TrackRAD2025 challenge dataset: real-time tumor tracking for MRI-guided radiotherapy

Yiling Wang; Elia Lombardo; Adrian Thummerer; Tom Blöcker; Yu Fan; Yue Zhao; Christianna Iris Papadopoulou; Coen Hurkmans; Rob H N Tijssen; Pia A W Görts; Shyama U Tetar; Davide Cusumano; Martijn PW Intven; Pim Borman; Marco Riboldi; Denis Dudáš; Hilary Byrne; Lorenzo Placidi; Marco Fusella; Michael Jameson; Miguel Palacios; Paul Cobussen; Tobias Finazzi; Cornelis J A Haasbeek; Paul Keall; Christopher Kurz; Guillaume Landry; Matteo Maspero

doi:10.1002/mp.17964

TrackRAD2025 challenge dataset: real-time tumor tracking for MRI-guided radiotherapy

Yiling Wang
, Elia Lombardo
, Adrian Thummerer
, Tom Blöcker
, Yu Fan
, Yue Zhao
, Christianna Iris Papadopoulou
, Coen Hurkmans
, Rob H N Tijssen
, Pia A W Görts
, Shyama U Tetar
, Davide Cusumano
, Martijn PW Intven
, Pim Borman
, Marco Riboldi
, Denis Dudáš
, Hilary Byrne
, Lorenzo Placidi
, Marco Fusella
, Michael Jameson

Miguel Palacios, Paul Cobussen, Tobias Finazzi, Cornelis J A Haasbeek, Paul Keall, Christopher Kurz, Guillaume Landry^*, Matteo Maspero

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

2 Downloads (Pure)

Abstract

PURPOSE: Magnetic resonance imaging (MRI) to visualize anatomical motion is becoming increasingly important when treating cancer patients with radiotherapy. Hybrid MRI-linear accelerator (MRI-linac) systems allow real-time motion management during irradiation. This paper presents a multi-institutional real-time MRI time series dataset from different MRI-linac vendors. The dataset is designed to support developing and evaluating real-time tumor localization (tracking) algorithms for MRI-guided radiotherapy within the TrackRAD2025 challenge ( https://trackrad2025.grand-challenge.org/).

ACQUISITION AND VALIDATION METHODS: The dataset consists of sagittal 2D cine MRIs (20-20543 frames per scan) in 585 patients from six centers (3 Dutch, 1 German, 1 Australian, and 1 Chinese). Tumors in the thorax, abdomen, and pelvis acquired on two commercially available MRI-linacs (0.35 T and 1.5 T) were included. For 108 cases, irradiation targets or tracking surrogates were manually segmented on each temporal frame. The dataset was randomly split into a public training set of 527 cases (477 unlabeled and 50 labeled) and a private testing set of 58 cases (all labeled).

DATA FORMAT AND USAGE NOTES: The data is publicly available under the TrackRAD2025 collection: https://doi.org/10.57967/hf/4539. Both the images and segmentations for each patient are available in metadata format.

POTENTIAL APPLICATIONS: This novel clinical dataset will enable the development and evaluation of real-time tumor localization algorithms for MRI-guided radiotherapy. By enabling more accurate motion management and adaptive treatment strategies, this dataset has the potential to advance the field of radiotherapy significantly.

Original language	English
Article number	e17964
Journal	Medical Physics
Volume	52
Issue number	7
DOIs	https://doi.org/10.1002/mp.17964
Publication status	Published - Jul 2025

Keywords

Databases, Factual
Humans
Image Processing, Computer-Assisted
Magnetic Resonance Imaging
Neoplasms/diagnostic imaging
Radiotherapy, Image-Guided/methods
Time Factors

Access to Document

10.1002/mp.17964Licence: CC BY

Medical Physics - 2025 - Wang - TrackRAD2025 challenge dataset real‐time tumor tracking for MRI‐guided radiotherapyFinal published version, 3.24 MBLicence: CC BY

Cite this

Wang, Y., Lombardo, E., Thummerer, A., Blöcker, T., Fan, Y., Zhao, Y., Papadopoulou, C. I., Hurkmans, C., Tijssen, R. H. N., Görts, P. A. W., Tetar, S. U., Cusumano, D., Intven, M. PW., Borman, P., Riboldi, M., Dudáš, D., Byrne, H., Placidi, L., Fusella, M., ... Maspero, M. (2025). TrackRAD2025 challenge dataset: real-time tumor tracking for MRI-guided radiotherapy. Medical Physics, 52(7), Article e17964. https://doi.org/10.1002/mp.17964

@article{91386db490af4d1c85e42c2dab239a48,

title = "TrackRAD2025 challenge dataset: real-time tumor tracking for MRI-guided radiotherapy",

abstract = "PURPOSE: Magnetic resonance imaging (MRI) to visualize anatomical motion is becoming increasingly important when treating cancer patients with radiotherapy. Hybrid MRI-linear accelerator (MRI-linac) systems allow real-time motion management during irradiation. This paper presents a multi-institutional real-time MRI time series dataset from different MRI-linac vendors. The dataset is designed to support developing and evaluating real-time tumor localization (tracking) algorithms for MRI-guided radiotherapy within the TrackRAD2025 challenge ( https://trackrad2025.grand-challenge.org/).ACQUISITION AND VALIDATION METHODS: The dataset consists of sagittal 2D cine MRIs (20-20543 frames per scan) in 585 patients from six centers (3 Dutch, 1 German, 1 Australian, and 1 Chinese). Tumors in the thorax, abdomen, and pelvis acquired on two commercially available MRI-linacs (0.35 T and 1.5 T) were included. For 108 cases, irradiation targets or tracking surrogates were manually segmented on each temporal frame. The dataset was randomly split into a public training set of 527 cases (477 unlabeled and 50 labeled) and a private testing set of 58 cases (all labeled).DATA FORMAT AND USAGE NOTES: The data is publicly available under the TrackRAD2025 collection: https://doi.org/10.57967/hf/4539. Both the images and segmentations for each patient are available in metadata format.POTENTIAL APPLICATIONS: This novel clinical dataset will enable the development and evaluation of real-time tumor localization algorithms for MRI-guided radiotherapy. By enabling more accurate motion management and adaptive treatment strategies, this dataset has the potential to advance the field of radiotherapy significantly.",

keywords = "Databases, Factual, Humans, Image Processing, Computer-Assisted, Magnetic Resonance Imaging, Neoplasms/diagnostic imaging, Radiotherapy, Image-Guided/methods, Time Factors",

author = "Yiling Wang and Elia Lombardo and Adrian Thummerer and Tom Bl{\"o}cker and Yu Fan and Yue Zhao and Papadopoulou, \{Christianna Iris\} and Coen Hurkmans and Tijssen, \{Rob H N\} and G{\"o}rts, \{Pia A W\} and Tetar, \{Shyama U\} and Davide Cusumano and Intven, \{Martijn PW\} and Pim Borman and Marco Riboldi and Denis Dud{\'a}{\v s} and Hilary Byrne and Lorenzo Placidi and Marco Fusella and Michael Jameson and Miguel Palacios and Paul Cobussen and Tobias Finazzi and Haasbeek, \{Cornelis J A\} and Paul Keall and Christopher Kurz and Guillaume Landry and Matteo Maspero",

note = "Publisher Copyright: {\textcopyright} 2025 The Author(s). Medical Physics published by Wiley Periodicals LLC on behalf of American Association of Physicists in Medicine.",

year = "2025",

month = jul,

doi = "10.1002/mp.17964",

language = "English",

volume = "52",

journal = "Medical Physics",

issn = "0094-2405",

publisher = "John Wiley \& Sons Inc.",

number = "7",

}

Wang, Y, Lombardo, E, Thummerer, A, Blöcker, T, Fan, Y, Zhao, Y, Papadopoulou, CI, Hurkmans, C, Tijssen, RHN, Görts, PAW, Tetar, SU, Cusumano, D, Intven, MPW, Borman, P, Riboldi, M, Dudáš, D, Byrne, H, Placidi, L, Fusella, M, Jameson, M, Palacios, M, Cobussen, P, Finazzi, T, Haasbeek, CJA, Keall, P, Kurz, C, Landry, G & Maspero, M 2025, 'TrackRAD2025 challenge dataset: real-time tumor tracking for MRI-guided radiotherapy', Medical Physics, vol. 52, no. 7, e17964. https://doi.org/10.1002/mp.17964

TY - JOUR

T1 - TrackRAD2025 challenge dataset

T2 - real-time tumor tracking for MRI-guided radiotherapy

AU - Wang, Yiling

AU - Lombardo, Elia

AU - Thummerer, Adrian

AU - Blöcker, Tom

AU - Fan, Yu

AU - Zhao, Yue

AU - Papadopoulou, Christianna Iris

AU - Hurkmans, Coen

AU - Tijssen, Rob H N

AU - Görts, Pia A W

AU - Tetar, Shyama U

AU - Cusumano, Davide

AU - Intven, Martijn PW

AU - Borman, Pim

AU - Riboldi, Marco

AU - Dudáš, Denis

AU - Byrne, Hilary

AU - Placidi, Lorenzo

AU - Fusella, Marco

AU - Jameson, Michael

AU - Palacios, Miguel

AU - Cobussen, Paul

AU - Finazzi, Tobias

AU - Haasbeek, Cornelis J A

AU - Keall, Paul

AU - Kurz, Christopher

AU - Landry, Guillaume

AU - Maspero, Matteo

PY - 2025/7

Y1 - 2025/7

N2 - PURPOSE: Magnetic resonance imaging (MRI) to visualize anatomical motion is becoming increasingly important when treating cancer patients with radiotherapy. Hybrid MRI-linear accelerator (MRI-linac) systems allow real-time motion management during irradiation. This paper presents a multi-institutional real-time MRI time series dataset from different MRI-linac vendors. The dataset is designed to support developing and evaluating real-time tumor localization (tracking) algorithms for MRI-guided radiotherapy within the TrackRAD2025 challenge ( https://trackrad2025.grand-challenge.org/).ACQUISITION AND VALIDATION METHODS: The dataset consists of sagittal 2D cine MRIs (20-20543 frames per scan) in 585 patients from six centers (3 Dutch, 1 German, 1 Australian, and 1 Chinese). Tumors in the thorax, abdomen, and pelvis acquired on two commercially available MRI-linacs (0.35 T and 1.5 T) were included. For 108 cases, irradiation targets or tracking surrogates were manually segmented on each temporal frame. The dataset was randomly split into a public training set of 527 cases (477 unlabeled and 50 labeled) and a private testing set of 58 cases (all labeled).DATA FORMAT AND USAGE NOTES: The data is publicly available under the TrackRAD2025 collection: https://doi.org/10.57967/hf/4539. Both the images and segmentations for each patient are available in metadata format.POTENTIAL APPLICATIONS: This novel clinical dataset will enable the development and evaluation of real-time tumor localization algorithms for MRI-guided radiotherapy. By enabling more accurate motion management and adaptive treatment strategies, this dataset has the potential to advance the field of radiotherapy significantly.

AB - PURPOSE: Magnetic resonance imaging (MRI) to visualize anatomical motion is becoming increasingly important when treating cancer patients with radiotherapy. Hybrid MRI-linear accelerator (MRI-linac) systems allow real-time motion management during irradiation. This paper presents a multi-institutional real-time MRI time series dataset from different MRI-linac vendors. The dataset is designed to support developing and evaluating real-time tumor localization (tracking) algorithms for MRI-guided radiotherapy within the TrackRAD2025 challenge ( https://trackrad2025.grand-challenge.org/).ACQUISITION AND VALIDATION METHODS: The dataset consists of sagittal 2D cine MRIs (20-20543 frames per scan) in 585 patients from six centers (3 Dutch, 1 German, 1 Australian, and 1 Chinese). Tumors in the thorax, abdomen, and pelvis acquired on two commercially available MRI-linacs (0.35 T and 1.5 T) were included. For 108 cases, irradiation targets or tracking surrogates were manually segmented on each temporal frame. The dataset was randomly split into a public training set of 527 cases (477 unlabeled and 50 labeled) and a private testing set of 58 cases (all labeled).DATA FORMAT AND USAGE NOTES: The data is publicly available under the TrackRAD2025 collection: https://doi.org/10.57967/hf/4539. Both the images and segmentations for each patient are available in metadata format.POTENTIAL APPLICATIONS: This novel clinical dataset will enable the development and evaluation of real-time tumor localization algorithms for MRI-guided radiotherapy. By enabling more accurate motion management and adaptive treatment strategies, this dataset has the potential to advance the field of radiotherapy significantly.

KW - Databases, Factual

KW - Humans

KW - Image Processing, Computer-Assisted

KW - Magnetic Resonance Imaging

KW - Neoplasms/diagnostic imaging

KW - Radiotherapy, Image-Guided/methods

KW - Time Factors

U2 - 10.1002/mp.17964

DO - 10.1002/mp.17964

M3 - Article

C2 - 40660787

SN - 0094-2405

VL - 52

JO - Medical Physics

JF - Medical Physics

IS - 7

M1 - e17964

ER -

TrackRAD2025 challenge dataset: real-time tumor tracking for MRI-guided radiotherapy

Abstract

Keywords

Access to Document

Fingerprint

Cite this