Swee Qi Pan0000-0002-9657-8311Hum Yan ChaiKhin Wee LaiWun-She YapYi ZhangHye-Young HeoTee Yee Kai2025-09-122025-09-122025-04-1710.1007/s10462-025-11227-5https://dspace-cris.utar.edu.my/handle/123456789/11335This review delves into the transformative role of Artificial Intelligence (AI) in advancing Chemical Exchange Saturation Transfer (CEST) Magnetic Resonance Imaging (MRI), a cutting-edge imaging method for non-invasive biochemical mapping. CEST MRI faces many technical challenges that hinder its clinical adoption. AI-driven approaches have emerged as one of the promising solutions to address some of these limitations. The evolution of AI in CEST MRI is traced from its inception, with pioneering studies in AI-driven image analysis, to current trends reflecting a marked increase in AI-related CEST publications. This review highlights AI's impact on various stages of the CEST MRI pipeline, including accelerated imaging acquisition and reconstruction, improved pre-processing and denoising methods, and advanced quantification techniques. Furthermore, AI has demonstrated potential in clinical applications, such as disease diagnosis, molecular subtyping, and treatment monitoring, underscoring its growing relevance in the field. This review also examines the challenges in AI applications and future directions in CEST MRI, including the use of synthetic data, the explainability and interpretability of AI models, and their implications for clinical adoption. Overall, this review provides a comprehensive understanding of the current state of AI applications in CEST MRI and will inspire further research to unlock the full potential of this powerful molecular imaging technique.enChemical exchange saturation transferArtificial intelligenceMachine learningMedical image processingTRANSFER CEST MRIPROTONOPTIMIZATIONTUMORSMODELCONTRASTSTROKESCHEMEjournal-article