> top > docs > PubMed:33180877 > annotations

PubMed:33180877 JSON TXT

Annnotations TAB JSON ListView MergeView

LitCovid-PD-FMA-UBERON

Id	Subject	Object	Predicate	Lexical cue	fma_id
T1	94-99	Body_part	denotes	chest	http://purl.org/sig/ont/fma/fma9576
T2	172-187	Body_part	denotes	neural networks	http://purl.org/sig/ont/fma/fma74616
T3	915-920	Body_part	denotes	chest	http://purl.org/sig/ont/fma/fma9576

LitCovid-PD-UBERON

Id	Subject	Object	Predicate	Lexical cue	uberon_id
T1	94-99	Body_part	denotes	chest	http://purl.obolibrary.org/obo/UBERON_0001443
T2	915-920	Body_part	denotes	chest	http://purl.obolibrary.org/obo/UBERON_0001443

LitCovid-PD-MONDO

Id	Subject	Object	Predicate	Lexical cue	mondo_id
T1	72-80	Disease	denotes	COVID-19	http://purl.obolibrary.org/obo/MONDO_0100096
T2	863-887	Disease	denotes	Coronavirus disease 2019	http://purl.obolibrary.org/obo/MONDO_0100096
T3	889-897	Disease	denotes	COVID-19	http://purl.obolibrary.org/obo/MONDO_0100096
T4	1120-1128	Disease	denotes	COVID-19	http://purl.obolibrary.org/obo/MONDO_0100096
T5	2084-2092	Disease	denotes	COVID-19	http://purl.obolibrary.org/obo/MONDO_0100096

LitCovid-PD-CLO

Id	Subject	Object	Predicate	Lexical cue
T1	94-99	http://www.ebi.ac.uk/efo/EFO_0000965	denotes	chest
T2	321-326	http://purl.obolibrary.org/obo/UBERON_0001456	denotes	faces
T3	760-761	http://purl.obolibrary.org/obo/CLO_0001020	denotes	a
T4	915-920	http://www.ebi.ac.uk/efo/EFO_0000965	denotes	chest

LitCovid-PD-CHEBI

Id	Subject	Object	Predicate	Lexical cue	chebi_id
T1	140-142	Chemical	denotes	DL	http://purl.obolibrary.org/obo/CHEBI_68596
T2	575-577	Chemical	denotes	DL	http://purl.obolibrary.org/obo/CHEBI_68596
T3	689-691	Chemical	denotes	GT	http://purl.obolibrary.org/obo/CHEBI_73920
T4	819-830	Chemical	denotes	application	http://purl.obolibrary.org/obo/CHEBI_33232

LitCovid-PD-GO-BP

Id	Subject	Object	Predicate	Lexical cue
T1	59-67	http://purl.obolibrary.org/obo/GO_0007612	denotes	learning
T2	130-138	http://purl.obolibrary.org/obo/GO_0007612	denotes	learning
T3	255-261	http://purl.obolibrary.org/obo/GO_0007601	denotes	vision
T4	308-314	http://purl.obolibrary.org/obo/GO_0007601	denotes	vision
T5	525-533	http://purl.obolibrary.org/obo/GO_0007612	denotes	learning
T6	588-596	http://purl.obolibrary.org/obo/GO_0007610	denotes	behavior
T7	715-723	http://purl.obolibrary.org/obo/GO_0007612	denotes	learning
T8	1314-1322	http://purl.obolibrary.org/obo/GO_0007612	denotes	learning
T9	1410-1418	http://purl.obolibrary.org/obo/GO_0007610	denotes	behavior
T10	1498-1510	http://purl.obolibrary.org/obo/GO_0051179	denotes	localization
T11	1569-1581	http://purl.obolibrary.org/obo/GO_0051179	denotes	localization
T12	1740-1752	http://purl.obolibrary.org/obo/GO_0051179	denotes	localization
T13	2003-2015	http://purl.obolibrary.org/obo/GO_0051179	denotes	localization

LitCovid-PubTator

Id	Subject	Object	Predicate	Lexical cue	tao:has_database_id
1	72-80	Disease	denotes	COVID-19	MESH:C000657245
6	863-887	Disease	denotes	Coronavirus disease 2019	MESH:C000657245
7	889-897	Disease	denotes	COVID-19	MESH:C000657245
8	1120-1128	Disease	denotes	COVID-19	MESH:C000657245
9	2084-2092	Disease	denotes	COVID-19	MESH:C000657245

LitCovid-sentences

Id	Subject	Object	Predicate	Lexical cue
T1	0-112	Sentence	denotes	Analyzing inter-reader variability affecting deep ensemble learning for COVID-19 detection in chest radiographs.
T2	113-268	Sentence	denotes	Data-driven deep learning (DL) methods using convolutional neural networks (CNNs) demonstrate promising performance in natural image computer vision tasks.
T3	269-739	Sentence	denotes	However, their use in medical computer vision tasks faces several limitations, viz., (i) adapting to visual characteristics that are unlike natural images; (ii) modeling random noise during training due to stochastic optimization and backpropagation-based learning strategy; (iii) challenges in explaining DL black-box behavior to support clinical decision-making; and (iv) inter-reader variability in the ground truth (GT) annotations affecting learning and evaluation.
T4	740-935	Sentence	denotes	This study proposes a systematic approach to address these limitations through application to the pandemic-caused need for Coronavirus disease 2019 (COVID-19) detection using chest X-rays (CXRs).
T5	936-1669	Sentence	denotes	Specifically, our contribution highlights significant benefits obtained through (i) pretraining specific to CXRs in transferring and fine-tuning the learned knowledge toward improving COVID-19 detection performance; (ii) using ensembles of the fine-tuned models to further improve performance over individual constituent models; (iii) performing statistical analyses at various learning stages for validating results; (iv) interpreting learned individual and ensemble model behavior through class-selective relevance mapping (CRM)-based region of interest (ROI) localization; and, (v) analyzing inter-reader variability and ensemble localization performance using Simultaneous Truth and Performance Level Estimation (STAPLE) methods.
T6	1670-1889	Sentence	denotes	We find that ensemble approaches markedly improved classification and localization performance, and that inter-reader variability and performance level assessment helps guide algorithm design and parameter optimization.
T7	1890-2111	Sentence	denotes	To the best of our knowledge, this is the first study to construct ensembles, perform ensemble-based disease ROI localization, and analyze inter-reader variability and algorithm performance for COVID-19 detection in CXRs.