The efficacy of deep learning models in the diagnosis of endometrial cancer using MRI: a comparison with radiologists.
Artificial intelligence
CNN
Convolutional neural network
Endometrial carcinoma
Magnetic resonance imaging
Journal
BMC medical imaging
ISSN: 1471-2342
Titre abrégé: BMC Med Imaging
Pays: England
ID NLM: 100968553
Informations de publication
Date de publication:
30 04 2022
30 04 2022
Historique:
received:
03
01
2022
accepted:
21
04
2022
entrez:
3
5
2022
pubmed:
4
5
2022
medline:
6
5
2022
Statut:
epublish
Résumé
To compare the diagnostic performance of deep learning models using convolutional neural networks (CNN) with that of radiologists in diagnosing endometrial cancer and to verify suitable imaging conditions. This retrospective study included patients with endometrial cancer or non-cancerous lesions who underwent MRI between 2015 and 2020. In Experiment 1, single and combined image sets of several sequences from 204 patients with cancer and 184 patients with non-cancerous lesions were used to train CNNs. Subsequently, testing was performed using 97 images from 51 patients with cancer and 46 patients with non-cancerous lesions. The test image sets were independently interpreted by three blinded radiologists. Experiment 2 investigated whether the addition of different types of images for training using the single image sets improved the diagnostic performance of CNNs. The AUC of the CNNs pertaining to the single and combined image sets were 0.88-0.95 and 0.87-0.93, respectively, indicating non-inferior diagnostic performance than the radiologists. The AUC of the CNNs trained with the addition of other types of single images to the single image sets was 0.88-0.95. CNNs demonstrated high diagnostic performance for the diagnosis of endometrial cancer using MRI. Although there were no significant differences, adding other types of images improved the diagnostic performance for some single image sets.
Identifiants
pubmed: 35501705
doi: 10.1186/s12880-022-00808-3
pii: 10.1186/s12880-022-00808-3
pmc: PMC9063362
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
80Informations de copyright
© 2022. The Author(s).
Références
Eur Radiol. 2020 Sep;30(9):4985-4994
pubmed: 32337640
J Womens Health (Larchmt). 2019 Feb;28(2):237-243
pubmed: 30484734
JAMA Netw Open. 2020 Jul 1;3(7):e2011625
pubmed: 32706384
Diagnostics (Basel). 2020 Dec 06;10(12):
pubmed: 33291266
Eur Radiol. 2020 Feb;30(2):1243-1253
pubmed: 31468158
Diagnostics (Basel). 2020 May 20;10(5):
pubmed: 32443922
Int J Environ Res Public Health. 2020 Aug 18;17(16):
pubmed: 32824765
Radiology. 2019 Dec;293(3):607-617
pubmed: 31592731
Radiol Artif Intell. 2021 Apr 21;3(4):e200184
pubmed: 34350408
Ultrason Imaging. 2020 Jul-Sep;42(4-5):213-220
pubmed: 32501152
Eur Radiol. 2008 Feb;18(2):384-9
pubmed: 17917730
Radiographics. 2009 May-Jun;29(3):759-74; discussion 774-8
pubmed: 19448114
Z Med Phys. 2019 May;29(2):102-127
pubmed: 30553609
J Magn Reson Imaging. 2007 Sep;26(3):682-7
pubmed: 17729360
CA Cancer J Clin. 2021 May;71(3):209-249
pubmed: 33538338
Proc SPIE Int Soc Opt Eng. 2017 Feb 11;10134:
pubmed: 28615793
Sci Rep. 2020 Nov 23;10(1):20331
pubmed: 33230285
Radiology. 2019 Mar;290(3):590-606
pubmed: 30694159
AJR Am J Roentgenol. 2007 Jun;188(6):1577-87
pubmed: 17515380
Sci Rep. 2021 Jan 8;11(1):179
pubmed: 33420205
Eur J Radiol. 2021 Feb;135:109471
pubmed: 33338759
Comput Biol Med. 2019 Nov;114:103438
pubmed: 31521902
Eur Radiol. 2019 Feb;29(2):792-805
pubmed: 29995239
Radiology. 2012 Feb;262(2):530-7
pubmed: 22114239
Top Magn Reson Imaging. 2003 Aug;14(4):329-37
pubmed: 14578777
Cancer Manag Res. 2020 Dec 14;12:12823-12840
pubmed: 33364831
J Eval Clin Pract. 2006 Apr;12(2):132-9
pubmed: 16579821
Biometrics. 1977 Mar;33(1):159-74
pubmed: 843571