Residual Deep Convolutional Neural Network Predicts MGMT Methylation Status.
Predicting methylation of the O6-methylguanine methyltransferase (MGMT) gene status utilizing MRI imaging is of high importance since it is a predictor of response and prognosis in brain tumors. In this study, we compare three different residual deep neural network (ResNet) architectures to evaluate...
| Publicado en: | Journal of Digital Imaging Vol. 30; no. 5; pp. 622 - 629 |
|---|---|
| Autores principales: | , , , , , |
| Formato: | diagnostic images research tables/charts Journal Article |
| Publicado: |
Springer Nature
Oct2017
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=125205817&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 125205817 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 08971889 DOQ jtl: Journal of Digital Imaging issn: 08971889 maglogo: N pubinfo: dt: Oct2017 vid: 30 iid: 5 pid: 237 pub: Springer Nature place: New York, New York artinfo: ui: 125205817 125205817 144080590 125205817 10.1007/s10278-017-0009-z 125205817 ppf: 622 ppct: 7 formats: fmt: @attributes: type: P tig: atl: Residual Deep Convolutional Neural Network Predicts MGMT Methylation Status. aug: au: Korfiatis, Panagiotis Kline, Timothy Lachance, Daniel Parney, Ian Buckner, Jan Erickson, Bradley affil: Department of Radiology , Mayo Clinic , 200 1st Street SW Rochester 55905 USA sug: subj: Neural Networks (Computer) Brain Neoplasms Physiopathology Methylation Models, Theoretical Tumor Markers, Biological Comparative Studies Descriptive Statistics P-Value Human ab: Predicting methylation of the O6-methylguanine methyltransferase (MGMT) gene status utilizing MRI imaging is of high importance since it is a predictor of response and prognosis in brain tumors. In this study, we compare three different residual deep neural network (ResNet) architectures to evaluate their ability in predicting MGMT methylation status without the need for a distinct tumor segmentation step. We found that the ResNet50 (50 layers) architecture was the best performing model, achieving an accuracy of 94.90% (+/− 3.92%) for the test set (classification of a slice as no tumor, methylated MGMT, or non-methylated). ResNet34 (34 layers) achieved 80.72% (+/− 13.61%) while ResNet18 (18 layers) accuracy was 76.75% (+/− 20.67%). ResNet50 performance was statistically significantly better than both ResNet18 and ResNet34 architectures ( p < 0.001). We report a method that alleviates the need of extensive preprocessing and acts as a proof of concept that deep neural architectures can be used to predict molecular biomarkers from routine medical images. pubtype: Academic Journal doctype: diagnostic images research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|