An imaging signature to predict outcome in metastatic colorectal cancer using routine computed tomography scans.
CT scan
Colorectal cancer
Radiomics
Journal
European journal of cancer (Oxford, England : 1990)
ISSN: 1879-0852
Titre abrégé: Eur J Cancer
Pays: England
ID NLM: 9005373
Informations de publication
Date de publication:
01 2022
01 2022
Historique:
received:
15
07
2021
revised:
10
10
2021
accepted:
24
10
2021
pubmed:
18
12
2021
medline:
14
1
2022
entrez:
17
12
2021
Statut:
ppublish
Résumé
Quantitative analysis of computed tomography (CT) scans of patients with metastatic colorectal cancer (mCRC) can identify imaging signatures that predict overall survival (OS). We retrospectively analysed CT images from 1584 mCRC patients on two phase III trials evaluating FOLFOX ± panitumumab (n = 331, 350) and FOLFIRI ± aflibercept (n = 437, 466). In the training set (n = 720), an algorithm was trained to predict OS landmarked from month 2; the output was a signature value on a scale from 0 to 1 (most to least favourable predicted OS). In the validation set (n = 864), hazard ratios (HRs) evaluated the association of the signature with OS using RECIST1.1 as a benchmark of comparison. In the training set, the selected signature combined three features - change in tumour volume, change in tumour spatial heterogeneity, and tumour volume - to predict OS. In the validation set, RECIST1.1 classified patients in three categories: response (n = 166, 19.2%), stable disease (n = 636, 73.6%), and progression (n = 62, 7.2%). The HR was 3.93 (2.79-5.54). Using the same distribution for the signature, the HR was 21.04 (14.88-30.58), showing an incremental prognostic separation. Stable disease by RECIST1.1 was reclassified by the signature along a continuum where patients belonging to the most and least favourable signature quartiles had a median OS of 40.73 (28.49 to NA) months (n = 94) and 7.03 (5.66-7.89) months (n = 166), respectively. A signature combining three imaging features provides early prognostic information that can improve treatment decisions for individual patients and clinical trial analyses.
Sections du résumé
BACKGROUND & AIMS
Quantitative analysis of computed tomography (CT) scans of patients with metastatic colorectal cancer (mCRC) can identify imaging signatures that predict overall survival (OS).
METHODS
We retrospectively analysed CT images from 1584 mCRC patients on two phase III trials evaluating FOLFOX ± panitumumab (n = 331, 350) and FOLFIRI ± aflibercept (n = 437, 466). In the training set (n = 720), an algorithm was trained to predict OS landmarked from month 2; the output was a signature value on a scale from 0 to 1 (most to least favourable predicted OS). In the validation set (n = 864), hazard ratios (HRs) evaluated the association of the signature with OS using RECIST1.1 as a benchmark of comparison.
RESULTS
In the training set, the selected signature combined three features - change in tumour volume, change in tumour spatial heterogeneity, and tumour volume - to predict OS. In the validation set, RECIST1.1 classified patients in three categories: response (n = 166, 19.2%), stable disease (n = 636, 73.6%), and progression (n = 62, 7.2%). The HR was 3.93 (2.79-5.54). Using the same distribution for the signature, the HR was 21.04 (14.88-30.58), showing an incremental prognostic separation. Stable disease by RECIST1.1 was reclassified by the signature along a continuum where patients belonging to the most and least favourable signature quartiles had a median OS of 40.73 (28.49 to NA) months (n = 94) and 7.03 (5.66-7.89) months (n = 166), respectively.
CONCLUSIONS
A signature combining three imaging features provides early prognostic information that can improve treatment decisions for individual patients and clinical trial analyses.
Identifiants
pubmed: 34916122
pii: S0959-8049(21)01187-4
doi: 10.1016/j.ejca.2021.10.029
pmc: PMC10018811
mid: NIHMS1753341
pii:
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
138-147Subventions
Organisme : NCI NIH HHS
ID : P30 CA008748
Pays : United States
Organisme : NCI NIH HHS
ID : R01 CA194783
Pays : United States
Organisme : NCI NIH HHS
ID : P30 CA006516
Pays : United States
Organisme : NCI NIH HHS
ID : U01 CA225431
Pays : United States
Informations de copyright
Copyright © 2021 Elsevier Ltd. All rights reserved.
Références
J Clin Oncol. 2006 Jan 20;24(3):394-400
pubmed: 16421419
J Clin Oncol. 2017 Jun 1;35(16):1786-1794
pubmed: 28291393
Lancet. 2015 May 9;385(9980):1843-52
pubmed: 25862517
J Nucl Med. 2009 May;50 Suppl 1:43S-54S
pubmed: 19403879
J Clin Oncol. 2016 Jun 20;34(18):2157-64
pubmed: 27138577
J Clin Oncol. 2007 May 1;25(13):1760-4
pubmed: 17470866
Sci Rep. 2017 Aug 11;7(1):7952
pubmed: 28801575
Oncotarget. 2016 May 24;7(21):31401-12
pubmed: 27120787
Gut. 2020 Mar;69(3):531-539
pubmed: 31101691
N Engl J Med. 2015 Apr 23;372(17):1598-607
pubmed: 25901426
Cancer Res. 2021 May 1;81(9):2522-2533
pubmed: 33589516
J Natl Cancer Inst. 2020 Sep 1;112(9):902-912
pubmed: 32016387
Acad Radiol. 2007 Dec;14(12):1520-30
pubmed: 18035281
JCO Clin Cancer Inform. 2018 Dec;2:1-12
pubmed: 30652552
J Clin Oncol. 1983 Nov;1(11):710-9
pubmed: 6668489
Ann Oncol. 2014 Jul;25(7):1346-1355
pubmed: 24718886
Stat Med. 2000 Aug 15;19(15):1997-2014
pubmed: 10900448
Eur J Cancer. 2014 Jan;50(2):320-31
pubmed: 24140268
Clin Cancer Res. 2012 Apr 15;18(8):2374-81
pubmed: 22344231
J Clin Oncol. 2012 Jul 20;30(21):2684-90
pubmed: 22689801