Artificial-intelligence-enhanced synthetic thick slabs versus standard slices in digital breast tomosynthesis.
Journal
The British journal of radiology
ISSN: 1748-880X
Titre abrégé: Br J Radiol
Pays: England
ID NLM: 0373125
Informations de publication
Date de publication:
01 Apr 2023
01 Apr 2023
Historique:
medline:
25
4
2023
pubmed:
28
3
2023
entrez:
27
3
2023
Statut:
ppublish
Résumé
Digital breast tomosynthesis (DBT) can provide additional information over mammography, albeit at the cost of prolonged reading time. This study retrospectively investigated the impact of reading enhanced synthetic 6 mm slabs instead of standard 1 mm slices on interpretation time and readers performance in a diagnostic assessment centre. Three radiologists (R1-3; 6/4/2 years of breast imaging experience) reviewed 111 diagnostic DBT examinations. Two datasets were interpreted independently for each patient, with one set containing artificial-intelligence-enhanced synthetic 6 mm slabs with 3 mm overlap, while the other set comprised standard 1 mm slices. Blinded to histology and follow-up, readers noted individual BIRADS categories and diagnostic confidence while reading time was recorded. Among the 111 examinations, 70 findings were histopathologically correlated including 56 malignancies. No significant difference was found between BIRADS categories assigned based on 6 mm Artificial-intelligence-enhanced synthetic 6 mm slabs allow for substantial interpretation time reduction in diagnostic DBT without a decrease in reader accuracy. A simplified slab-only protocol instead of 1 mm slices may offset the higher reading time without a loss of diagnosis-relevant image information in first and second readings. Further evaluations are required regarding workflow implications, particularly in screening settings.
Identifiants
pubmed: 36972100
doi: 10.1259/bjr.20220967
pmc: PMC10161903
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
20220967Références
Radiology. 2018 Apr;287(1):58-67
pubmed: 29239711
Br J Radiol. 2016 Jun;89(1062):20150743
pubmed: 27072391
J Am Coll Radiol. 2014 Jun;11(6):594-9
pubmed: 24713501
AJR Am J Roentgenol. 2018 Mar;210(3):685-694
pubmed: 29064756
Eur J Radiol. 2017 Dec;97:83-89
pubmed: 29153373
Eur Radiol. 2022 Apr;32(4):2301-2312
pubmed: 34694451
Health Technol Assess. 2015 Jan;19(4):i-xxv, 1-136
pubmed: 25599513
Can Assoc Radiol J. 2022 Aug;73(3):535-541
pubmed: 35193417
J Med Imaging (Bellingham). 2016 Jan;3(1):011003
pubmed: 26870746
Lancet Oncol. 2013 Jun;14(7):583-9
pubmed: 23623721
Radiology. 2014 Jan;270(1):49-56
pubmed: 24354377
Breast Cancer Res Treat. 2016 Feb;156(1):109-16
pubmed: 26931450
Eur Radiol. 2019 Jul;29(7):3802-3811
pubmed: 30737568
Radiology. 2018 Aug;288(2):375-385
pubmed: 29869961
Lancet Oncol. 2016 Aug;17(8):1105-1113
pubmed: 27345635
Lancet Oncol. 2018 Nov;19(11):1493-1503
pubmed: 30322817
Eur Radiol. 2017 Jul;27(7):2737-2743
pubmed: 27807699
Radiology. 2018 Jun;287(3):787-794
pubmed: 29494322
AJR Am J Roentgenol. 2021 Aug;217(2):314-325
pubmed: 32966115
EClinicalMedicine. 2021 Mar 20;34:100804
pubmed: 33997729
Radiology. 2020 Dec;297(3):534-542
pubmed: 33021891
J Natl Cancer Inst. 2021 Jun 1;113(6):680-690
pubmed: 33372954
Radiology. 2019 Apr;291(1):23-30
pubmed: 30777808
Med Phys. 2012 May;39(5):2431-7
pubmed: 22559613
Lancet Oncol. 2022 May;23(5):601-611
pubmed: 35427470
Breast. 2020 Apr;50:135-140
pubmed: 31607526