Data Management And Sharing System of China National Clinical Research Center for Neurological Diseases
MRI features predict p53 status in lower-grade gliomas via a machine-learning approach
First author：Li Yiming,Qian Zenghui
Corresponding author：Jiang Tao,Liu Xing,Wang Yinyan
essential_information
- Person in charge：Li Yiming,Qian Zenghui
- Data Sources： OTHERS
- Number of papers：OTHERS20190649
- Published time：2017-10-29
2017-10-29
Published articles
Journal：Neuroimage Clin.
Publication type: Research Article
IF(IF): 3.943
PMID: 29527478 Link To Pubmed Full text Download
Background And Purpose
Method
Preoperative MR images were retrospectively obtained from 272 patients with primary grade II/III gliomas. The patients were randomly allocated in a 2:1 ratio to a training (n = 180) or validation (n = 92) set. A total of 431 radiomic features were extracted from each patient. The lest absolute shrinkage and selection operator (LASSO) method was used for feature selection and radiomic signature construction. Subsequently, a machine-learning model to predict p53 status was established using the selected features and a Support Vector Machine classifier. The predictive performance of all individual features and the model was calculated using receiver operating characteristic curves in both the training and validation sets.
Conclusion
These results demonstrate that MR image texture features are predictive of p53 mutation status in lower-grade gliomas. Thus, our procedure can be conveniently used to facilitate presurgical molecular pathological diagnosis.
Main results
The p53-related radiomic signature was built using the LASSO algorithm; this procedure consisted of four first-order statistics or related wavelet features (including Maximum, Median, Minimum, and Uniformity), a shape and size-based feature (Spherical Disproportion), and ten textural features or related wavelet features (including Correlation, Run Percentage, and Sum Entropy). The prediction accuracies based on the area under the curve were 89.6% in the training set and 76.3% in the validation set, which were better than individual features.