Detail
Article
Online article
FT
Medvik - BMC
  • Something wrong with this record ?

MRI texture features as biomarkers to predict MGMT methylation status in glioblastomas

P. Korfiatis, TL. Kline, L. Coufalova, DH. Lachance, IF. Parney, RE. Carter, JC. Buckner, BJ. Erickson,

. 2016 ; 43 (6) : 2835.

Language English Country United States

Document type Journal Article

Persistent link   https://www.medvik.cz/link/bmc17013788

PURPOSE: Imaging biomarker research focuses on discovering relationships between radiological features and histological findings. In glioblastoma patients, methylation of the O(6)-methylguanine methyltransferase (MGMT) gene promoter is positively correlated with an increased effectiveness of current standard of care. In this paper, the authors investigate texture features as potential imaging biomarkers for capturing the MGMT methylation status of glioblastoma multiforme (GBM) tumors when combined with supervised classification schemes. METHODS: A retrospective study of 155 GBM patients with known MGMT methylation status was conducted. Co-occurrence and run length texture features were calculated, and both support vector machines (SVMs) and random forest classifiers were used to predict MGMT methylation status. RESULTS: The best classification system (an SVM-based classifier) had a maximum area under the receiver-operating characteristic (ROC) curve of 0.85 (95% CI: 0.78-0.91) using four texture features (correlation, energy, entropy, and local intensity) originating from the T2-weighted images, yielding at the optimal threshold of the ROC curve, a sensitivity of 0.803 and a specificity of 0.813. CONCLUSIONS: Results show that supervised machine learning of MRI texture features can predict MGMT methylation status in preoperative GBM tumors, thus providing a new noninvasive imaging biomarker.

References provided by Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc17013788
003      
CZ-PrNML
005      
20170418103350.0
007      
ta
008      
170413s2016 xxu f 000 0|eng||
009      
AR
024    7_
$a 10.1118/1.4948668 $2 doi
035    __
$a (PubMed)27277032
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxu
100    1_
$a Korfiatis, Panagiotis $u Department of Radiology, Mayo Clinic, 200 1st Street SW, Rochester, Minnesota 55905.
245    10
$a MRI texture features as biomarkers to predict MGMT methylation status in glioblastomas / $c P. Korfiatis, TL. Kline, L. Coufalova, DH. Lachance, IF. Parney, RE. Carter, JC. Buckner, BJ. Erickson,
520    9_
$a PURPOSE: Imaging biomarker research focuses on discovering relationships between radiological features and histological findings. In glioblastoma patients, methylation of the O(6)-methylguanine methyltransferase (MGMT) gene promoter is positively correlated with an increased effectiveness of current standard of care. In this paper, the authors investigate texture features as potential imaging biomarkers for capturing the MGMT methylation status of glioblastoma multiforme (GBM) tumors when combined with supervised classification schemes. METHODS: A retrospective study of 155 GBM patients with known MGMT methylation status was conducted. Co-occurrence and run length texture features were calculated, and both support vector machines (SVMs) and random forest classifiers were used to predict MGMT methylation status. RESULTS: The best classification system (an SVM-based classifier) had a maximum area under the receiver-operating characteristic (ROC) curve of 0.85 (95% CI: 0.78-0.91) using four texture features (correlation, energy, entropy, and local intensity) originating from the T2-weighted images, yielding at the optimal threshold of the ROC curve, a sensitivity of 0.803 and a specificity of 0.813. CONCLUSIONS: Results show that supervised machine learning of MRI texture features can predict MGMT methylation status in preoperative GBM tumors, thus providing a new noninvasive imaging biomarker.
650    _2
$a nádorové biomarkery $x genetika $7 D014408
650    _2
$a mozek $x diagnostické zobrazování $x chirurgie $7 D001921
650    _2
$a nádory mozku $x diagnostické zobrazování $x genetika $x chirurgie $7 D001932
650    12
$a metylace DNA $7 D019175
650    _2
$a DNA modifikační methylasy $x genetika $7 D015254
650    _2
$a enzymy opravy DNA $x genetika $7 D045643
650    _2
$a glioblastom $x diagnostické zobrazování $x genetika $x chirurgie $7 D005909
650    _2
$a lidé $7 D006801
650    _2
$a magnetická rezonanční tomografie $x metody $7 D008279
650    _2
$a promotorové oblasti (genetika) $7 D011401
650    _2
$a ROC křivka $7 D012372
650    _2
$a retrospektivní studie $7 D012189
650    _2
$a support vector machine $7 D060388
650    _2
$a nádorové supresorové proteiny $x genetika $7 D025521
655    _2
$a časopisecké články $7 D016428
700    1_
$a Kline, Timothy L $u Department of Radiology, Mayo Clinic, 200 1st Street SW, Rochester, Minnesota 55905.
700    1_
$a Coufalova, Lucie $u Department of Radiology, Mayo Clinic, 200 1st Street SW, Rochester, Minnesota 55905; Department of Neurosurgery of First Faculty of Medicine, Charles University in Prague, Military University Hospital, Prague 128 21, Czech Republic; and International Clinical Research Center, St. Anne's University Hospital Brno, Brno 656 91, Czech Republic.
700    1_
$a Lachance, Daniel H $u Department of Neurology, Mayo Clinic, 200 1st Street SW, Rochester, Minnesota 55905.
700    1_
$a Parney, Ian F $u Department of Neurologic Surgery, Mayo Clinic, 200 1st Street SW, Rochester, Minnesota 55905.
700    1_
$a Carter, Rickey E $u Department of Health Sciences Research, Mayo Clinic, 200 1st Street SW, Rochester, Minnesota 55905.
700    1_
$a Buckner, Jan C $u Department of Medical Oncology, Mayo Clinic, 200 1st Street SW, Rochester, Minnesota 55905.
700    1_
$a Erickson, Bradley J $u Department of Radiology, Mayo Clinic, 200 1st Street SW, Rochester, Minnesota 55905.
773    0_
$w MED00003245 $t Medical physics $x 2473-4209 $g Roč. 43, č. 6 (2016), s. 2835
856    41
$u https://pubmed.ncbi.nlm.nih.gov/27277032 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y a $z 0
990    __
$a 20170413 $b ABA008
991    __
$a 20170418103658 $b ABA008
999    __
$a ok $b bmc $g 1200253 $s 974566
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2016 $b 43 $c 6 $d 2835 $i 2473-4209 $m Medical physics $n Med Phys $x MED00003245
LZP    __
$a Pubmed-20170413

Find record

Citation metrics

Archiving options