Automatized Hepatic Tumor Volume Analysis of Neuroendocrine Liver Metastases by Gd-EOB MRI-A Deep-Learning Model to Support Multidisciplinary Cancer Conference Decision-Making.
MRI
automatized quantification
deep learning
liver metastases
multidisciplinary cancer conference
neuroendocrine neoplasms
Journal
Cancers
ISSN: 2072-6694
Titre abrégé: Cancers (Basel)
Pays: Switzerland
ID NLM: 101526829
Informations de publication
Date de publication:
31 May 2021
31 May 2021
Historique:
received:
06
05
2021
revised:
22
05
2021
accepted:
25
05
2021
entrez:
2
6
2021
pubmed:
3
6
2021
medline:
3
6
2021
Statut:
epublish
Résumé
Rapid quantification of liver metastasis for diagnosis and follow-up is an unmet medical need in patients with secondary liver malignancies. We present a 3D-quantification model of neuroendocrine liver metastases (NELM) using gadoxetic-acid (Gd-EOB)-enhanced MRI as a useful tool for multidisciplinary cancer conferences (MCC). Manual 3D-segmentations of NELM and livers (149 patients in 278 Gd-EOB MRI scans) were used to train a neural network ( Internal validation of the model's accuracy showed a high overlap for NELM and livers (Matthew's correlation coefficient (φ): 0.76/0.95, respectively) with higher φ in larger NELM volume (φ = 0.80 vs. 0.71; The model shows high accuracy in 3D-quantification of NELM and HTL in Gd-EOB-MRI. The model's measurements correlated well with MCC's evaluation of therapeutic response.
Sections du résumé
BACKGROUND
BACKGROUND
Rapid quantification of liver metastasis for diagnosis and follow-up is an unmet medical need in patients with secondary liver malignancies. We present a 3D-quantification model of neuroendocrine liver metastases (NELM) using gadoxetic-acid (Gd-EOB)-enhanced MRI as a useful tool for multidisciplinary cancer conferences (MCC).
METHODS
METHODS
Manual 3D-segmentations of NELM and livers (149 patients in 278 Gd-EOB MRI scans) were used to train a neural network (
RESULTS
RESULTS
Internal validation of the model's accuracy showed a high overlap for NELM and livers (Matthew's correlation coefficient (φ): 0.76/0.95, respectively) with higher φ in larger NELM volume (φ = 0.80 vs. 0.71;
CONCLUSION
CONCLUSIONS
The model shows high accuracy in 3D-quantification of NELM and HTL in Gd-EOB-MRI. The model's measurements correlated well with MCC's evaluation of therapeutic response.
Identifiants
pubmed: 34072865
pii: cancers13112726
doi: 10.3390/cancers13112726
pmc: PMC8199286
pii:
doi:
Types de publication
Journal Article
Langues
eng
Références
J Natl Cancer Inst. 2000 Feb 2;92(3):179-81
pubmed: 10655425
Radiology. 2019 Dec;293(3):531-540
pubmed: 31660801
J Clin Oncol. 2005 Jan 1;23(1):70-8
pubmed: 15625361
Nat Med. 2019 Mar;25(3):433-438
pubmed: 30742121
Diagn Interv Imaging. 2018 Feb;99(2):73-81
pubmed: 29339222
Oncologist. 2019 Nov;24(11):e1082-e1090
pubmed: 30910869
Nat Rev Endocrinol. 2020 Oct;16(10):590-607
pubmed: 32839579
Cancers (Basel). 2020 Jun 07;12(6):
pubmed: 32517291
Cancers (Basel). 2019 Jun 14;11(6):
pubmed: 31207914
J Natl Cancer Inst. 2013 Jan 16;105(2):113-21
pubmed: 23274388
JMIR Med Inform. 2019 Aug 16;7(3):e10010
pubmed: 31420959
Radiology. 2013 Aug;268(2):390-9
pubmed: 23533288
Eur J Cancer. 2009 Jan;45(2):228-47
pubmed: 19097774
Diagn Interv Radiol. 2016 May-Jun;22(3):201-6
pubmed: 27015320
J Clin Oncol. 2008 Jun 20;26(18):3063-72
pubmed: 18565894
Acta Radiol. 2021 Mar;62(3):291-301
pubmed: 32517533
Curr Oncol. 2012 Aug;19(4):e232-8
pubmed: 22876151
Radiology. 2019 Jul;292(1):110-111
pubmed: 31094652
Radiology. 2017 Mar;282(3):708-716
pubmed: 28076722
AJR Am J Roentgenol. 2014 May;202(5):W487-95
pubmed: 24758684
CA Cancer J Clin. 2018 Nov;68(6):471-487
pubmed: 30295930
J Comput Assist Tomogr. 2016 Sep-Oct;40(5):717-22
pubmed: 27636124
Cancer Manag Res. 2018 Nov 13;10:5629-5638
pubmed: 30519109
BMC Genomics. 2020 Jan 2;21(1):6
pubmed: 31898477
JAMA Oncol. 2017 Oct 1;3(10):1335-1342
pubmed: 28448665
Acad Radiol. 2020 Jun 29;:
pubmed: 32616417
Pancreas. 2017 Oct;46(9):1219-1224
pubmed: 28902795
Nat Med. 2019 Jun;25(6):954-961
pubmed: 31110349
AJR Am J Roentgenol. 2003 Sep;181(3):809-17
pubmed: 12933487
Neuroendocrinology. 2017;104(1):1-10
pubmed: 26562558
World J Gastroenterol. 2019 Feb 14;25(6):672-682
pubmed: 30783371
Oncotarget. 2017 May 3;8(42):71699-71708
pubmed: 29069739
Neuroendocrinology. 2012;95(2):157-76
pubmed: 22262022
Eur J Gastroenterol Hepatol. 2013 Feb;25(2):232-8
pubmed: 23108416
Endocrine. 2020 Jan;67(1):243-251
pubmed: 31564038
Lancet Oncol. 2019 Jul;20(7):938-947
pubmed: 31201137
Cancers (Basel). 2020 Mar 30;12(4):
pubmed: 32235636
J Am Coll Radiol. 2020 Nov;17(11):1475-1484
pubmed: 32721409
Acta Radiol. 2015 Dec;56(12):1419-27
pubmed: 25406435
Int J Comput Assist Radiol Surg. 2013 Jul;8(4):607-20
pubmed: 23588509
Sci Rep. 2018 Oct 30;8(1):16016
pubmed: 30375454
Eur J Cancer. 2016 Jul;62:132-7
pubmed: 27189322
AJR Am J Roentgenol. 2011 Aug;197(2):W204-20
pubmed: 21785044
Eur Radiol. 2019 Jul;29(7):3348-3357
pubmed: 31093705
World J Gastrointest Oncol. 2019 Dec 15;11(12):1218-1230
pubmed: 31908726
Ann Transl Med. 2013 Apr;1(1):6
pubmed: 25332951
Eur Radiol. 2019 Jul;29(7):3338-3347
pubmed: 31016442
Cancers (Basel). 2019 Sep 18;11(9):
pubmed: 31540509
Int J Cancer. 2008 Oct 1;123(7):1556-64
pubmed: 18646189
Int J Colorectal Dis. 2016 Nov;31(11):1739-1749
pubmed: 27682648
J Gastroenterol. 2015 Jan;50(1):58-64
pubmed: 24499825
Br J Cancer. 2019 Oct;121(7):537-544
pubmed: 31477779
Eur J Radiol. 2012 Oct;81(10):2820-5
pubmed: 22236704
Eur J Radiol. 2012 Sep;81(9):2037-41
pubmed: 21719224
Endocr Rev. 2020 Apr 1;41(2):
pubmed: 31555796
Eur Radiol. 2019 May;29(5):2698-2705
pubmed: 30402706
Clin Radiol. 2016 Sep;71(9):863-8
pubmed: 27345612
Br J Cancer. 2018 Jan;118(2):181-188
pubmed: 29161241
Radiology. 2020 Jun;295(3):626-637
pubmed: 32255417
Semin Ultrasound CT MR. 2016 Dec;37(6):533-548
pubmed: 27986172
Hepatol Res. 2016 Aug;46(9):853-61
pubmed: 26750497
Rofo. 2010 Dec;182(12):1082-90
pubmed: 21104596
Neuroendocrinology. 2017 Mar 30;105(3):212-244
pubmed: 28355596
Eur Radiol. 2020 Dec;30(12):6593-6602
pubmed: 32601948
Abdom Radiol (NY). 2018 Sep;43(9):2329-2339
pubmed: 29470627
Med Sci Monit. 2012 May;18(5):MT33-40
pubmed: 22534718
Acta Radiol. 2014 Jun;55(5):532-42
pubmed: 23982322
Neuroendocrinology. 2018;106(1):74-88
pubmed: 28728155