MRI Manufacturer Shift and Adaptation: Increasing the Generalizability of Deep Learning Segmentation for MR Images Acquired with Different Scanners.

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
Historique:
received: 08 11 2019
revised: 27 03 2020
accepted: 16 04 2020
entrez: 3 5 2021
pubmed: 4 5 2021
medline: 4 5 2021
Statut: epublish

Résumé

To quantitatively evaluate the generalizability of a deep learning segmentation tool to MRI data from scanners of different MRI manufacturers and to improve the cross-manufacturer performance by using a manufacturer-adaptation strategy. This retrospective study included 150 cine MRI datasets from three MRI manufacturers, acquired between 2017 and 2018 ( The segmentation CNNs exhibited a significant performance drop when applied to datasets from different manufacturers (Dice reduced from 89.7% ± 2.3 [standard deviation] to 68.7% ± 10.8, A segmentation CNN well trained on datasets from one MRI manufacturer may not generalize well to datasets from other manufacturers. The proposed manufacturer adaptation can largely improve the generalizability of a deep learning segmentation tool without additional annotation.

Identifiants

DOI: 10.1148/ryai.2020190195 PMID: 33937833 PMC: PMC8082399
pubmed: 33937833
doi: 10.1148/ryai.2020190195
pmc: PMC8082399
doi:

Types de publication

Journal Article

Langues

eng

Pagination

e190195

Informations de copyright

2020 by the Radiological Society of North America, Inc.

Déclaration de conflit d'intérêts

Disclosures of Conflicts of Interest: W.Y. Activities related to the present article: institution received money from National Key Research and Development Program of China under Grant 2018YFC0116303. Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. L.H. disclosed no relevant relationships. L.X. disclosed no relevant relationships. S.G. disclosed no relevant relationships. F.Y. disclosed no relevant relationships. Y.W. Activities related to the present article: institution received money from National Key Research and Development Program of China under Grant 2018YFC0116303. Activities not related to the present article: disclosed no relevant relationships. Other relationships: disclosed no relevant relationships. Q.T. disclosed no relevant relationships.

Références

Circ Cardiovasc Imaging. 2019 Oct;12(10):e009759
pubmed: 31547690
Acad Radiol. 2004 Feb;11(2):178-89
pubmed: 14974593
IEEE Trans Med Imaging. 2018 Nov;37(11):2453-2462
pubmed: 29993738
Nature. 2015 May 28;521(7553):436-44
pubmed: 26017442
Annu Rev Biomed Eng. 2017 Jun 21;19:221-248
pubmed: 28301734
Radiology. 2020 Mar;294(3):487-489
pubmed: 31891322
Comput Biol Med. 2019 Nov;114:103438
pubmed: 31521902
Radiographics. 2005 Jul-Aug;25(4):1087-99
pubmed: 16009826
Circ Cardiovasc Imaging. 2019 Oct;12(10):e009214
pubmed: 31547689
Radiology. 2019 Jan;290(1):81-88
pubmed: 30299231
IEEE Trans Med Imaging. 2018 Nov;37(11):2514-2525
pubmed: 29994302
J Am Coll Radiol. 2018 Feb;15(2):350-359
pubmed: 29158061
J Cardiovasc Magn Reson. 2018 Sep 14;20(1):65
pubmed: 30217194
J Am Coll Radiol. 2019 Sep;16(9 Pt A):1179-1189
pubmed: 31151893
IEEE Trans Pattern Anal Mach Intell. 2020 Feb 02;PP:
pubmed: 32012000

Auteurs

Wenjun Yan (W)

Biomedical Engineering Center, Fudan University, Shanghai, China (W.Y., Y.W.); Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China (L.H., L.X.); Department of Radiology, Ruijin Hospital, Shanghai Jiaotong University, Shanghai, China (S.G., F.Y.); and Division of Image Processing, Department of Radiology, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands (Q.T.).

Lu Huang (L)

Biomedical Engineering Center, Fudan University, Shanghai, China (W.Y., Y.W.); Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China (L.H., L.X.); Department of Radiology, Ruijin Hospital, Shanghai Jiaotong University, Shanghai, China (S.G., F.Y.); and Division of Image Processing, Department of Radiology, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands (Q.T.).
ORCID: 0000-0003-0067-9423

Liming Xia (L)

Biomedical Engineering Center, Fudan University, Shanghai, China (W.Y., Y.W.); Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China (L.H., L.X.); Department of Radiology, Ruijin Hospital, Shanghai Jiaotong University, Shanghai, China (S.G., F.Y.); and Division of Image Processing, Department of Radiology, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands (Q.T.).

Shengjia Gu (S)

Biomedical Engineering Center, Fudan University, Shanghai, China (W.Y., Y.W.); Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China (L.H., L.X.); Department of Radiology, Ruijin Hospital, Shanghai Jiaotong University, Shanghai, China (S.G., F.Y.); and Division of Image Processing, Department of Radiology, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands (Q.T.).
ORCID: 0000-0001-5840-2422

Fuhua Yan (F)

Biomedical Engineering Center, Fudan University, Shanghai, China (W.Y., Y.W.); Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China (L.H., L.X.); Department of Radiology, Ruijin Hospital, Shanghai Jiaotong University, Shanghai, China (S.G., F.Y.); and Division of Image Processing, Department of Radiology, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands (Q.T.).
ORCID: 0000-0002-5910-1506

Yuanyuan Wang (Y)

Biomedical Engineering Center, Fudan University, Shanghai, China (W.Y., Y.W.); Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China (L.H., L.X.); Department of Radiology, Ruijin Hospital, Shanghai Jiaotong University, Shanghai, China (S.G., F.Y.); and Division of Image Processing, Department of Radiology, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands (Q.T.).

Qian Tao (Q)

Biomedical Engineering Center, Fudan University, Shanghai, China (W.Y., Y.W.); Department of Radiology, Tongji Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan, China (L.H., L.X.); Department of Radiology, Ruijin Hospital, Shanghai Jiaotong University, Shanghai, China (S.G., F.Y.); and Division of Image Processing, Department of Radiology, Leiden University Medical Center, Albinusdreef 2, 2333 ZA Leiden, the Netherlands (Q.T.).

Classifications MeSH