Related Experiment Video
Updated: Jul 13, 2026
17:16
Registered Bioimaging of Nanomaterials for Diagnostic and Therapeutic Monitoring
Published on: December 9, 2010
10.5K
Radiomics-based MRI for predicting Erythropoietin-producing hepatocellular receptor A2 expression and tumor grade in
Xiaoxue Liu1, Jianrui Li1, Xiang Liao1
1Department of Diagnostic Radiology, Affiliated Jinling Hospital, Medical School of Nanjing University, 305#, Eastern Zhongshan Rd, Nanjing, 210002, China.
Neuroradiology
|August 9, 2021
Summary
Radiomics imaging can predict EphA2 expression in diffuse gliomas. This approach also aids in tumor grading, offering valuable insights for glioma prognosis and management.
Area of Science:
- Neuro-oncology
- Radiology
- Biomarker Discovery
Background:
- EphA2 receptor tyrosine kinase is crucial for glioma invasion and linked to poor prognosis.
- Accurate prediction of EphA2 expression and tumor grade is vital for effective glioma management.
Purpose of the Study:
- To develop a radiomics-based imaging index for predicting EphA2 expression in diffuse gliomas.
- To assess the utility of this index for tumor grading.
Main Methods:
- Radiomics features were extracted from pre-operative MRI (T1-weighted, diffusion kurtosis imaging) in 182 diffuse glioma patients.
- Machine learning models were built to predict EphA2 expression and tumor grade.
- EphA2 expression was validated using immunohistochemistry.
Main Results:
- A logistic regression model achieved high performance in predicting EphA2 expression (AUC 0.836/0.724).
- Tumor grading models using radiomics features showed excellent performance (AUC 0.930-0.983).
- Two radiomics features strongly correlated with EphA2 expression and were included in grading models.
Conclusions:
- Radiomics features from diffusion kurtosis MRI can predict EphA2 expression in gliomas.
- This radiomics approach can assist in diffuse glioma tumor grading.
