A systematic review of brain metastases from lung cancer using magnetic resonance neuroimaging: Clinical and technical aspects

Abstract

Abstract Introduction Brain metastases (BMs) are common in lung cancer (LC) and are associated with poor prognosis. Magnetic resonance imaging (MRI) plays a vital role in the detection, diagnosis and management of BMs. This review summarises recent advances in MRI techniques for BMs from LC. Methods This systematic review was conducted following the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses (PRISMA) guidelines. A comprehensive literature search was conducted in three electronic databases: PubMed, Scopus and the Web of Science. The search was limited to studies published between January 2000 and March 2023. The quality of the included studies was evaluated using appropriate tools for different study designs. A narrative synthesis was carried out to describe the key findings of the included studies. Results Sixty‐five studies were included. Standard MRI sequences such as T1‐weighted (T1w), T2‐weighted (T2w) and fluid‐attenuated inversion recovery (FLAIR) were commonly used. Advanced techniques included perfusion‐weighted imaging (PWI), diffusion‐weighted imaging (DWI) and radiomics analysis. DWI and PWI parameters could distinguish tumour recurrence from radiation necrosis. Radiomics models predicted genetic mutations and the risk of BMs. Diagnostic accuracy was improved with deep learning (DL) approaches. Prognostic factors such as performance status and concurrent chemotherapy impacted survival. Conclusion Advanced MRI techniques and specialised MRI methods have emerging roles in managing BMs from LC. PWI and DWI improve diagnostic accuracy in treated BMs. Radiomics and DL facilitate personalised prognosis and treatment. Magnetic resonance imaging plays a key role in the continuum of care for BMs of patients with LC, from screening to treatment monitoring.

Keywords

• Brain metastases
• deep learning
• lung cancer
• MRI
• radiomics