About: Automated Quantification of CT Patterns Associated with COVID-19 from Chest CT

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Automated Quantification of CT Patterns Associated with COVID-19 from Chest CT Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : covidontheweb.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	Automated Quantification of CT Patterns Associated with COVID-19 from Chest CT
Creator	Balachandran, Abishek Chabin, Guillaume Chaganti, Shikha Cohen, Stuart Comaniciu, Dorin Donald, ) Flohr, Thomas Georgescu, Bogdan Grenier, Philippe Zucker, Barbara Foch, Hôpital Suresnes, France
Source	PMC
abstract	PURPOSE: To present a method that automatically segments and quantifies abnormal CT patterns commonly present in coronavirus disease 2019 (COVID-19), namely ground glass opacities and consolidations. MATERIALS AND METHODS: In this retrospective study, the proposed method takes as input a non-contrasted chest CT and segments the lesions, lungs, and lobes in three dimensions, based on a dataset of 9749 chest CT volumes. The method outputs two combined measures of the severity of lung and lobe involvement, quantifying both the extent of COVID-19 abnormalities and presence of high opacities, based on deep learning and deep reinforcement learning. The first measure of (PO, PHO) is global, while the second of (LSS, LHOS) is lobe-wise. Evaluation of the algorithm is reported on CTs of 200 participants (100 COVID-19 confirmed patients and 100 healthy controls) from institutions from Canada, Europe and the United States collected between 2002-Present (April 2020). Ground truth is established by manual annotations of lesions, lungs, and lobes. Correlation and regression analyses were performed to compare the prediction to the ground truth. RESULTS: Pearson correlation coefficient between method prediction and ground truth for COVID-19 cases was calculated as 0.92 for PO (P < .001), 0.97 for PHO (P < .001), 0.91 for LSS (P < .001), 0.90 for LHOS (P < .001). 98 of 100 healthy controls had a predicted PO of less than 1%, 2 had between 1-2%. Automated processing time to compute the severity scores was 10 seconds per case compared to 30 minutes required for manual annotations. CONCLUSION: A new method segments regions of CT abnormalities associated with COVID-19 and computes (PO, PHO), as well as (LSS, LHOS) severity scores.
has issue date	2020-07-29(xsd:dateTime)
bibo:doi	10.1148/ryai.2020200048
has license	no-cc
sha1sum (hex)	caf3985d309e4fbf219a43bc2155718d3eea836b
schema:url	https://doi.org/10.1148/ryai.2020200048
resource representing a document's title	Automated Quantification of CT Patterns Associated with COVID-19 from Chest CT
has PubMed Central identifier	PMC7392373
schema:publication	Radiol Artif Intell
resource representing a document's body	covid:caf3985d309e4fbf219a43bc2155718d3eea836b#body_text
is schema:about of	named entity 'Chest' named entity 'progression' named entity 'quantification' named entity 'COVID-19' named entity 'lung diseases' named entity 'ground truth' named entity 'COVID-19' named entity 'April 20, 2020' named entity 'COPD' named entity 'ground truth' named entity 'COVID' named entity 'false positive' named entity 'validation set' named entity 'COVID-19' named entity 'attenuation' named entity 'GGO' named entity 'ground truth' named entity 'chest imaging' named entity 'chest CT' named entity 'PHO' named entity 'confidence interval' named entity 'COVID-19' named entity 'anatomical' named entity 'tested positive' named entity 'ROI' named entity 'lungs' named entity 'GGO' named entity 'viral pneumonia' named entity 'lung parenchyma' named entity 'pleural effusion' named entity 'COVID -19' named entity 'RT-PCR' named entity 'scatter plot' named entity 'radiologist' named entity 'chest CT' named entity 'algorithm' named entity 'linear regression' named entity 'batch normalization' named entity 'data set' named entity 'Coefficient of determination' named entity 'extent of disease' named entity 'CNN' named entity 'COVID-19' named entity 'opacity' named entity 'COVID' named entity 'ground truth' named entity 'infection' named entity 'extent of disease' named entity 'radiologists' named entity 'emergency rooms' named entity 'CT scan' named entity 'COVID-19' named entity 'AstraZeneca' named entity 'data set' named entity 'United States' named entity 'confidence interval' named entity 'ground glass opacities' named entity 'PHO' named entity 'chest CT' named entity 'opacity' named entity 'clinical setting' named entity 'CT scans' named entity 'chest CT' named entity 'COVID' named entity 'Canada' named entity 'upsampling' named entity 'scientific research' named entity 'United States' named entity 'loss function' named entity 'RT-PCR' named entity 'machine learning' named entity 'model selection'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2025 OpenLink Software