date: 2022-01-31T05:28:13Z
pdf:PDFVersion: 1.6
pdf:docinfo:title: Automatic Lung Segmentation and Quantification of Aeration in Computed Tomography of the Chest Using 3D Transfer Learning
xmp:CreatorTool: LaTeX with hyperref package + hypdvips
access_permission:can_print_degraded: true
subject: Background:  Identification of lung parenchyma on computer tomographic (CT) scans in the research setting is done semi-automatically and requires cumbersome manual correction.
language: en
dc:format: application/pdf; version=1.6
pdf:docinfo:creator_tool: LaTeX with hyperref package + hypdvips
access_permission:fill_in_form: true
pdf:encrypted: false
dc:title: Automatic Lung Segmentation and Quantification of Aeration in Computed Tomography of the Chest Using 3D Transfer Learning
modified: 2022-01-31T05:28:13Z
cp:subject: Background:  Identification of lung parenchyma on computer tomographic (CT) scans in the research setting is done semi-automatically and requires cumbersome manual correction.
pdf:docinfo:subject: Background:  Identification of lung parenchyma on computer tomographic (CT) scans in the research setting is done semi-automatically and requires cumbersome manual correction.
pdf:docinfo:creator: Lorenzo Maiello and Robert Huhle
meta:author: Lorenzo Maiello and Robert Huhle
meta:creation-date: 2022-01-31T02:33:20Z
created: 2022-01-31T02:33:20Z
access_permission:extract_for_accessibility: true
Creation-Date: 2022-01-31T02:33:20Z
Author: Lorenzo Maiello and Robert Huhle
producer: dvips + MiKTeX GPL Ghostscript  9.0
pdf:docinfo:producer: dvips + MiKTeX GPL Ghostscript  9.0
pdf:unmappedUnicodeCharsPerPage: 0
dc:description: Background:  Identification of lung parenchyma on computer tomographic (CT) scans in the research setting is done semi-automatically and requires cumbersome manual correction.
Keywords: uNet, COVID-19, lung segmentation, ARDS, Jaccard index, deep learning, transfer learning, lung recruitment
access_permission:modify_annotations: true
dc:creator: Lorenzo Maiello and Robert Huhle
description: Background:  Identification of lung parenchyma on computer tomographic (CT) scans in the research setting is done semi-automatically and requires cumbersome manual correction.
dcterms:created: 2022-01-31T02:33:20Z
Last-Modified: 2022-01-31T05:28:13Z
dcterms:modified: 2022-01-31T05:28:13Z
title: Automatic Lung Segmentation and Quantification of Aeration in Computed Tomography of the Chest Using 3D Transfer Learning
xmpMM:DocumentID: uuid:07e01451-dfbe-4f1d-b22a-d2eaf3480f08
Last-Save-Date: 2022-01-31T05:28:13Z
pdf:docinfo:keywords: uNet, COVID-19, lung segmentation, ARDS, Jaccard index, deep learning, transfer learning, lung recruitment
pdf:docinfo:modified: 2022-01-31T05:28:13Z
meta:save-date: 2022-01-31T05:28:13Z
Content-Type: application/pdf
X-Parsed-By: org.apache.tika.parser.DefaultParser
creator: Lorenzo Maiello and Robert Huhle
dc:language: en
dc:subject: uNet, COVID-19, lung segmentation, ARDS, Jaccard index, deep learning, transfer learning, lung recruitment
access_permission:assemble_document: true
xmpTPg:NPages: 13
pdf:charsPerPage: 3517
access_permission:extract_content: true
access_permission:can_print: true
meta:keyword: uNet, COVID-19, lung segmentation, ARDS, Jaccard index, deep learning, transfer learning, lung recruitment
access_permission:can_modify: true
pdf:docinfo:created: 2022-01-31T02:33:20Z