AI co-pilot: content-based image retrieval for the reading of rare diseases in chest CT.
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
16 03 2023
16 03 2023
Historique:
received:
26
08
2022
accepted:
13
02
2023
entrez:
17
3
2023
pubmed:
18
3
2023
medline:
22
3
2023
Statut:
epublish
Résumé
The aim of the study was to evaluate the impact of the newly developed Similar patient search (SPS) Web Service, which supports reading complex lung diseases in computed tomography (CT), on the diagnostic accuracy of residents. SPS is an image-based search engine for pre-diagnosed cases along with related clinical reference content ( https://eref.thieme.de ). The reference database was constructed using 13,658 annotated regions of interest (ROIs) from 621 patients, comprising 69 lung diseases. For validation, 50 CT scans were evaluated by five radiology residents without SPS, and three months later with SPS. The residents could give a maximum of three diagnoses per case. A maximum of 3 points was achieved if the correct diagnosis without any additional diagnoses was provided. The residents achieved an average score of 17.6 ± 5.0 points without SPS. By using SPS, the residents increased their score by 81.8% to 32.0 ± 9.5 points. The improvement of the score per case was highly significant (p = 0.0001). The residents required an average of 205.9 ± 350.6 s per case (21.9% increase) when SPS was used. However, in the second half of the cases, after the residents became more familiar with SPS, this increase dropped to 7%. Residents' average score in reading complex chest CT scans improved by 81.8% when the AI-driven SPS with integrated clinical reference content was used. The increase in time per case due to the use of the SPS was minimal.
Identifiants
pubmed: 36928759
doi: 10.1038/s41598-023-29949-3
pii: 10.1038/s41598-023-29949-3
pmc: PMC10020154
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
4336Informations de copyright
© 2023. The Author(s).
Références
Sci Rep. 2020 Jan 15;10(1):338
pubmed: 31941918
J Bras Pneumol. 2010 Jan-Feb;36(1):29-36
pubmed: 20209305
IEEE J Biomed Health Inform. 2017 Jan;21(1):76-84
pubmed: 28114048
J Digit Imaging. 2011 Apr;24(2):208-22
pubmed: 20376525
Respir Med. 2007 Jun;101(6):1350-4
pubmed: 17107778
Br J Radiol. 2000 Oct;73(874):1052-5
pubmed: 11271897
Am J Respir Crit Care Med. 2011 Mar 15;183(6):788-824
pubmed: 21471066
Med Biol Eng Comput. 2020 Apr;58(4):725-737
pubmed: 31965407
Lancet Respir Med. 2018 Nov;6(11):837-845
pubmed: 30232049
IEEE J Biomed Health Inform. 2019 Mar;23(2):714-722
pubmed: 29993791
Comput Med Imaging Graph. 2012 Apr;36(3):227-38
pubmed: 21803548
Thorax. 2016 Jan;71(1):45-51
pubmed: 26585524
Med Phys. 2019 Oct;46(10):4563-4574
pubmed: 31396974
IEEE Trans Med Imaging. 2016 May;35(5):1207-1216
pubmed: 26955021
JAMA. 2012 Jun 13;307(22):2400-9
pubmed: 22692172