Deep learning-based quantification of PET/CT prostate gland uptake: association with overall survival.
Adult
Aged
Aged, 80 and over
Choline
/ pharmacokinetics
Deep Learning
Fluorine Radioisotopes
/ pharmacokinetics
Humans
Image Interpretation, Computer-Assisted
/ methods
Male
Middle Aged
Positron Emission Tomography Computed Tomography
/ methods
Prognosis
Prostate
/ diagnostic imaging
Prostatic Neoplasms
/ diagnostic imaging
Reproducibility of Results
Survival Analysis
Young Adult
artificial intelligence
convolutional neural network
objective quantification
prostatic neoplasms
Journal
Clinical physiology and functional imaging
ISSN: 1475-097X
Titre abrégé: Clin Physiol Funct Imaging
Pays: England
ID NLM: 101137604
Informations de publication
Date de publication:
Mar 2020
Mar 2020
Historique:
received:
21
05
2019
revised:
10
11
2019
accepted:
22
11
2019
pubmed:
4
12
2019
medline:
28
11
2020
entrez:
4
12
2019
Statut:
ppublish
Résumé
To validate a deep-learning (DL) algorithm for automated quantification of prostate cancer on positron emission tomography/computed tomography (PET/CT) and explore the potential of PET/CT measurements as prognostic biomarkers. Training of the DL-algorithm regarding prostate volume was performed on manually segmented CT images in 100 patients. Validation of the DL-algorithm was carried out in 45 patients with biopsy-proven hormone-naïve prostate cancer. The automated measurements of prostate volume were compared with manual measurements made independently by two observers. PET/CT measurements of tumour burden based on volume and SUV of abnormal voxels were calculated automatically. Voxels in the co-registered The SDI between the automated and the manual volume segmentations was 0·78 and 0·79, respectively. Automated PET/CT measures reflecting total lesion uptake and the relation between volume of abnormal voxels and total prostate volume were significantly associated with overall survival (P = 0·02), whereas age, PSA, and Gleason score were not. Automated PET/CT biomarkers showed good agreement to manual measurements and were significantly associated with overall survival.
Identifiants
pubmed: 31794112
doi: 10.1111/cpf.12611
pmc: PMC7027436
doi:
Substances chimiques
Fluorine Radioisotopes
0
Choline
N91BDP6H0X
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
106-113Subventions
Organisme : Sveriges Regering
ID : ALFGBG-720751
Organisme : Gothenburg University
Organisme : EXINI Diagnostics AB
Informations de copyright
© 2019 The Authors. Clinical Physiology and Functional Imaging published by John Wiley & Sons Ltd on behalf of Scandinavian Society of Clinical Physiology and Nuclear Medicine.
Références
Eur J Nucl Med Mol Imaging. 2008 Aug;35(8):1464-72
pubmed: 18373092
EJNMMI Res. 2017 Dec;7(1):25
pubmed: 28324340
J Nucl Med. 2013 Aug;54(8):1195-201
pubmed: 23785174
Technol Cancer Res Treat. 2018 Jan 1;17:1533034618775530
pubmed: 29804518
Eur J Nucl Med Mol Imaging. 2019 Apr;46(4):921-929
pubmed: 30631911
J Nucl Med. 2006 Aug;47(8):1249-54
pubmed: 16883001
CMAJ. 2014 Nov 4;186(16):1225-34
pubmed: 25349003
IEEE Trans Pattern Anal Mach Intell. 2018 Apr;40(4):834-848
pubmed: 28463186
J Am Coll Radiol. 2018 Feb;15(2):350-359
pubmed: 29158061
Eur J Nucl Med Mol Imaging. 2015 Feb;42(2):328-54
pubmed: 25452219
Radiographics. 2016 Mar-Apr;36(2):481-96
pubmed: 26963458
Eur Urol. 2016 Jul;70(1):161-175
pubmed: 26850970
Eur J Nucl Med Mol Imaging. 2014 Nov;41(11):2158-60
pubmed: 24993455
J Nucl Med. 2015 Aug;56(8):1185-90
pubmed: 26112024
Scand J Urol. 2016 Dec;50(6):420-424
pubmed: 27416104
World J Urol. 2019 Jul;37(7):1255-1261
pubmed: 30374609
BJU Int. 2014 Dec;114(6):818-23
pubmed: 24314065
J Nucl Med. 2016 Oct;57(Suppl 3):49S-54S
pubmed: 27694172
Eur J Nucl Med Mol Imaging. 2018 Jun;45(6):893-897
pubmed: 29468310
Radiology. 2019 Jan;290(1):218-228
pubmed: 30251934
Radiology. 2019 Jan;290(1):52-58
pubmed: 30325282
Radiology. 2019 Jan;290(1):81-88
pubmed: 30299231
Sci Rep. 2017 Nov 13;7(1):15415
pubmed: 29133818