Cerebral Glioma Grading Using Bayesian Network with Features Extracted from Multiple Modalities of Magnetic Resonance Imaging

Jisu Hu; Wenbo Wu; Bin Zhu; Huiting Wang; Renyuan Liu; Xin Zhang; Ming Li; Yongbo Yang; Jing Yan; Fengnan Niu; Chuanshuai Tian; Kun Wang; Haiping Yu; Weibo Chen; Suiren Wan; Yu Sun; Bing Zhang

doi:10.1371/journal.pone.0153369

Cerebral Glioma Grading Using Bayesian Network with Features Extracted from Multiple Modalities of Magnetic Resonance Imaging

PLoS One. 2016 Apr 14;11(4):e0153369. doi: 10.1371/journal.pone.0153369. eCollection 2016.

Authors

Jisu Hu^{1

2}, Wenbo Wu³, Bin Zhu³, Huiting Wang³, Renyuan Liu³, Xin Zhang³, Ming Li³, Yongbo Yang⁴, Jing Yan⁵, Fengnan Niu⁶, Chuanshuai Tian³, Kun Wang³, Haiping Yu³, Weibo Chen⁷, Suiren Wan¹, Yu Sun¹, Bing Zhang³

Affiliations

¹ The Laboratory for Medical Electronics, School of Biological Sciences and Medical Engineering, Southeast University, Nanjing, Jiangsu, China.
² Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, Jiangsu, China.
³ Department of Radiology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing, Jiangsu, China.
⁴ Department of Neurosurgery, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing, Jiangsu, China.
⁵ Department of Oncology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing, Jiangsu, China.
⁶ Department of Pathology, The Affiliated Drum Tower Hospital of Nanjing University Medical School, Nanjing, Jiangsu, China.
⁷ Philips Healthcare, Shanghai, China.

Abstract

Many modalities of magnetic resonance imaging (MRI) have been confirmed to be of great diagnostic value in glioma grading. Contrast enhanced T1-weighted imaging allows the recognition of blood-brain barrier breakdown. Perfusion weighted imaging and MR spectroscopic imaging enable the quantitative measurement of perfusion parameters and metabolic alterations respectively. These modalities can potentially improve the grading process in glioma if combined properly. In this study, Bayesian Network, which is a powerful and flexible method for probabilistic analysis under uncertainty, is used to combine features extracted from contrast enhanced T1-weighted imaging, perfusion weighted imaging and MR spectroscopic imaging. The networks were constructed using K2 algorithm along with manual determination and distribution parameters learned using maximum likelihood estimation. The grading performance was evaluated in a leave-one-out analysis, achieving an overall grading accuracy of 92.86% and an area under the curve of 0.9577 in the receiver operating characteristic analysis given all available features observed in the total 56 patients. Results and discussions show that Bayesian Network is promising in combining features from multiple modalities of MRI for improved grading performance.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Adult
Aged
Aged, 80 and over
Algorithms
Area Under Curve
Bayes Theorem
Brain Neoplasms / diagnostic imaging
Brain Neoplasms / pathology*
Echo-Planar Imaging
Female
Glioma / diagnostic imaging
Glioma / pathology*
Humans
Likelihood Functions
Magnetic Resonance Imaging
Male
Middle Aged
Neoplasm Grading
ROC Curve
Radiography
Signal-To-Noise Ratio

Associated data

figshare/10.6084/M9.FIGSHARE.1401870

Grants and funding

This work was supported by the National Natural Science Foundation of China (81571040, 81300925, B. Zhang), the Provincial Natural Science Foundation of Jiangsu (2014-2016, BK20131085, B. Zhang), the provincial postdoctoral project (1501076A, B. Zhang), the project of the sixth peak of talented people (WSN-O50, B. Zhang), the Key Project of Nanjing Health Bureau (ZKX14027 B. Zhang), and the Jiangsu Province Medical Key talented people and "the 12th five years plan for China development" (2011-2016, RC2011013, B. Zhang). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Philips Healthcare provided support in the form of salary for author Weibo Chen, but did not have any additional role in the study design, data collection and analysis, decision to publish, or preparation of the manuscript. The specific role of this author is articulated in the ‘author contributions’ section.