Yiming Li1, Xing Liu1, Kaibin Xu2, Zenghui Qian1, Kai Wang3, Xing Fan1, Shaowu Li1, Yinyan Wang4,5, Tao Jiang6. 1. Beijing Neurosurgical Institute, Capital Medical University, 6 Tiantanxili, Beijing, 100050, China. 2. Institute of Automation, Chinese Academy of Sciences, Beijing, China. 3. Department of Neuroradiology, Beijing Tiantan Hospital, Beijing, China. 4. Department of Neuroradiology, Beijing Tiantan Hospital, Beijing, China. tiantanyinyan@126.com. 5. Department of Neurosurgery, Beijing Tiantan Hospital, Capital Medical University, 6 Tiantanxili, Beijing, 100050, China. tiantanyinyan@126.com. 6. Beijing Neurosurgical Institute, Capital Medical University, 6 Tiantanxili, Beijing, 100050, China. taojiang1964@163.com.
Abstract
OBJECTIVE: To identify the magnetic resonance imaging (MRI) features associated with epidermal growth factor (EGFR) expression level in lower grade gliomas using radiomic analysis. METHODS:270 lower grade glioma patients with known EGFR expression status were randomly assigned into training (n=200) and validation (n=70) sets, and were subjected to feature extraction. Using a logistic regression model, a signature of MRI features was identified to be predictive of the EGFR expression level in lower grade gliomas in the training set, and the accuracy of prediction was assessed in the validation set. RESULTS: A signature of 41 MRI features achieved accuracies of 82.5% (area under the curve [AUC] = 0.90) in the training set and 90.0% (AUC = 0.95) in the validation set. This radiomic signature consisted of 25 first-order statistics or related wavelet features (including range, standard deviation, uniformity, variance), one shape and size-based feature (spherical disproportion), and 15 textural features or related wavelet features (including sum variance, sum entropy, run percentage). CONCLUSIONS: A radiomic signature allowing for the prediction of the EGFR expression level in patients with lower grade glioma was identified, suggesting that using tumour-derived radiological features for predicting genomic information is feasible. KEY POINTS: • EGFR expression status is an important biomarker for gliomas. • EGFR in lower grade gliomas could be predicted using radiogenomic analysis. • A logistic regression model is an efficient approach for analysing radiomic features.
RCT Entities:
OBJECTIVE: To identify the magnetic resonance imaging (MRI) features associated with epidermal growth factor (EGFR) expression level in lower grade gliomas using radiomic analysis. METHODS: 270 lower grade gliomapatients with known EGFR expression status were randomly assigned into training (n=200) and validation (n=70) sets, and were subjected to feature extraction. Using a logistic regression model, a signature of MRI features was identified to be predictive of the EGFR expression level in lower grade gliomas in the training set, and the accuracy of prediction was assessed in the validation set. RESULTS: A signature of 41 MRI features achieved accuracies of 82.5% (area under the curve [AUC] = 0.90) in the training set and 90.0% (AUC = 0.95) in the validation set. This radiomic signature consisted of 25 first-order statistics or related wavelet features (including range, standard deviation, uniformity, variance), one shape and size-based feature (spherical disproportion), and 15 textural features or related wavelet features (including sum variance, sum entropy, run percentage). CONCLUSIONS: A radiomic signature allowing for the prediction of the EGFR expression level in patients with lower grade glioma was identified, suggesting that using tumour-derived radiological features for predicting genomic information is feasible. KEY POINTS: • EGFR expression status is an important biomarker for gliomas. • EGFR in lower grade gliomas could be predicted using radiogenomic analysis. • A logistic regression model is an efficient approach for analysing radiomic features.
Authors: Christian J Herold; Jonathan S Lewin; Andreas G Wibmer; James H Thrall; Gabriel P Krestin; Adrian K Dixon; Stefan O Schoenberg; Rena J Geckle; Ada Muellner; Hedvig Hricak Journal: Radiology Date: 2015-10-13 Impact factor: 11.105
Authors: Philipp Kickingereder; Sina Burth; Antje Wick; Michael Götz; Oliver Eidel; Heinz-Peter Schlemmer; Klaus H Maier-Hein; Wolfgang Wick; Martin Bendszus; Alexander Radbruch; David Bonekamp Journal: Radiology Date: 2016-06-20 Impact factor: 11.105
Authors: Scott C Davis; Kimberley S Samkoe; Julia A O'Hara; Summer L Gibbs-Strauss; Hannah L Payne; P Jack Hoopes; Keith D Paulsen; Brian W Pogue Journal: Acad Radiol Date: 2010-03 Impact factor: 3.173
Authors: X J Qiao; B M Ellingson; H J Kim; D J J Wang; N Salamon; M Linetsky; A R Sepahdari; B Jiang; J J Tian; S R Esswein; T F Cloughesy; A Lai; L Nghiemphu; W B Pope Journal: AJNR Am J Neuroradiol Date: 2014-12-26 Impact factor: 3.825
Authors: A Gupta; R J Young; A D Shah; A D Schweitzer; J J Graber; W Shi; Z Zhang; J Huse; A M P Omuro Journal: Clin Neuroradiol Date: 2014-01-29 Impact factor: 3.649
Authors: Dawn Q Chong; Xin Y Toh; Ivy A W Ho; Kian C Sia; Jennifer P Newman; Yulyana Yulyana; Wai-Hoe Ng; Siang H Lai; Mac M F Ho; Nivedh Dinesh; Chee K Tham; Paula Y P Lam Journal: BMC Cancer Date: 2015-04-11 Impact factor: 4.430
Authors: Olle R Lindberg; Andrew McKinney; Jane R Engler; Gayane Koshkakaryan; Henry Gong; Aaron E Robinson; Andrew J Ewald; Emmanuelle Huillard; C David James; Annette M Molinaro; Joseph T Shieh; Joanna J Phillips Journal: Oncotarget Date: 2016-11-29
Authors: Ji Eun Park; Donghyun Kim; Ho Sung Kim; Seo Young Park; Jung Youn Kim; Se Jin Cho; Jae Ho Shin; Jeong Hoon Kim Journal: Eur Radiol Date: 2019-07-26 Impact factor: 5.315
Authors: Tejus A Bale; Justin T Jordan; Otto Rapalino; Nisha Ramamurthy; Nicholas Jessop; John C DeWitt; Valentina Nardi; Maria Martinez-Lage Alvarez; Matthew Frosch; Tracy T Batchelor; David N Louis; A John Iafrate; Daniel P Cahill; Jochen K Lennerz Journal: Neuro Oncol Date: 2019-05-06 Impact factor: 12.300