Radiomics for the noninvasive prediction of the BRAF mutation status in patients with melanoma brain metastases.
MRI
artificial intelligence (AI)
brain tumors
machine learning
radiogenomics
Journal
Neuro-oncology
ISSN: 1523-5866
Titre abrégé: Neuro Oncol
Pays: England
ID NLM: 100887420
Informations de publication
Date de publication:
01 08 2022
01 08 2022
Historique:
pubmed:
23
12
2021
medline:
3
8
2022
entrez:
22
12
2021
Statut:
ppublish
Résumé
The BRAF V600E mutation is present in approximately 50% of patients with melanoma brain metastases and an important prerequisite for response to targeted therapies, particularly BRAF inhibitors. As heterogeneity in terms of BRAF mutation status may occur in melanoma patients, a wild-type extracranial primary tumor does not necessarily rule out a targetable mutation in brain metastases using BRAF inhibitors. We evaluated the potential of MRI radiomics for a noninvasive prediction of the intracranial BRAF mutation status. Fifty-nine patients with melanoma brain metastases from two university brain tumor centers (group 1, 45 patients; group 2, 14 patients) underwent tumor resection with subsequent genetic analysis of the intracranial BRAF mutation status. Preoperative contrast-enhanced MRI was manually segmented and analyzed. Group 1 was used for model training and validation, group 2 for model testing. After radiomics feature extraction, a test-retest analysis was performed to identify robust features prior to feature selection. Finally, the best performing radiomics model was applied to the test data. Diagnostic performances were evaluated using receiver operating characteristic (ROC) analyses. Twenty-two of 45 patients (49%) in group 1, and 8 of 14 patients (57%) in group 2 had an intracranial BRAF V600E mutation. A linear support vector machine classifier using a six-parameter radiomics signature yielded an area under the ROC curve of 0.92 (sensitivity, 83%; specificity, 88%) in the test data. The developed radiomics classifier allows a noninvasive prediction of the intracranial BRAF V600E mutation status in patients with melanoma brain metastases with high diagnostic performance.
Sections du résumé
BACKGROUND
The BRAF V600E mutation is present in approximately 50% of patients with melanoma brain metastases and an important prerequisite for response to targeted therapies, particularly BRAF inhibitors. As heterogeneity in terms of BRAF mutation status may occur in melanoma patients, a wild-type extracranial primary tumor does not necessarily rule out a targetable mutation in brain metastases using BRAF inhibitors. We evaluated the potential of MRI radiomics for a noninvasive prediction of the intracranial BRAF mutation status.
METHODS
Fifty-nine patients with melanoma brain metastases from two university brain tumor centers (group 1, 45 patients; group 2, 14 patients) underwent tumor resection with subsequent genetic analysis of the intracranial BRAF mutation status. Preoperative contrast-enhanced MRI was manually segmented and analyzed. Group 1 was used for model training and validation, group 2 for model testing. After radiomics feature extraction, a test-retest analysis was performed to identify robust features prior to feature selection. Finally, the best performing radiomics model was applied to the test data. Diagnostic performances were evaluated using receiver operating characteristic (ROC) analyses.
RESULTS
Twenty-two of 45 patients (49%) in group 1, and 8 of 14 patients (57%) in group 2 had an intracranial BRAF V600E mutation. A linear support vector machine classifier using a six-parameter radiomics signature yielded an area under the ROC curve of 0.92 (sensitivity, 83%; specificity, 88%) in the test data.
CONCLUSIONS
The developed radiomics classifier allows a noninvasive prediction of the intracranial BRAF V600E mutation status in patients with melanoma brain metastases with high diagnostic performance.
Identifiants
pubmed: 34935978
pii: 6478897
doi: 10.1093/neuonc/noab294
pmc: PMC9340614
doi:
Substances chimiques
BRAF protein, human
EC 2.7.11.1
Proto-Oncogene Proteins B-raf
EC 2.7.11.1
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
1331-1340Informations de copyright
© The Author(s) 2021. Published by Oxford University Press on behalf of the Society for Neuro-Oncology. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.
Références
J Magn Reson Imaging. 2019 Aug;50(2):519-528
pubmed: 30635952
J Neurosci Methods. 2016 May 1;264:47-56
pubmed: 26945974
Neuro Oncol. 2017 Feb 1;19(2):162-174
pubmed: 28391295
Br J Cancer. 2013 Nov 26;109(11):2833-41
pubmed: 24196789
Ann Oncol. 2021 Nov;32(11):1332-1347
pubmed: 34364998
Stat Med. 1996 Feb 28;15(4):361-87
pubmed: 8668867
Neuroimage Clin. 2018 Aug 19;20:537-542
pubmed: 30175040
Handb Clin Neurol. 2018;149:27-42
pubmed: 29307358
Nat Rev Neurol. 2020 Oct;16(10):557-574
pubmed: 32873927
Neuroimage. 2006 Jul 1;31(3):1116-28
pubmed: 16545965
Sci Rep. 2019 Jan 24;9(1):614
pubmed: 30679599
Methods. 2021 Apr;188:112-121
pubmed: 32522530
Radiology. 2016 Feb;278(2):563-77
pubmed: 26579733
Am J Epidemiol. 2007 Mar 15;165(6):710-8
pubmed: 17182981
Mod Pathol. 2011 Jul;24(7):1015-22
pubmed: 21423154
Neuroimage. 2012 Aug 15;62(2):782-90
pubmed: 21979382
Eur J Cancer. 2017 Aug;81:106-115
pubmed: 28623774
Int J Cancer. 2020 Mar 15;146(6):1479-1489
pubmed: 31583684
Sci Rep. 2020 Apr 20;10(1):6623
pubmed: 32313236
Sci Rep. 2020 Jul 23;10(1):12340
pubmed: 32704007
Medicine (Baltimore). 2017 Dec;96(48):e8404
pubmed: 29310328
Hum Brain Mapp. 2019 Dec 1;40(17):4952-4964
pubmed: 31403237
Cancer. 2017 Jun 1;123(S11):2163-2175
pubmed: 28543697
Cancer Res. 2017 Nov 1;77(21):e104-e107
pubmed: 29092951
Cancer. 2019 Nov 1;125(21):3776-3789
pubmed: 31287564
IEEE Trans Med Imaging. 2010 Jun;29(6):1310-20
pubmed: 20378467
Eur Radiol. 2018 Nov;28(11):4514-4523
pubmed: 29761357
Radiology. 2021 Mar;298(3):505-516
pubmed: 33399513
Radiology. 2019 Feb;290(2):479-487
pubmed: 30526358
Neuroimage. 2011 Feb 1;54(3):2033-44
pubmed: 20851191
Neuro Oncol. 2020 Jun 9;22(6):797-805
pubmed: 31956919
Front Oncol. 2020 Dec 08;10:578895
pubmed: 33364192