Artificial intelligence and machine learning for magnetic nanoparticles and nanocarriers in cancer imaging, drug delivery, and magnetic control: a systematic review

We reviewed artificial intelligence and machine learning in magnetic resonance imaging-visible magnetic nanoparticles, nanocarriers, and systems for imaging, drug delivery, hyperthermia, targeting, transport, and control. Using "preferred reporting items for systematic reviews and meta-analyses (PRISMA) 2020" methods, 2,283 records from seven databases yielded 65 studies. Predicted outcomes were colloidal stability, toxicity, uptake, magnetic descriptors, specific absorption rate, relaxivity, MRI signal, superparamagnetic iron oxide nanoparticle (SPION) quantification, drug release, biodistribution, and magnetic navigation. Evidence was strongest in bounded tasks: magnetic-property and relaxivity prediction, image-derived SPION mapping, hyperthermia modelling, and controlled magnetic transport. Most studies optimised isolated endpoints rather than integrating stability, MRI visibility, drug loading, release, tumour delivery, safety, and therapeutic response. External validation across datasets, laboratories, particle batches, biological models, scanners, and patient cohorts remains limited.

Abstract from PubMed Central (PMID 42936742, PMC13701153). This entry was added automatically by our daily literature monitor because it matches the topics we follow; read the full paper at the original source.