Artificial intelligence in Glioblastoma Diagnostics: Integrating MRI, histopathology, and molecular profiling

Gliomas are among the most aggressive and diagnostically challenging brain tumors. Conventional pathways (MRI, histopathology, clinical assessment) have limited sensitivity for early or low-grade disease and introduce delays. Artificial intelligence (AI)-particularly deep learning (e.g., CNNs)-may enhance diagnostic precision and efficiency.

We systematically searched IEEE Xplore, Scopus, Web of Science, and PubMed through July 2025 for studies on AI in brain tumor diagnostics, emphasizing MRI, fMRI, and PET. We examined AI contributions to grading, subtype differentiation, and prediction, including integrations with radiomics, multimodal fusion, transfer learning, and molecular profiling. Records were deduplicated (EndNote 21); two reviewers screened and quality-appraised studies (Newcastle-Ottawa; Cochrane). Owing to heterogeneity, we performed a narrative synthesis.

While AI systems achieve strong performance on public benchmarks (e.g., the Brain Tumor Segmentation [BraTS] Challenge), translation into routine clinical care remains limited. Key barriers include limited model interpretability, cross-site and cross-scanner data heterogeneity, and reduced external generalizability. Inconsistent reporting and the scarcity of prospective, multi-center validation further impede adoption. Moreover, opaque decision pathways and variability in data quality and calibration across institutions undermine reliability and clinician trust.

AI is a promising decision-support adjunct to MRI, histopathology, and molecular profiling, with potential to improve diagnostic accuracy and efficiency. Routine adoption requires prospective multi-center validation with external cohorts, standardized reporting, bias mitigation using diverse datasets, and clinically meaningful explainability, alongside regulatory clearance, workflow integration, clinician training, and post-deployment monitoring. Future work should quantify cost-effectiveness and patient-outcome benefits to justify clinical implementation.