Whole-Volume Tumor MRI Radiomics for Prognostic Modeling in Endometrial Cancer.
LASSO regression
MRI
endometrial cancer
prognostic modeling
radiomics
Journal
Journal of magnetic resonance imaging : JMRI
ISSN: 1522-2586
Titre abrégé: J Magn Reson Imaging
Pays: United States
ID NLM: 9105850
Informations de publication
Date de publication:
03 2021
03 2021
Historique:
received:
01
09
2020
revised:
30
10
2020
accepted:
30
10
2020
pubmed:
18
11
2020
medline:
15
5
2021
entrez:
17
11
2020
Statut:
ppublish
Résumé
In endometrial cancer (EC), preoperative pelvic MRI is recommended for local staging, while final tumor stage and grade are established by surgery and pathology. MRI-based radiomic tumor profiling may aid in preoperative risk-stratification and support clinical treatment decisions in EC. To develop MRI-based whole-volume tumor radiomic signatures for prediction of aggressive EC disease. Retrospective. A total of 138 women with histologically confirmed EC, divided into training (n Axial oblique T Primary tumors were manually segmented by two radiologists with 4 and 8 years' of experience. Radiomic tumor features were computed and used for prediction of surgicopathologically-verified deep (≥50%) myometrial invasion (DMI), lymph node metastases (LNM), advanced stage (FIGO III + IV), nonendometrioid (NE) histology, and high-grade endometrioid tumors (E3). Corresponding analyses were also conducted using radiomics extracted from the axial oblique image slice depicting the largest tumor area. Logistic least absolute shrinkage and selection operator (LASSO) was applied for radiomic modeling in the training cohort. The diagnostic performances of the radiomic signatures were evaluated by area under the receiver operating characteristic curve in the training (AUC The whole-tumor radiomic signatures yielded AUC MRI-based whole-tumor radiomic signatures yield medium-to-high diagnostic performance for predicting aggressive EC disease. The signatures may aid in preoperative risk assessment and hence guide personalized treatment strategies in EC. 4 TECHNICAL EFFICACY STAGE: 2.
Sections du résumé
BACKGROUND
In endometrial cancer (EC), preoperative pelvic MRI is recommended for local staging, while final tumor stage and grade are established by surgery and pathology. MRI-based radiomic tumor profiling may aid in preoperative risk-stratification and support clinical treatment decisions in EC.
PURPOSE
To develop MRI-based whole-volume tumor radiomic signatures for prediction of aggressive EC disease.
STUDY TYPE
Retrospective.
POPULATION
A total of 138 women with histologically confirmed EC, divided into training (n
FIELD STRENGTH/SEQUENCE
Axial oblique T
ASSESSMENT
Primary tumors were manually segmented by two radiologists with 4 and 8 years' of experience. Radiomic tumor features were computed and used for prediction of surgicopathologically-verified deep (≥50%) myometrial invasion (DMI), lymph node metastases (LNM), advanced stage (FIGO III + IV), nonendometrioid (NE) histology, and high-grade endometrioid tumors (E3). Corresponding analyses were also conducted using radiomics extracted from the axial oblique image slice depicting the largest tumor area.
STATISTICAL TESTS
Logistic least absolute shrinkage and selection operator (LASSO) was applied for radiomic modeling in the training cohort. The diagnostic performances of the radiomic signatures were evaluated by area under the receiver operating characteristic curve in the training (AUC
RESULTS
The whole-tumor radiomic signatures yielded AUC
DATA CONCLUSION
MRI-based whole-tumor radiomic signatures yield medium-to-high diagnostic performance for predicting aggressive EC disease. The signatures may aid in preoperative risk assessment and hence guide personalized treatment strategies in EC.
LEVEL OF EVIDENCE
4 TECHNICAL EFFICACY STAGE: 2.
Identifiants
pubmed: 33200420
doi: 10.1002/jmri.27444
pmc: PMC7894560
doi:
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
928-937Informations de copyright
© 2020 The Authors. Journal of Magnetic Resonance Imaging published by Wiley Periodicals LLC. on behalf of International Society for Magnetic Resonance in Medicine.
Références
PET Clin. 2018 Apr;13(2):289-299
pubmed: 29482755
Br J Radiol. 2019 Dec;92(1104):20190105
pubmed: 31538516
Radiology. 2017 Sep;284(3):748-757
pubmed: 28493790
Abdom Radiol (NY). 2019 Jun;44(6):2021-2029
pubmed: 29926137
Radiology. 2020 May;295(2):328-338
pubmed: 32154773
Eur Radiol. 2019 Feb;29(2):792-805
pubmed: 29995239
Gynecol Oncol. 2013 Jun;129(3):472-7
pubmed: 23474346
Radiother Oncol. 2015 Dec;117(3):559-81
pubmed: 26683800
Oncologist. 2019 Sep;24(9):e880-e890
pubmed: 31186375
Int J Gynecol Cancer. 2018 May;28(4):684-691
pubmed: 29489475
Radiology. 2016 Feb;278(2):563-77
pubmed: 26579733
Lancet Oncol. 2019 Sep;20(9):1273-1285
pubmed: 31345626
J Nucl Med. 2019 Sep;60(Suppl 2):38S-44S
pubmed: 31481588
Int J Gynaecol Obstet. 2014 May;125(2):97-8
pubmed: 24630859
AJR Am J Roentgenol. 2018 Feb;210(2):271-278
pubmed: 29166151
Eur Radiol. 2009 Jul;19(7):1565-74
pubmed: 19194709
Clin Cancer Res. 2011 May 15;17(10):3368-77
pubmed: 21242118
Eur Radiol. 2020 May;30(5):2443-2453
pubmed: 32034487
Int J Gynecol Cancer. 2013 May;23(4):690-7
pubmed: 23518862
Int J Gynecol Cancer. 2015 Mar;25(3):459-66
pubmed: 25628109
J Magn Reson Imaging. 2020 Oct;52(4):1257-1262
pubmed: 32315482
J Magn Reson Imaging. 2018 Dec;48(6):1637-1647
pubmed: 30102441
Int J Gynaecol Obstet. 2009 May;105(2):103-4
pubmed: 19367689
Eur J Radiol. 2017 Jan;86:297-307
pubmed: 27638103
Radiology. 2019 Feb;290(2):479-487
pubmed: 30526358
Front Oncol. 2019 Oct 09;9:1007
pubmed: 31649877
Int J Gynecol Pathol. 2019 Jan;38 Suppl 1:S64-S74
pubmed: 30550484
Acad Radiol. 2020 Mar 28;:
pubmed: 32229081
Curr Oncol Rep. 2016 Apr;18(4):25
pubmed: 26922331
Br J Radiol. 2020 Apr;93(1108):20190948
pubmed: 32101448
CA Cancer J Clin. 2018 Nov;68(6):394-424
pubmed: 30207593