Related Experiment Video
Updated: Aug 4, 2025
10:48
PET and MRI Guided Irradiation of a Glioblastoma Rat Model Using a Micro-irradiator
Published on: December 28, 2017
9.6K
Deep Learning in MRI-guided Radiation Therapy: A Systematic Review
Zach Eidex1,2, Yifu Ding1, Jing Wang1
1Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA.
Arxiv
|March 30, 2023
Summary
Deep learning enhances MRI-guided radiation therapy (MRgRT) for precise cancer treatment planning. This review covers AI applications in segmentation, synthesis, radiomics, and real-time MRI, discussing clinical impacts and future potential.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Radiation Oncology
Background:
- MRI-guided radiation therapy (MRgRT) provides adaptive treatment planning.
- Deep learning (DL) offers advanced capabilities to augment MRgRT.
Approach:
- Systematic review of DL applications in MRgRT.
- Categorization of studies into segmentation, synthesis, radiomics, and real-time MRI.
- Emphasis on underlying methodologies and clinical implications.
Key Points:
- DL algorithms improve segmentation accuracy and speed for MRgRT.
- AI-driven synthesis of MR images enhances treatment visualization.
- Radiomics and real-time MRI applications show promise for adaptive MRgRT.
Conclusions:
- DL integration is transforming MRgRT, enabling more precise and personalized cancer treatments.
- Addressing current challenges in DL for MRgRT is crucial for future clinical adoption.
- Future research should focus on robust validation and real-world implementation of DL in MRgRT.
