Glioma Grading on Conventional MR Images: A Deep Learning Study With Transfer Learning

doi:10.3389/fnins.2018.00804

CORC > 计算技术研究所 > 中国科学院计算技术研究所 > 中国科学院计算技术研究所期刊论文 > 英文

	Glioma Grading on Conventional MR Images: A Deep Learning Study With Transfer Learning
	Hu, Bo 4; Yan, Song-Lin 3; Wang, Wen 4; Zhao, Di 1; Cui, Guang-Bin 4; Ge, Xiang-Wei 2; Zhang, Jin 4; Cheng, Dong-Liang 2; Yang, Yang 4; Yan, Lin-Feng 4
刊名	FRONTIERS IN NEUROSCIENCE
	2018-11-15
卷号	12 页码:10
关键词	deep learning convolutional neural network (CNN) transfer learning glioma grading magnetic resonance imaging (MRI)
ISSN号	1662-453X
DOI	10.3389/fnins.2018.00804
英文摘要	Background: Accurate glioma grading before surgery is of the utmost importance in treatment planning and prognosis prediction. But previous studies on magnetic resonance imaging (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.
资助项目	National Key Research and Development Program of China[2016YFC0107105] ; National Natural Science Foundation of China[61603399]
WOS研究方向	Neurosciences & Neurology
语种	英语
出版者	FRONTIERS MEDIA SA
WOS记录号	WOS:000450198700001
内容类型	期刊论文
源URL	[http://119.78.100.204/handle/2XEOYT63/4329]
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Wen; Zhao, Di; Cui, Guang-Bin
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 2.Fourth Mil Med Univ, Student Brigade, Xian, Shaanxi, Peoples R China 3.Chinese Acad Sci, Comp Network Informat Ctr, Beijing, Peoples R China 4.Fourth Mil Med Univ, Tangdu Hosp, Dept Radiol, Funct & Mol Imaging Key Lab Shaanxi Prov, Xian, Shaanxi, Peoples R China
推荐引用方式 GB/T 7714	Hu, Bo,Yan, Song-Lin,Wang, Wen,et al. Glioma Grading on Conventional MR Images: A Deep Learning Study With Transfer Learning[J]. FRONTIERS IN NEUROSCIENCE,2018,12:10.
APA	Hu, Bo.,Yan, Song-Lin.,Wang, Wen.,Zhao, Di.,Cui, Guang-Bin.,...&Hu, Yu-Chuan.(2018).Glioma Grading on Conventional MR Images: A Deep Learning Study With Transfer Learning.FRONTIERS IN NEUROSCIENCE,12,10.
MLA	Hu, Bo,et al."Glioma Grading on Conventional MR Images: A Deep Learning Study With Transfer Learning".FRONTIERS IN NEUROSCIENCE 12(2018):10.