Impact Factor 3.877

The world's most-cited Neurosciences journals

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Neurosci. | doi: 10.3389/fnins.2018.00804

Glioma grading on conventional MR images: a deep learning study with transfer learning

 Yang Yang1, Lin-Feng Yan1, Xin Zhang1, Yu Han1, Hai-Yan Nan1, Yu-Chuan Hu1, Bo Hu1, Song-Lin Yan2, Di Zhao3*,  Wen Wang1* and Guang-Bin Cui1*
  • 1Department of Radiology, Tangdu Hospital, Fourth Military Medical University, China
  • 2Computer Network Information Center (CAS), China
  • 3Institute Of Computing Technology (CAS), China

Background: Accurate glioma grading before surgery is of the utmost importance in treatment planning and prognosis prediction. But previous studies on MRI images were not effective enough. According to the remarkable performance of convolutional neural network (CNN) in medical domain, we hypothesized that a deep learning algorithm can achieve high accuracy in distinguishing the World Health Organization (WHO) low grade and high grade gliomas.
Methods: One hundred and thirteen glioma patients were retrospectively included. Tumor images were segmented with a rectangular region of interest (ROI), which contained about 80% of the tumor. Then, 20% data were randomly selected and leaved out at patient-level as test dataset. AlexNet and GoogLeNet were both trained from scratch and fine-tuned from models that pre-trained on the large scale natural image database, ImageNet, to magnetic resonance images. The classification task was evaluated with five-fold cross-validation (CV) on patient-level split.
Results: The performance measures, including validation accuracy, test accuracy and test area under curve (AUC), averaged from five-fold CV of GoogLeNet which trained from scratch were 0.867, 0.909 and 0.939, respectively. With transfer learning and fine-tuning, better performances were obtained for both AlexNet and GoogLeNet, especially for AlexNet. Meanwhile, GoogLeNet performed better than AlexNet no matter trained from scratch or learned from pre-trained model.
Conclusion: In conclusion, we demonstrated that the application of CNN, especially trained with transfer learning and fine-tuning, to preoperative glioma grading improves the performance, compared with either the performance of traditional machine learning method based on hand-crafted features, or even the CNNs trained from scratch.

Keywords: Convolutional neural network (CNN), Magnetic Resonance Imaging, Glioma grading, transfer learning (TL), deep learning (DL)

Received: 26 Jul 2018; Accepted: 16 Oct 2018.

Edited by:

Feng Liu, Tianjin Medical University General Hospital, China

Reviewed by:

Gang Li, University of North Carolina at Chapel Hill, United States
Jizheng Zhao, Northwest A&F University, China  

Copyright: © 2018 Yang, Yan, Zhang, Han, Nan, Hu, Hu, Yan, Zhao, Wang and Cui. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence:
PhD. Di Zhao, Institute Of Computing Technology (CAS), Beijing, 100190, Beijing Municipality, China, zhaodi@escience.cn
Prof. Wen Wang, Department of Radiology, Tangdu Hospital, Fourth Military Medical University, Xi’an, China, wangwen@fmmu.edu.cn
Prof. Guang-Bin Cui, Department of Radiology, Tangdu Hospital, Fourth Military Medical University, Xi’an, China, cgbtd@126.com