Related Experiment Video
Updated: Sep 9, 2025
06:32
Evaluation of Biomarkers in Glioma by Immunohistochemistry on Paraffin-Embedded 3D Glioma Neurosphere Cultures
Published on: January 9, 2019
8.0K
Advanced MRI, Radiomics and Radiogenomics in Unravelling Incidental Glioma Grading and Genetic Status: Where Are We?
Alessia Guarnera1, Tamara Ius2, Andrea Romano1
1Neuroradiology Unit, NESMOS (Neuroscience, Mental Health and Sensory Organs) Department, Sant'Andrea Hospital, La Sapienza University, Via di Grottarossa, 1035-1039, 00189 Rome, Italy.
Medicina (Kaunas, Lithuania)
|August 28, 2025
Summary
Advanced MRI techniques and artificial intelligence (AI) aid in diagnosing gliomas by predicting genetic status. AI models show promise in glioma management, but standardization and reproducibility challenges remain.
Area of Science:
- Neuroradiology
- Oncology
- Medical Imaging
Background:
- The 2021 WHO classification highlights molecular advances in brain tumour diagnosis.
- Incidental gliomas are increasingly detected via MRI, posing diagnostic and therapeutic challenges.
- Non-invasive identification of glioma genetic profiles and grading is crucial for surgical decisions.
Purpose of the Study:
- To review standard and advanced MRI sequences for differentiating low-grade (iLGGs) from high-grade gliomas (HGGs).
- To provide an overview of AI applications in glioma differential diagnosis.
- To demonstrate how MRI, radiomics, and radiogenomics unravel glioma genetic profiles.
Main Methods:
- Utilizing standard and advanced MRI sequences (DWI/ADC, PWI, MRS, DTI, fMRI).
- Applying Artificial Intelligence (AI) models, including radiomics and radiogenomics.
- Analyzing key glioma biomarkers (IDH, EGFR, TERT, MGMT, p53, H3-K27M, ATRX, Ki67, 1p19).
Main Results:
- AI-driven models demonstrate high accuracy in glioma detection, grading, prognostication, and pre-surgical planning.
- Radiomics and radiogenomics enhance MRI in predicting glioma genetic status and patient outcomes.
- Standard and advanced MRI, coupled with AI, are vital for in vivo glioma assessment.
Conclusions:
- AI, radiomics, and radiogenomics are pivotal in assessing glioma grading and genetic profiles for personalized medicine.
- Addressing challenges in standardization, data, reproducibility, and interpretability is essential for AI adoption.
- Future research focusing on multi-institutional validation, multi-omics integration, and explainable AI will advance AI-based glioma management.
