Integrating MRI radiomics and transcriptomics to predict IDH mutation status and prognosis in glioma - PubMed
3 hours ago
- #Radiomics
- #Transcriptomics
- #Glioma Prognosis
- Study integrates MRI radiomics and transcriptomics to predict IDH mutation status and prognosis in glioma.
- Used 61 MRI files from TCIA and an external set of 66 patients for training, validation, and external validation.
- Extracted 1,037 radiomic features from manually delineated ROIs and applied statistical tests and LASSO regression for feature reduction.
- Identified nine IDH mutation-related radiomic features for predictive modeling, which also showed prognostic value in Cox regression.
- Differential analysis revealed eight key genes linked to glioma progression and IDH mutations, validated via Western blot, immune infiltration, and spatial transcriptomics.
- Radiomic features (e.g., RF3, RF7, RF4) correlated with key IDH mutation genes and MMP9, indicating potential biological interactions.
- Conclusions highlight the value of radiomics combined with bioinformatics for predicting IDH mutations and understanding glioma genetics.