Open AccessPredicting epidermal growth factor receptor gene amplification status in glioblastoma multiforme by quantitative enhancement and necrosis features deriving from conventional magnetic resonance imaging
Author(s) -
Fei Dong,
Qiang Zeng,
Biwang Jiang,
Xinfeng Yu,
Weiwei Wang,
Jingjing Xu,
Jinming Yu,
Qian Li,
Minming Zhang
Publication year - 2018
Publication title -
medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.59
H-Index - 148
eISSN - 1536-5964
pISSN - 0025-7974
DOI - 10.1097/md.0000000000010833
Subject(s) - medicine , receiver operating characteristic , epidermal growth factor receptor , magnetic resonance imaging , glioblastoma , univariate analysis , gene duplication , decision tree , feature (linguistics) , predictive value , gene , pathology , oncology , radiology , cancer research , receptor , multivariate analysis , artificial intelligence , biology , computer science , genetics , linguistics , philosophy
To study whether some of the quantitative enhancement and necrosis features in preoperative conventional MRI (cMRI) had a predictive value for epidermal growth factor receptor (EGFR) gene amplification status in glioblastoma multiforme (GBM). Fifty-five patients with pathologically determined GBMs who underwent cMRI were retrospectively reviewed. The following cMRI features were quantitatively measured and recorded: long and short diameters of the enhanced portion (LDE and SDE), maximum and minimum thickness of the enhanced portion (MaxTE and MinTE), and long and short diameters of the necrotic portion (LDN and SDN). Univariate analysis of each feature and a decision tree model fed with all the features were performed. Area under the receiver operating characteristic (ROC) curve (AUC) was used to assess the performance of features, and predictive accuracy was used to assess the performance of the model. For single feature, MinTE showed the best performance in differentiating EGFR gene amplification negative (wild-type) (nEGFR) GBM from EGFR gene amplification positive (pEGFR) GBM, and it got an AUC of 0.68 with a cut-off value of 2.6 mm. The decision tree model included 2 features MinTE and SDN, and got an accuracy of 0.83 in validation dataset. Our results suggest that quantitative measurement of the features MinTE and SDN in preoperative cMRI had a high accuracy for predicting EGFR gene amplification status in GBM.