Radiomics and its application to neuro-oncology: A narrative review of advances, clinical application and implementation challenges.

Objectives

A narrative review of the literature was carried out in PubMed, Scopus and Web of Science (2012-2024) to explore the role of radiomics and artificial intelligence (AI) in neuro-oncology, with an emphasis on its diagnostic, prognostic, and therapeutic potential. KEY

Findings

Radiomics allows automated extraction of quantitative characteristics of medical images (MRI, CT, and PET/CT), identifying patterns not visible to the human eye. It has been shown to be useful in pre-surgical classification of gliomas, survival prediction and differentiation between tumour progression and pseudo-progression. Integration with deep learning algorithms may improve diagnostic accuracy and facilitate patient stratification based on molecular biomarkers such as isocitrate dehydrogenase (IDH) and Methylguanine-DNA methyltransferase (MGMT). Radiogenomics links image phenotypes with genetic alterations, enhancing personalised medicine. However, limitations persist due to the lack of standardisation of protocols, variability in segmentation, and the scarcity of validated multicentre studies.

Conclusion

Radiomics represents a promising tool to optimise the diagnostic and therapeutic approach in neuro-oncology. However, prospective validation and methodological standardisation are required before definitive integration into clinical practice. PLAIN LANGUAGE SUMMARY Brain tumours can be difficult to diagnose and treat because they often behave differently from one person to another. This study reviewed published research on radiomics, a method that uses artificial intelligence to analyse hidden patterns in medical images such as MRI, CT, and PET scans. This study found that radiomics may help classify brain tumours, predict outcomes, identify treatment-related changes, and support more personalised care, although important challenges remain around standardisation and validation. This matters because more accurate and personalised approaches could help improve diagnosis, treatment planning, and monitoring for people with brain tumours.