Artificial intelligence in CT for quantifying lung changes in the era of CFTR modulators

2021 ◽  
pp. 2100844
Author(s):  
Gael Dournes ◽  
Chase S. Hall ◽  
Matthew M. Willmering ◽  
Alan S. Brody ◽  
Julie Macey ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Cystic Fibrosis ◽  
Ground Truth ◽  
Rank Test ◽  
Dice Coefficient ◽  
Semantic Labeling ◽  
Bronchial Mucus ◽  
Spearman Test ◽  
Ct Slices

RationaleChest computed tomography (CT) remains the imaging standard for demonstrating cystic fibrosis airway structural disease in vivo. However, visual scorings as an outcome measure are time-consuming, require training, and lack high reproducibility.ObjectiveTo validate a fully automated artificial intelligence-driven scoring of cystic fibrosis lung disease severity.MethodsData were retrospectively collected in three cystic fibrosis reference centers, between 2008 and 2020, in 184 patients 4 to 54-years-old. An algorithm using three two-dimensional convolutional neural networks was trained with 78 patients’ CTs (23 530 CT slices) for the semantic labeling of bronchiectasis, peribronchial thickening, bronchial mucus, bronchiolar mucus, and collapse/consolidation. 36 patients’ CTs (11 435 CT slices) were used for testing versus ground-truth labels. The method's clinical validity was assessed in an independent group of 70 patients with or without lumacaftor/ivacaftor treatment (n=10 and 60, respectively) with repeat examinations. Similarity and reproducibility were assessed using Dice coefficient, correlations using Spearman test, and paired comparisons using Wilcoxon rank test.Measurement and main resultsThe overall pixelwise similarity of artificial intelligence-driven versus ground-truth labels was good (Dice coefficient=0.71). All artificial intelligence-driven volumetric quantifications had moderate to very good correlations to a visual imaging scoring (p<0.001) and fair to good correlations to FEV1% at pulmonary function test (p<0.001). Significant decreases in peribronchial thickening (p=0.005), bronchial mucus (p=0.005), bronchiolar mucus (p=0.007) volumes were measured in patients with lumacaftor/ivacaftor. Conversely, bronchiectasis (p=0.002) and peribronchial thickening (p=0.008) volumes increased in patients without lumacaftor/ivacaftor. The reproducibility was almost perfect (Dice>0.99).ConclusionArtificial intelligence allows a fully automated volumetric quantification of cystic fibrosis-related modifications over an entire lung. The novel scoring system could provide a robust disease outcome in the era of effective CFTR modulator therapy.

Preliminary Report of In vitro and In vivo Effectiveness of Dornase Alfa on SARS-CoV-2 Infection (Preprint)

2020 ◽  
Author(s):  
Hacer Kuzu Okur ◽  
Koray Yalcin ◽  
Cihan Tastan ◽  
Sevda Demir ◽  
Bulut Yurtsever ◽  
...  
Keyword(s):  
Cystic Fibrosis ◽  
Respiratory Tract ◽  
Mononuclear Cells ◽  
Multiple Organ ◽  
Peripheral Blood Mononuclear ◽  
Dornase Alfa ◽  
Tract Infections ◽  
Adult Peripheral Blood

UNSTRUCTURED Dornase alfa, the recombinant form of the human DNase I enzyme, breaks down neutrophil extracellular traps (NET) that include a vast amount of DNA fragments, histones, microbicidal proteins and oxidant enzymes released from necrotic neutrophils in the highly viscous mucus of cystic fibrosis patients. Dornase alfa has been used for decades in patients with cystic fibrosis to reduce the viscoelasticity of respiratory tract secretions, to decrease the severity of respiratory tract infections, and to improve lung function. Previous studies have linked abnormal NET formations to lung diseases, especially to acute respiratory distress syndrome (ARDS). Coronavirus disease 2019 (COVID-19) pandemic affected more than two million people over the world, resulting in unprecedented health, social and economic crises. The COVID-19, viral pneumonia that progresses to ARDS and even multiple organ failure, is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). High blood neutrophil levels are an early indicator of SARS-CoV-2 infection and predict severe respiratory diseases. A similar mucus structure is detected in COVID-19 patients due to the accumulation of excessive NET in the lungs. Here, we show our preliminary results with dornase alfa that may have an in-vitro anti-viral effect against SARS-CoV-2 infection in a bovine kidney cell line, MDBK without drug toxicity on healthy adult peripheral blood mononuclear cells. In this preliminary study, we also showed that dornase alfa can promote clearance of NET formation in both an in-vitro and three COVID-19 cases who showed clinical improvement in radiological analysis (2-of-3 cases), oxygen saturation (SpO2), respiratory rate, disappearing of dyspnea and coughing.

scholarly journals Functional and Transcriptional Adaptations of Blood Monocytes Recruited to the Cystic Fibrosis Airway Microenvironment In Vitro

2021 ◽  
Vol 22 (5) ◽  
pp. 2530
Author(s):  
Bijean D. Ford ◽  
Diego Moncada Giraldo ◽  
Camilla Margaroli ◽  
Vincent D. Giacalone ◽  
Milton R. Brown ◽  
...  
Keyword(s):  
Cystic Fibrosis ◽  
Bactericidal Activity ◽  
Scavenger Receptor ◽  
Receptor Expression ◽  
Blood Monocytes ◽  
Bacterial Killing ◽  
Blood Neutrophils ◽  
Vitro Model

Cystic fibrosis (CF) lung disease is dominated by the recruitment of myeloid cells (neutrophils and monocytes) from the blood which fail to clear the lung of colonizing microbes. In prior in vitro studies, we showed that blood neutrophils migrated through the well-differentiated lung epithelium into the CF airway fluid supernatant (ASN) mimic the dysfunction of CF airway neutrophils in vivo, including decreased bactericidal activity despite an increased metabolism. Here, we hypothesized that, in a similar manner to neutrophils, blood monocytes undergo significant adaptations upon recruitment to CFASN. To test this hypothesis, primary human blood monocytes were transmigrated in our in vitro model into the ASN from healthy control (HC) or CF subjects to mimic in vivo recruitment to normal or CF airways, respectively. Surface phenotype, metabolic and bacterial killing activities, and transcriptomic profile by RNA sequencing were quantified post-transmigration. Unlike neutrophils, monocytes were not metabolically activated, nor did they show broad differences in activation and scavenger receptor expression upon recruitment to the CFASN compared to HCASN. However, monocytes recruited to CFASN showed decreased bactericidal activity. RNASeq analysis showed strong effects of transmigration on monocyte RNA profile, with differences between CFASN and HCASN conditions, notably in immune signaling, including lower expression in the former of the antimicrobial factor ISG15, defensin-like chemokine CXCL11, and nitric oxide-producing enzyme NOS3. While monocytes undergo qualitatively different adaptations from those seen in neutrophils upon recruitment to the CF airway microenvironment, their bactericidal activity is also dysregulated, which could explain why they also fail to protect CF airways from infection.

Correlation of AGR2 expression with the incidence of metastasis in luminal breast cancer

2021 ◽  
pp. 1-5
Author(s):  
David Samuel Kereh ◽  
John Pieter ◽  
William Hamdani ◽  
Haryasena Haryasena ◽  
Daniel Sampepajung ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Mean Value ◽  
Rank Test ◽  
Luminal Breast Cancer ◽  
P Value ◽  
Strong Positive Correlation ◽  
Breast Cancer Patients ◽  
The Mean ◽  
Spearman Test

BACKGROUND: AGR2 expression is associated with luminal breast cancer. Overexpression of AGR2 is a predictor of poor prognosis. Several studies have found correlations between AGR2 in disseminated tumor cells (DTCs) in breast cancer patients. OBJECTIVE: This study aims to determine the correlation between anterior Gradient2 (AGR2) expression with the incidence of distant metastases in luminal breast cancer. METHODS: This study was an observational study using a cross-sectional method and was conducted at Wahidin Sudirohusodo Hospital and the network. ELISA methods examine AGR2 expression from blood serum of breast cancer patients. To compare the AGR2 expression in metastatic patients and the non-metastatic patient was tested with Mann Whitney test. The correlation of AGR2 expression and metastasis was tested with the Rank Spearman test. RESULTS: The mean value of AGR2 antibody expression on ELISA in this study was 2.90 ± 1.82 ng/dl, and its cut-off point was 2.1 ng/dl. Based on this cut-off point value, 14 subjects (66.7%) had overexpression of AGR2 serum ELISA, and 7 subjects (33.3%) had not. The mean value AGR2 was significantly higher in metastatic than not metastatic, 3.77 versus 1.76 (p < 0.01). The Spearman rank test obtained a p-value for the 2 tail test of 0.003 (p < 0.05), which showed a significant correlation of both, while the correlation coefficient of 0.612 showed a strong positive correlation of AGR2 overexpression and metastasis. CONCLUSIONS: AGR2 expression is correlated with metastasis in Luminal breast cancer.

scholarly journals EXTH-46. ARTIFICIAL INTELLIGENCE-BASED IDENTIFICATION OF COMBINED VANDETANIB AND EVEROLIMUS IN THE TREATMENT OF ACVR1-MUTANT DIFFUSE INTRINSIC PONTINE GLIOMA

2020 ◽  
Vol 22 (Supplement_2) ◽  
pp. ii97-ii97
Author(s):  
Diana Carvalho ◽  
Peter Richardson ◽  
Nagore Gene Olaciregui ◽  
Reda Stankunaite ◽  
Cinzia Emilia Lavarino ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Cell Viability ◽  
Xenograft Model ◽  
Diffuse Intrinsic Pontine Glioma ◽  
Pontine Glioma ◽  
Serine Threonine Kinase ◽  
Orthotopic Xenografts ◽  
Extended Survival

Abstract Somatic mutations in ACVR1, encoding the serine/threonine kinase ALK2 receptor, are found in a quarter of children with the currently incurable brain tumour diffuse intrinsic pontine glioma (DIPG). Treatment of ACVR1-mutant DIPG patient-derived models with multiple inhibitor chemotypes leads to a reduction in cell viability in vitro and extended survival in orthotopic xenografts in vivo, though there are currently no specific ACVR1 inhibitors licensed for DIPG. Using an Artificial Intelligence-based platform to search for approved compounds which could be used to treat ACVR1-mutant DIPG, the combination of vandetanib and everolimus was identified as a possible therapeutic approach. Vandetanib, an approved inhibitor of VEGFR/RET/EGFR, was found to target ACVR1 (Kd=150nM) and reduce DIPG cell viability in vitro, but has been trialed in DIPG patients with limited success, in part due to an inability to cross the blood-brain-barrier. In addition to mTOR, everolimus inhibits both ABCG2 (BCRP) and ABCB1 (P-gp) transporter, and was synergistic in DIPG cells when combined with vandetanib in vitro. This combination is well-tolerated in vivo, and significantly extended survival and reduced tumour burden in an orthotopic ACVR1-mutant patient-derived DIPG xenograft model. Based on these preclinical data, three patients with ACVR1-mutant DIPG were treated with vandetanib and everolimus. These cases may inform on the dosing and the toxicity profile of this combination for future clinical studies. This bench-to-bedside approach represents a rapidly translatable therapeutic strategy in children with ACVR1 mutant DIPG.

scholarly journals Simulating a Ground Truth for Transit Time Analysis of Indicator Dilution Curves

2020 ◽  
Vol 6 (3) ◽  
pp. 268-271
Author(s):  
Michael Reiß ◽  
Ady Naber ◽  
Werner Nahm
Keyword(s):  
Transit Time ◽  
Sampling Rate ◽  
Ground Truth ◽  
Indicator Dilution ◽  
Cross Sectional ◽  
In Vivo Measurements ◽  
Multiple Indicator Dilution ◽  
Transit Times ◽  
Dilution Curves

AbstractTransit times of a bolus through an organ can provide valuable information for researchers, technicians and clinicians. Therefore, an indicator is injected and the temporal propagation is monitored at two distinct locations. The transit time extracted from two indicator dilution curves can be used to calculate for example blood flow and thus provide the surgeon with important diagnostic information. However, the performance of methods to determine the transit time Δt cannot be assessed quantitatively due to the lack of a sufficient and trustworthy ground truth derived from in vivo measurements. Therefore, we propose a method to obtain an in silico generated dataset of differently subsampled indicator dilution curves with a ground truth of the transit time. This method allows variations on shape, sampling rate and noise while being accurate and easily configurable. COMSOL Multiphysics is used to simulate a laminar flow through a pipe containing blood analogue. The indicator is modelled as a rectangular function of concentration in a segment of the pipe. Afterwards, a flow is applied and the rectangular function will be diluted. Shape varying dilution curves are obtained by discrete-time measurement of the average dye concentration over different cross-sectional areas of the pipe. One dataset is obtained by duplicating one curve followed by subsampling, delaying and applying noise. Multiple indicator dilution curves were simulated, which are qualitatively matching in vivo measurements. The curves temporal resolution, delay and noise level can be chosen according to the requirements of the field of research. Various datasets, each containing two corresponding dilution curves with an existing ground truth transit time, are now available. With additional knowledge or assumptions regarding the detection-specific transfer function, realistic signal characteristics can be simulated. The accuracy of methods for the assessment of Δt can now be quantitatively compared and their sensitivity to noise evaluated.

scholarly journals Fully-automated root image analysis (faRIA)

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Narendra Narisetti ◽  
Michael Henke ◽  
Christiane Seiler ◽  
Astrid Junker ◽  
Jörn Ostermann ◽  
...  
Keyword(s):  
Near Infrared ◽  
Climatic Factors ◽  
Plant Root ◽  
Ground Truth ◽  
Parameter Tuning ◽  
Dice Coefficient ◽  
Powerful Analytical Tool ◽  
Manual Interaction ◽  
And Function ◽  
Noisy Background

AbstractHigh-throughput root phenotyping in the soil became an indispensable quantitative tool for the assessment of effects of climatic factors and molecular perturbation on plant root morphology, development and function. To efficiently analyse a large amount of structurally complex soil-root images advanced methods for automated image segmentation are required. Due to often unavoidable overlap between the intensity of fore- and background regions simple thresholding methods are, generally, not suitable for the segmentation of root regions. Higher-level cognitive models such as convolutional neural networks (CNN) provide capabilities for segmenting roots from heterogeneous and noisy background structures, however, they require a representative set of manually segmented (ground truth) images. Here, we present a GUI-based tool for fully automated quantitative analysis of root images using a pre-trained CNN model, which relies on an extension of the U-Net architecture. The developed CNN framework was designed to efficiently segment root structures of different size, shape and optical contrast using low budget hardware systems. The CNN model was trained on a set of 6465 masks derived from 182 manually segmented near-infrared (NIR) maize root images. Our experimental results show that the proposed approach achieves a Dice coefficient of 0.87 and outperforms existing tools (e.g., SegRoot) with Dice coefficient of 0.67 by application not only to NIR but also to other imaging modalities and plant species such as barley and arabidopsis soil-root images from LED-rhizotron and UV imaging systems, respectively. In summary, the developed software framework enables users to efficiently analyse soil-root images in an automated manner (i.e. without manual interaction with data and/or parameter tuning) providing quantitative plant scientists with a powerful analytical tool.

scholarly journals Co-Overexpression of TWIST1-CSF1 Is a Common Event in Metastatic Oral Cancer and Drives Biologically Aggressive Phenotype

Cancers ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 153
Author(s):  
Sabrina Daniela da Silva ◽  
Fabio Albuquerque Marchi ◽  
Jie Su ◽  
Long Yang ◽  
Ludmila Valverde ◽  
...  
Keyword(s):  
Epithelial Mesenchymal Transition ◽  
Inflammatory Cells ◽  
Rank Test ◽  
Mesenchymal Transition ◽  
Genome Wide ◽  
A Genome ◽  
Enhanced Expression ◽  
Advanced Stages

Invasive oral squamous cell carcinoma (OSCC) is often ulcerated and heavily infiltrated by pro-inflammatory cells. We conducted a genome-wide profiling of tissues from OSCC patients (early versus advanced stages) with 10 years follow-up. Co-amplification and co-overexpression of TWIST1, a transcriptional activator of epithelial-mesenchymal-transition (EMT), and colony-stimulating factor-1 (CSF1), a major chemotactic agent for tumor-associated macrophages (TAMs), were observed in metastatic OSCC cases. The overexpression of these markers strongly predicted poor patient survival (log-rank test, p = 0.0035 and p = 0.0219). Protein analysis confirmed the enhanced expression of TWIST1 and CSF1 in metastatic tissues. In preclinical models using OSCC cell lines, macrophages, and an in vivo matrigel plug assay, we demonstrated that TWIST1 gene overexpression induces the activation of CSF1 while TWIST1 gene silencing down-regulates CSF1 preventing OSCC invasion. Furthermore, excessive macrophage activation and polarization was observed in co-culture system involving OSCC cells overexpressing TWIST1. In summary, this study provides insight into the cooperation between TWIST1 transcription factor and CSF1 to promote OSCC invasiveness and opens up the potential therapeutic utility of currently developed antibodies and small molecules targeting cancer-associated macrophages.

Sign in / Sign up

Export Citation Format

Share Document