Open AccessDeep learning for lung disease segmentation on CT: Which reconstruction kernel should be used?
Author(s) -
Trieu-Nghi Hoang-Thi,
Maria Vakalopoulou,
Stergios Christodoulidis,
Nikos Paragios,
MariePierre Revel,
Guillaume Chassag
Publication year - 2021
Publication title -
diagnostic and interventional imaging
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.037
H-Index - 36
ISSN - 2211-5684
DOI - 10.1016/j.diii.2021.10.001
Subject(s) - medicine , interquartile range , wilcoxon signed rank test , nuclear medicine , covid-19 , segmentation , interstitial lung disease , computed tomography , lung , radiology , artificial intelligence , mann–whitney u test , disease , infectious disease (medical specialty) , computer science
The purpose of this study was to determine whether a single reconstruction kernel or both high and low frequency kernels should be used for training deep learning models for the segmentation of diffuse lung disease on chest computed tomography (CT).
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom