Related Experiment Video
Updated: Sep 15, 2025
08:17
Dynamic Lung Tumor Tracking for Stereotactic Ablative Body Radiation Therapy
Published on: June 7, 2015
15.8K
TrackRAD2025 challenge dataset: real-time tumor tracking for MRI-guided radiotherapy
Yiling Wang1, Elia Lombardo2, Adrian Thummerer2
1Department of Radiation Oncology, Radiation Oncology Key Laboratory of Sichuan Province, Sichuan Clinical Research Center for Cancer, Sichuan Cancer Hospital & Institute, Sichuan Cancer Center, University of Electronic Science and Technology of China, Chengdu, China.
Medical Physics
|July 15, 2025
Summary
A new multi-institutional dataset of real-time MRI scans from MRI-linear accelerator systems is now available. This resource supports the development of advanced tumor tracking algorithms for adaptive radiotherapy.
Area of Science:
- Medical Imaging
- Radiotherapy
- Machine Learning
Background:
- Real-time visualization of anatomical motion is crucial for effective radiotherapy in cancer patients.
- Hybrid MRI-linear accelerator (MRI-linac) systems offer advanced capabilities for motion management during treatment.
- Developing robust real-time tumor localization algorithms is essential for adaptive radiotherapy strategies.
Purpose of the Study:
- To present a novel, multi-institutional real-time MRI time series dataset.
- To facilitate the development and evaluation of real-time tumor tracking algorithms for MRI-guided radiotherapy.
- To support the TrackRAD2025 challenge by providing a comprehensive data resource.
Main Methods:
- The dataset comprises sagittal 2D cine MRIs from 585 patients across six international centers.
- Data was acquired using two commercial MRI-linac vendors at 0.35 T and 1.5 T field strengths.
- Manual segmentation of irradiation targets or tracking surrogates was performed for 108 cases, with a public training and private testing split.
Main Results:
- The dataset includes a large collection of real-time MRI scans with varying frame rates and patient cohorts.
- Segmentation data is provided for a subset of cases, enabling supervised learning approaches.
- The data is publicly accessible, promoting collaborative research and algorithm development.
Conclusions:
- This dataset represents a significant resource for advancing real-time tumor localization in MRI-guided radiotherapy.
- It will enable the creation and validation of more accurate motion management and adaptive treatment techniques.
- The availability of this data has the potential to substantially improve radiotherapy outcomes for cancer patients.
