Format

Send to

Choose Destination
J Digit Imaging. 2017 Oct;30(5):622-628. doi: 10.1007/s10278-017-0009-z.

Residual Deep Convolutional Neural Network Predicts MGMT Methylation Status.

Author information

1
Department of Radiology, Mayo Clinic, 200 1st Street SW, Rochester, MN, 55905, USA.
2
Department of Neurology, Mayo Clinic, 200 1st Street SW, Rochester, MN, 55905, USA.
3
Department of Neurologic Surgery, Mayo Clinic, 200 1st Street SW, Rochester, MN, 55905, USA.
4
Department of Medical Oncology, Mayo Clinic, 200 1st Street SW, Rochester, MN, 55905, USA.
5
Department of Radiology, Mayo Clinic, 200 1st Street SW, Rochester, MN, 55905, USA. bje@mayo.edu.

Abstract

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.

KEYWORDS:

Deep learning; MGMT methylation; MRI

PMID:
28785873
PMCID:
PMC5603430
DOI:
10.1007/s10278-017-0009-z
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Springer Icon for PubMed Central
Loading ...
Support Center