Cerebral Glioma Grading Using Bayesian Network with Features Extracted from Multiple Modalities of Magnetic Resonance Imaging.
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 me...
| Main Authors: | , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2016-01-01
|
| Series: | PLoS ONE |
| Online Access: | http://europepmc.org/articles/PMC4831834?pdf=render |
| _version_ | 1819071434525245440 |
|---|---|
| author | 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 |
| author_facet | 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 |
| author_sort | Jisu Hu |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-12-21T17:21:46Z |
| format | Article |
| id | doaj.art-b78f201a2ef9419ba01214381bf2135d |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-12-21T17:21:46Z |
| publishDate | 2016-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-b78f201a2ef9419ba01214381bf2135d2022-12-21T18:56:08ZengPublic Library of Science (PLoS)PLoS ONE1932-62032016-01-01114e015336910.1371/journal.pone.0153369Cerebral Glioma Grading Using Bayesian Network with Features Extracted from Multiple Modalities of Magnetic Resonance Imaging.Jisu HuWenbo WuBin ZhuHuiting WangRenyuan LiuXin ZhangMing LiYongbo YangJing YanFengnan NiuChuanshuai TianKun WangHaiping YuWeibo ChenSuiren WanYu SunBing ZhangMany 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.http://europepmc.org/articles/PMC4831834?pdf=render |
| spellingShingle | 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 Cerebral Glioma Grading Using Bayesian Network with Features Extracted from Multiple Modalities of Magnetic Resonance Imaging. PLoS ONE |
| title | Cerebral Glioma Grading Using Bayesian Network with Features Extracted from Multiple Modalities of Magnetic Resonance Imaging. |
| title_full | Cerebral Glioma Grading Using Bayesian Network with Features Extracted from Multiple Modalities of Magnetic Resonance Imaging. |
| title_fullStr | Cerebral Glioma Grading Using Bayesian Network with Features Extracted from Multiple Modalities of Magnetic Resonance Imaging. |
| title_full_unstemmed | Cerebral Glioma Grading Using Bayesian Network with Features Extracted from Multiple Modalities of Magnetic Resonance Imaging. |
| title_short | Cerebral Glioma Grading Using Bayesian Network with Features Extracted from Multiple Modalities of Magnetic Resonance Imaging. |
| title_sort | cerebral glioma grading using bayesian network with features extracted from multiple modalities of magnetic resonance imaging |
| url | http://europepmc.org/articles/PMC4831834?pdf=render |
| work_keys_str_mv | AT jisuhu cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT wenbowu cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT binzhu cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT huitingwang cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT renyuanliu cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT xinzhang cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT mingli cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT yongboyang cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT jingyan cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT fengnanniu cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT chuanshuaitian cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT kunwang cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT haipingyu cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT weibochen cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT suirenwan cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT yusun cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging AT bingzhang cerebralgliomagradingusingbayesiannetworkwithfeaturesextractedfrommultiplemodalitiesofmagneticresonanceimaging |