Usefulness of a deep learning system for diagnosing Sjögren's syndrome using ultrasonography images.

Szczegóły
Abstrakt

Tytuł:: Usefulness of a deep learning system for diagnosing Sjögren's syndrome using ultrasonography images.
Autorzy:: Kise Y; Department of Oral and Maxillofacial Radiology, Aichi Gakuin University, Nagoya, Japan.
Shimizu M; Department of Oral and Maxillofacial Radiology, Kyushu University Hospital, Fukuoka, Japan.
Ikeda H; Department of Oral and Maxillofacial Radiology, Aichi Gakuin University, Nagoya, Japan.
Fujii T; Department of Oral and Maxillofacial Radiology, Aichi Gakuin University, Nagoya, Japan.
Kuwada C; Department of Oral and Maxillofacial Radiology, Aichi Gakuin University, Nagoya, Japan.
Nishiyama M; Department of Oral and Maxillofacial Radiology, Aichi Gakuin University, Nagoya, Japan.
Funakoshi T; Department of Oral and Maxillofacial Radiology, Aichi Gakuin University, Nagoya, Japan.
Ariji Y; Department of Oral and Maxillofacial Radiology, Aichi Gakuin University, Nagoya, Japan.
Fujita H; Department of Electrical, Electronic and Computer Faculty of Engineering, Gifu University, Gifu, Japan.
Katsumata A; Department of Oral Radiology, Asahi University School of Dentistry, Mizuho, Japan.
Yoshiura K; Department of Oral and Maxillofacial Radiology, Faculty of Dental Science, Kyushu University, Fukuoka, Japan.
Ariji E; Department of Oral and Maxillofacial Radiology, Aichi Gakuin University, Nagoya, Japan.
Źródło:: Dento maxillo facial radiology [Dentomaxillofac Radiol] 2020 Mar; Vol. 49 (3), pp. 20190348. Date of Electronic Publication: 2019 Dec 11.
Typ publikacji:: Journal Article
Język:: English
Imprint Name(s):: Publication: 2003- : London : British Institute of Radiology
Original Publication: Erlangen, Germany : University Press Erlangen
MeSH Terms:: Deep Learning*
Sjogren's Syndrome*/diagnostic imaging
Ultrasonography*
Humans ; Parotid Gland/diagnostic imaging ; Submandibular Gland/diagnostic imaging
References:: Clin Exp Rheumatol. 2018 May-Jun;36 Suppl 112(3):165-172. (PMID: 29600950)
Ultrasound Med Biol. 2014 Dec;40(12):2759-67. (PMID: 25261905)
Arthritis Care Res (Hoboken). 2020 Jan;72(1):78-87. (PMID: 30697959)
Int J Rheum Dis. 2019 Feb;22(2):175-181. (PMID: 30187679)
Ann Rheum Dis. 2019 Jul;78(7):967-973. (PMID: 31036626)
Radiology. 2018 Dec;289(3):688-697. (PMID: 30179104)
Arthritis Res Ther. 2017 Dec 6;19(1):269. (PMID: 29208023)
Clin Imaging. 2018 Jul - Aug;50:229-234. (PMID: 29689477)
AJNR Am J Neuroradiol. 2005 May;26(5):1207-14. (PMID: 15891185)
Korean J Radiol. 2019 May;20(5):749-758. (PMID: 30993926)
Med Ultrason. 2018 Aug 30;20(3):313-318. (PMID: 30167584)
Oral Radiol. 2020 Apr;36(2):148-155. (PMID: 31197738)
Comput Methods Programs Biomed. 2017 Jan;138:49-56. (PMID: 27886714)
Sci Rep. 2018 Nov 20;8(1):17128. (PMID: 30459471)
Ultrasound Med Biol. 2016 Sep;42(9):2130-9. (PMID: 27207020)
Dentomaxillofac Radiol. 2019 Sep;48(6):20190019. (PMID: 31075042)
Oral Surg Oral Med Oral Pathol Oral Radiol Endod. 2006 Jul;102(1):85-93. (PMID: 16831678)
J Magn Reson Imaging. 2017 Nov;46(5):1409-1417. (PMID: 28323371)
AJNR Am J Neuroradiol. 1997 May;18(5):951-8. (PMID: 9159376)
Oral Surg Oral Med Oral Pathol Oral Radiol. 2019 May;127(5):458-463. (PMID: 30497907)
Oral Radiol. 2019 May;35(2):101-126. (PMID: 30484212)
Eur J Radiol Open. 2018 Sep 24;5:165-170. (PMID: 30258856)
Oral Dis. 2017 Jan;23(1):84-90. (PMID: 27580143)
Mod Rheumatol. 2004 Dec;14(6):425-34. (PMID: 24387718)
Rheumatology (Oxford). 2021 Aug 2;60(8):3522-3527. (PMID: 30892624)
Acta Reumatol Port. 2018 Jan-Mar;43(1):61-65. (PMID: 29602165)
Eur J Radiol. 2012 Oct;81(10):2702-9. (PMID: 22285605)
Clin Exp Rheumatol. 2018 Sep-Oct;36 Suppl 114(5):159-164. (PMID: 30296991)
Jpn J Radiol. 2019 Jun;37(6):466-472. (PMID: 30888570)
Ann Rheum Dis. 2002 Jun;61(6):554-8. (PMID: 12006334)
J Healthc Eng. 2017;2017:8314740. (PMID: 29065651)
Ann Rheum Dis. 2017 Nov;76(11):1883-1889. (PMID: 28754802)
Arthritis Res Ther. 2015 Aug 23;17:223. (PMID: 26298875)
Br J Radiol. 2018 Feb;91(1083):20170576. (PMID: 29215311)
Scand J Rheumatol. 2018 Jul;47(4):303-310. (PMID: 29411664)
Br J Radiol. 2018 May;91(1085):20170671. (PMID: 29376736)
Lancet Respir Med. 2018 Nov;6(11):837-845. (PMID: 30232049)
Contributed Indexing:: Keywords: Sjögren's syndrome; deep learning; ultrasonography
Entry Date(s):: Date Created: 20191206 Date Completed: 20200224 Latest Revision: 20231113
Update Code:: 20240104
PubMed Central ID:: PMC7068075
DOI:: 10.1259/dmfr.20190348
PMID:: 31804146
: Czasopismo naukowe

Full Text Finder

Objectives: We evaluated the diagnostic performance of a deep learning system for the detection of Sjögren's syndrome (SjS) in ultrasonography (US) images, and compared it with the performance of inexperienced radiologists.
Methods: 100 patients with a confirmed diagnosis of SjS according to both the Japanese criteria and American-European Consensus Group criteria and 100 non-SjS patients that had a dry mouth and suspected SjS but were definitively diagnosed as non-SjS were enrolled in this study. All the patients underwent US scans of both the parotid glands (PG) and submandibular glands (SMG). The training group consisted of 80 SjS patients and 80 non-SjS patients, whereas the test group consisted of 20 SjS patients and 20 non-SjS patients for deep learning analysis. The performance of the deep learning system for diagnosing SjS from the US images was compared with the diagnoses made by three inexperienced radiologists.
Results: The accuracy, sensitivity and specificity of the deep learning system for the PG were 89.5, 90.0 and 89.0%, respectively, and those for the inexperienced radiologists were 76.7, 67.0 and 86.3%, respectively. The deep learning system results for the SMG were 84.0, 81.0 and 87.0%, respectively, and those for the inexperienced radiologists were 72.0, 78.0 and 66.0%, respectively. The AUC for the inexperienced radiologists was significantly different from that of the deep learning system.
Conclusions: The deep learning system had a high diagnostic ability for SjS. This suggests that deep learning could be used for diagnostic support when interpreting US images.

Informacja