Deep Learning-based Approach for Automated Assessment of Interstitial Lung Disease in Systemic Sclerosis on CT Images.
Journal
Radiology. Artificial intelligence
ISSN: 2638-6100
Titre abrégé: Radiol Artif Intell
Pays: United States
ID NLM: 101746556
Informations de publication
Date de publication:
Jul 2020
Jul 2020
Historique:
received:
31
01
2019
revised:
19
03
2020
accepted:
31
03
2020
entrez:
3
5
2021
pubmed:
4
5
2021
medline:
4
5
2021
Statut:
epublish
Résumé
To develop a deep learning algorithm for the automatic assessment of the extent of systemic sclerosis (SSc)-related interstitial lung disease (ILD) on chest CT images. This retrospective study included 208 patients with SSc (median age, 57 years; 167 women) evaluated between January 2009 and October 2017. A multicomponent deep neural network (AtlasNet) was trained on 6888 fully annotated CT images (80% for training and 20% for validation) from 17 patients with no, mild, or severe lung disease. The model was tested on a dataset of 400 images from another 20 patients, independently partially annotated by three radiologist readers. The ILD contours from the three readers and the deep learning neural network were compared by using the Dice similarity coefficient (DSC). The correlation between disease extent obtained from the deep learning algorithm and that obtained by using pulmonary function tests (PFTs) was then evaluated in the remaining 171 patients and in an external validation dataset of 31 patients based on the analysis of all slices of the chest CT scan. The Spearman rank correlation coefficient (ρ) was calculated to evaluate the correlation between disease extent and PFT results. The median DSCs between the readers and the deep learning ILD contours ranged from 0.74 to 0.75, whereas the median DSCs between contours from radiologists ranged from 0.68 to 0.71. The disease extent obtained from the algorithm, by analyzing the whole CT scan, correlated with the diffusion lung capacity for carbon monoxide, total lung capacity, and forced vital capacity (ρ The developed algorithm performed similarly to radiologists for disease-extent contouring, which correlated with pulmonary function to assess CT images from patients with SSc-related ILD.
Identifiants
pubmed: 33937829
doi: 10.1148/ryai.2020190006
pmc: PMC8082359
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e190006Informations de copyright
2020 by the Radiological Society of North America, Inc.
Déclaration de conflit d'intérêts
Disclosures of Conflicts of Interest: G.C. disclosed no relevant relationships. M.V. disclosed no relevant relationships. A.R. disclosed no relevant relationships. E.I.Z. disclosed no relevant relationships. G.A. disclosed no relevant relationships. C.M. disclosed no relevant relationships. R.M. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: disclosed money paid to author for employment from Therapanacea. Other relationships: disclosed no relevant relationships. N. Bus disclosed no relevant relationships. N.J. disclosed no relevant relationships. A.M. disclosed no relevant relationships. T.H.H. disclosed no relevant relationships. L.M.C. disclosed no relevant relationships. N. Benmostefa disclosed no relevant relationships. L.M. disclosed no relevant relationships. A.T.D.X. disclosed no relevant relationships. N.P. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: disclosed money paid to author for consultancy from Safran, employment from Therapanacea, and royalties from Intrasense; disclosed patents issued from Ecole Centrale Supelec; patents licensed from Intrasence, Therapanacea, and Olea; and royalties from Intrasense, Therapanacea, and Olea. Other relationships: disclosed no relevant relationships. M.P.R. disclosed no relevant relationships.
Références
PLoS One. 2016 Mar 01;11(3):e0149240
pubmed: 26930658
Semin Arthritis Rheum. 2008 Feb;37(4):223-35
pubmed: 17692364
Clin Radiol. 1994 Apr;49(4):236-40
pubmed: 8162678
Radiology. 2017 Oct;285(1):270-278
pubmed: 28493789
Ann Rheum Dis. 2016 Feb;75(2):374-81
pubmed: 25452309
Arthritis Rheum. 2013 Nov;65(11):2737-47
pubmed: 24122180
Radiology. 2013 Mar;266(3):936-44
pubmed: 23220902
IEEE Trans Inf Technol Biomed. 2012 Jul;16(4):665-75
pubmed: 22588617
Ann Rheum Dis. 2012 Aug;71(8):1355-60
pubmed: 22615460
IEEE Trans Pattern Anal Mach Intell. 2017 Dec;39(12):2481-2495
pubmed: 28060704
Chest. 1998 Dec;114(6):1623-9
pubmed: 9872198
Semin Arthritis Rheum. 2014 Oct;44(2):208-19
pubmed: 24931517
Clin Exp Rheumatol. 2010 Sep-Oct;28(5 Suppl 62):S26-35
pubmed: 21050542
J Rheumatol. 1988 Feb;15(2):202-5
pubmed: 3361530
Ann Rheum Dis. 2010 Oct;69(10):1809-15
pubmed: 20551155
Eur Respir J. 2018 Sep 17;52(3):
pubmed: 30139770
PLoS One. 2016 Dec 29;11(12):e0166550
pubmed: 28033372
Acta Radiol. 2003 May;44(3):258-64
pubmed: 12751995
BMC Med Imaging. 2015 Aug 12;15:29
pubmed: 26263899
Acad Radiol. 2010 Feb;17(2):146-56
pubmed: 19931472
J Comput Assist Tomogr. 2011 Sep-Oct;35(5):596-601
pubmed: 21926855
Am J Respir Crit Care Med. 2008 Jun 1;177(11):1248-54
pubmed: 18369202
Comput Med Imaging Graph. 2012 Apr;36(3):227-38
pubmed: 21803548
Chest. 2007 Mar;131(3):672-681
pubmed: 17356079
Am J Respir Crit Care Med. 2011 Mar 15;183(6):788-824
pubmed: 21471066
Med Image Anal. 2017 Dec;42:60-88
pubmed: 28778026
Chest. 2008 Aug;134(2):358-367
pubmed: 18641099
IEEE Trans Med Imaging. 2013 Apr;32(4):797-808
pubmed: 23340591
Acad Radiol. 2018 Nov;25(11):1472-1480
pubmed: 29606338
Lancet Respir Med. 2018 Feb;6(2):138-153
pubmed: 29154106
Rheumatology (Oxford). 2013 Jan;52(1):155-60
pubmed: 23065360
Presse Med. 2014 Oct;43(10 Pt 2):e329-43
pubmed: 25217474