Heart and bladder detection and segmentation on FDG PET/CT by deep learning.
Deep learning
FDG PET/CT
Physiological noise
Segmentation
Journal
BMC medical imaging
ISSN: 1471-2342
Titre abrégé: BMC Med Imaging
Pays: England
ID NLM: 100968553
Informations de publication
Date de publication:
30 03 2022
30 03 2022
Historique:
received:
14
07
2021
accepted:
22
03
2022
entrez:
31
3
2022
pubmed:
1
4
2022
medline:
2
4
2022
Statut:
epublish
Résumé
Positron emission tomography (PET)/ computed tomography (CT) has been extensively used to quantify metabolically active tumors in various oncology indications. However, FDG-PET/CT often encounters false positives in tumor detection due to A deep learning based approach is proposed to segment the heart and bladder on whole body PET/CT automatically. Two 3D U-Nets were developed separately to segment the heart and bladder, where each network receives the PET and CT as a multi-modal input. Data sets were obtained from retrospective clinical trials and include 575 PET/CT for heart segmentation and 538 for bladder segmentation. The models were evaluated on a test set from an independent trial and achieved a Dice Similarity Coefficient (DSC) of 0.96 for heart segmentation and 0.95 for bladder segmentation, Average Surface Distance (ASD) of 0.44 mm on heart and 0.90 mm on bladder. This methodology could be a valuable component to the FDG-PET/CT data processing chain by removing FDG physiological noise associated with heart and/or bladder accumulation prior to image analysis by manual, semi- or automated tumor analysis methods.
Identifiants
pubmed: 35354384
doi: 10.1186/s12880-022-00785-7
pii: 10.1186/s12880-022-00785-7
pmc: PMC8977865
doi:
Substances chimiques
Fluorodeoxyglucose F18
0Z5B2CJX4D
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
58Informations de copyright
© 2022. The Author(s).
Références
Med Biol Eng Comput. 2017 Jun;55(6):897-908
pubmed: 27638108
Comput Biol Med. 2014 Jul;50:76-96
pubmed: 24845019
Insights Imaging. 2011 Dec;2(6):679-698
pubmed: 22347986
Radiographics. 2017 Mar-Apr;37(2):577-594
pubmed: 28287942
Med Phys. 2008 Aug;35(8):3711-21
pubmed: 18777930
PLoS One. 2019 Jan 9;14(1):e0210224
pubmed: 30625203
J Digit Imaging. 2020 Aug;33(4):888-894
pubmed: 32378059
Biomed Res Int. 2020 Feb 25;2020:9746716
pubmed: 32185229
Proc SPIE Int Soc Opt Eng. 2018 Feb;10578:
pubmed: 30197464
Annu Int Conf IEEE Eng Med Biol Soc. 2011;2011:8479-82
pubmed: 22256316
Ann Saudi Med. 2011 Jan-Feb;31(1):3-13
pubmed: 21245592
J Clin Oncol. 2017 Nov 1;35(31):3529-3537
pubmed: 28796588
J Nucl Med. 2021 Jan;62(1):30-36
pubmed: 32532925
Front Cardiovasc Med. 2020 Mar 05;7:25
pubmed: 32195270
Med Image Anal. 2019 Dec;58:101537
pubmed: 31446280
Comput Biol Med. 2016 Apr 1;71:77-85
pubmed: 26897070
Br Med Bull. 2016 Dec;120(1):55-74
pubmed: 27613996
AJR Am J Roentgenol. 2010 Dec;195(6):1397-403
pubmed: 21098201
Phys Med Biol. 2021 Mar 04;66(6):065012
pubmed: 33666176
Med Phys. 2009 Oct;36(10):4349-58
pubmed: 19928065
Artif Intell Med. 2019 Mar;94:67-78
pubmed: 30871684
J Nucl Med. 2006 Jun;47(6):1059-66
pubmed: 16741317
Med Image Anal. 2013 Dec;17(8):929-45
pubmed: 23837967
J Nucl Med Technol. 2014 Mar;42(1):5-13
pubmed: 24503347
Radiother Oncol. 2003 Dec;69(3):247-50
pubmed: 14644483
Recent Results Cancer Res. 2013;187:351-69
pubmed: 23179888
Acad Radiol. 2014 May;21(5):675-84
pubmed: 24703482
Annu Int Conf IEEE Eng Med Biol Soc. 2020 Jul;2020:1536-1539
pubmed: 33018284
J Clin Med. 2020 Jul 17;9(7):
pubmed: 32709049
Blood. 2018 Mar 29;131(13):1456-1463
pubmed: 29437590