COVID-19 suspects can be useful for screening or triage in a hospital setting. This study has a few objectives: first, to develop a model that accurately detects pneumonia in COVID-19 suspects; second, to assess its performance in a real-world clinical setting; and third, by integrating the model with the daily clinical workflow, to measure its impact on report turn-around time. (2) Methods: The model was developed from the NIH Chest-14 open-source dataset and fine-tuned using an internal dataset comprising more than 4000 CXRs acquired in our institution. Input from two senior radiologists provided the reference standard. The model was integrated into daily clinical workflow, prioritising abnormal CXRs for expedited reporting. Area under the receiver operating characteristic curve (AUC), F1 score, sensitivity, and specificity were calculated to characterise diagnostic performance. The average time taken by radiologists in reporting the CXRs was compared against the mean baseline time taken prior to implementation of the AI model. (3) Results: 9431 unique CXRs were included in the datasets, of which 1232 were ground truth-labelled positive for pneumonia. On the "live" dataset, the model achieved an AUC of 0.95 (95% confidence interval (CI): 0.92, 0.96) corresponding to a specificity of 97% (95% CI: 0.97, 0.98) and sensitivity of 79% (95% CI: 0.72, 0.84). No statistically significant degradation of diagnostic performance was encountered during clinical deployment, and report turn-around time was reduced by 22%. (4) Conclusion: In real-world clinical deployment, our model expedites reporting of pneumonia in COVID-19 suspects while preserving diagnostic performance without significant model drift.

Anisotropic traction stresses and focal adhesion polarization mediates topography-induced cell elongation.

Cell elongation and differentiation has been shown to be modulated by topographical cues provided by grating substratum. However, little is known about the mechanisms and forces involved in the grating-induced cell elongation, due to the difficulty in fabricating soft elastic gels that allow 3-dimensional (3D) cell traction stress measurements. In this paper, we present a method to fabricate soft elastic polyacrylamide grating substrates, using an imprinted polyethylene terephthalate mould, for 3D cell traction stress measurements. Fibroblasts were observed to form protrusions in the grating grooves, and elongate and align parallel to the grating direction on the soft polyacrylamide grating substrates. Focal adhesions were also found to be aligned parallel to the grating direction as compared to cells on flat substrates, suggesting that grating grooves restrict focal adhesion growth perpendicular to the grating direction. The 3D traction stress measurements revealed that highly elongated fibroblasts on grating substrates exert anisotropic traction stresses, in the direction parallel to the grating direction. We propose that focal adhesion alignment along the grating direction may result in increased actin stress fibre formation in the direction parallel to the grating, leading to polarized traction stresses which drive cell elongation.

Human mesenchymal stem cell basal membrane bending on gratings is dependent on both grating width and curvature.

The topography of the extracellular substrate provides physical cues to elicit specific downstream biophysical and biochemical effects in cells. An example of such a topographical substrate is periodic gratings, where the dimensions of the periodic gratings influence cell morphology and directs cell differentiation. We first develop a novel sample preparation technique using Spurr's resin to allow for cross-sectional transmission electron microscopy imaging of cells on grating grooves, and observed that the plasma membrane on the basal surface of these cells can deform and bend into grooves between the gratings. We postulate that such membrane bending is an important first step in eliciting downstream effects. Thus, we use a combination of image analysis and mathematical modeling to explain the extent of bending of basal membrane into grooves. We show that the extent to which the basal membrane bends into grooves depends on both groove width and angle of the grating ridge. Our model predicts that the basal membrane will bend into grooves when they are wider than 1.9 µm in width. The existence of such a threshold may provide an explanation for how the width of periodic gratings may bring about cellular downstream effects, such as cell proliferation or differentiation.

Anisotropic rigidity sensing on grating topography directs human mesenchymal stem cell elongation.

Through mechanotransduction, cells can sense physical cues from the extracellular environment and convert them into internal signals that affect various cellular functions. For example, human mesenchymal stem cells (hMSCs) cultured on topographical gratings have been shown to elongate and differentiate to different extents depending on grating width. Using a combination of experiments and mathematical modeling, the physical parameters of substrate topography that direct cell elongation were determined. On a variety of topographical gratings with different grating widths, heights and rigidity, elongation of hMSCs was measured and a monotonic increase was observed for grating aspect ratio (crosssectional height to line-width ratio) between 0.035 and 2. The elongation was also dependent on the grating substrate rigidity over a range of 0.18-1.43 MPa. A mathematical model was developed to explain our observations by relating cell elongation to the anisotropic deformation of the gratings and how this anisotropy depends on the aspect ratio and rigidity of the gratings. Our model was in good agreement with the experimental data for the range of grating aspect ratio and substrate rigidity studied. In addition, we also showed that the percentage of aligned cells, which had a strong linear correlation with elongation for slightly elongated cells, saturated toward 100 % at higher level of cell elongation. Our results may be useful in designing gratings to elicit specific cellular responses that may depend on the extent of cell elongation.

Left ventricle segmentation by dynamic shape constrained random walks.

Accurate and robust extraction of the left ventricle (LV) cavity is a key step for quantitative analysis of cardiac functions. In this study, we propose an improved LV cavity segmentation method that incorporates a dynamic shape constraint into the weighting function of the random walks algorithm. The method involves an iterative process that updates an intermediate result to the desired solution. The shape constraint restricts the solution space of the segmentation result, such that the robustness of the algorithm is increased to handle misleading information that emanates from noise, weak boundaries, and clutter. Our experiments on real cardiac magnetic resonance images demonstrate that the proposed method obtains better segmentation performance than standard method.

Nanotopography modulates mechanotransduction of stem cells and induces differentiation through focal adhesion kinase.

Regulated biophysical cues, such as nanotopography, have been shown to be integral for tissue regeneration and embryogenesis in the stem cell niche. Tissue homeostasis involves the interaction of multipotent cells with nanoscaled topographical features in their ECM to regulate aspects of cell behavior. Synthetic nanostructures can drive specific cell differentiation, but the sensing mechanisms for nanocues remain poorly understood. Here, we report that nanotopography-induced human mesenchymal stem cell (hMSC) differentiation through cell mechanotransduction is modulated by the integrin-activated focal adhesion kinase (FAK). On nanogratings with 250 nm line width on polydimethylsiloxane, hMSCs developed aligned stress fibers and showed an upregulation of neurogenic and myogenic differentiation markers. The observed cellular focal adhesions within these cells were also significantly smaller and more elongated on the nanogratings compared to microgratings or unpatterned control. In addition, our mechanistic study confirmed that this regulation was dependent upon actomyosin contractility, suggesting a direct force-dependent mechanism. The topography-induced differentiation was observed on different ECM compositions but the response was not indicative of a direct ECM-induced hMSC differentiation pathway. FAK phosphorylation was required for topography-induced hMSC differentiation while FAK overexpression overruled the topographical cues in determining cell lineage bias. The results indicated that FAK activity had a direct impact on topography-induced gene expression, and that this effect of FAK was independent of cell shape. These findings suggest that hMSC sense and transduce nanotopographical signals through focal adhesions and actomyosin cytoskeleton contractility to induce differential gene expression.

Sequential logic model deciphers dynamic transcriptional control of gene expressions.

BACKGROUND: Cellular signaling involves a sequence of events from ligand binding to membrane receptors through transcription factors activation and the induction of mRNA expression. The transcriptional-regulatory system plays a pivotal role in the control of gene expression. A novel computational approach to the study of gene regulation circuits is presented here. METHODOLOGY: Based on the concept of finite state machine, which provides a discrete view of gene regulation, a novel sequential logic model (SLM) is developed to decipher control mechanisms of dynamic transcriptional regulation of gene expressions. The SLM technique is also used to systematically analyze the dynamic function of transcriptional inputs, the dependency and cooperativity, such as synergy effect, among the binding sites with respect to when, how much and how fast the gene of interest is expressed. PRINCIPAL FINDINGS: SLM is verified by a set of well studied expression data on endo16 of Strongylocentrotus purpuratus (sea urchin) during the embryonic midgut development. A dynamic regulatory mechanism for endo16 expression controlled by three binding sites, UI, R and Otx is identified and demonstrated to be consistent with experimental findings. Furthermore, we show that during transition from specification to differentiation in wild type endo16 expression profile, SLM reveals three binary activities are not sufficient to explain the transcriptional regulation of endo16 expression and additional activities of binding sites are required. Further analyses suggest detailed mechanism of R switch activity where indirect dependency occurs in between UI activity and R switch during specification to differentiation stage. CONCLUSIONS/SIGNIFICANCE: The sequential logic formalism allows for a simplification of regulation network dynamics going from a continuous to a discrete representation of gene activation in time. In effect our SLM is non-parametric and model-independent, yet providing rich biological insight. The demonstration of the efficacy of this approach in endo16 is a promising step for further application of the proposed method.

In silico analysis of p53 using the p53 knowledgebase: mutations, polymorphisms, microRNAs and pathways.

P53 is probably the most important tumor suppressor known. Over the years, information about this gene has increased dramatically. We have built a comprehensive knowledgebase of p53, which aims to facilitate wet-lab biologists to formulate their experiments and new-comers to learn whatever they need about the gene and bioinformaticians to make new discoveries through data analysis. Using the information curated, including mutation information, transcription factors, transcriptional targets, and single nucleotide polymorphisms, we have performed extensive bioinformatics analysis, and made several new discoveries about p53. We have identified point missense mutations that are over-represented in cancers, but lack of functional studies. By assessing the capability of six p53 transcriptional targets' tag SNPs selected from HapMap to capture SNPs obtained from National Institute of Environmental Health Sciences (NIEHS) Environmental Genome project and vice versa, we conclude that NIEHS data is a better source for tagSNP selections of these genes in future association studies. Analysis of microRNA regulation in the transcriptional network of the p53 gene reveals potentially important regulatory relationships between oncogenic microRNAs and transcription factors of p53. By mapping transcription factors of p53 to pathways involved in cell cycle and apoptosis, we have identified distinctive transcriptional controls of p53 in these two physiological states.