Artificial intelligence for real-time motion tracking in MRI-guided radiotherapy: A systematic review.
Authors
Affiliations (5)
Affiliations (5)
- School of Electronic Engineering, Beijing University of Posts and Telecommunications, 10 Xitucheng Road, Haidian District, Beijing 100876, China. Electronic address: [email protected].
- School of Electronic Engineering, Beijing University of Posts and Telecommunications, 10 Xitucheng Road, Haidian District, Beijing 100876, China. Electronic address: [email protected].
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 17 Panjiayuan South Road, Chaoyang District, Beijing 100021, China. Electronic address: [email protected].
- School of Electronic Engineering, Beijing University of Posts and Telecommunications, 10 Xitucheng Road, Haidian District, Beijing 100876, China. Electronic address: [email protected].
- Department of Radiation Oncology, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, 17 Panjiayuan South Road, Chaoyang District, Beijing 100021, China. Electronic address: [email protected].
Abstract
Intrafraction motion compromises accurate dose delivery in MRI-guided radiotherapy (MRIgRT), motivating the adoption of artificial intelligence (AI). This systematic review aims to evaluate the performance of AI-driven motion tracking approaches and identify barriers to clinical translation. PubMed and Web of Science were searched from January 1, 2020, to January 1, 2026. Studies were selected via a two-stage screening process based on predefined criteria. Key information was extracted, and the Checklist for Artificial Intelligence in Medical Imaging (CLAIM) was used to assess methodological quality. Twenty-eight studies were included. Nineteen focused on target localization through registration-, segmentation-, reconstruction-, or machine learning-based approaches, and nine addressed motion prediction. Reported performance generally indicated sub-2 mm localization or prediction errors in many settings, segmentation accuracy of at least 0.83 in 12 studies, and inference times ranging from < 0.1-420 ms, although one volumetric reconstruction study required 8000 ms. Current research exhibits a pronounced anatomical bias toward the liver (n = 23). Only two studies used established public datasets, five reported external validation, and six released source code. The mean CLAIM score was 24.00 ± 2.85. AI-driven motion tracking has substantially advanced real-time motion management in MRIgRT, but clinical translation remains limited by anatomical bias, small and heterogeneous datasets, scarce external validation, heterogeneous evaluation metrics, and insufficient deployment and prospective dosimetric validation. Future progress will require multi-center open datasets, anatomy-aware model design, workflow-level optimization, and prospective clinically oriented validation.