Journal Article

DKFZ-2026-01260

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png MRIgRT real-time target tracking: TrackRAD2025 challenge report.

Blöcker, T. J. ; Görts, P. A. W. ; Wang, Y. ; Lombardo, E. ; Thummerer, A. ; Fan, Y. ; Zhao, Y. ; Papadopoulou, C. I. ; Hurkmans, C. ; Tijssen, R. H. N. ; Cusumano, D. ; Intven, M. P. ; Borman, P. ; Riboldi, M. ; Dudáš, D. ; Byrne, H. L. ; Placidi, L. ; Fusella, M. ; Jameson, M. ; Palacios, M. A. ; Cobussen, P. ; Finazzi, T. ; Tetar, S. U. ; Haasbeek, C. J. A. ; Keall, P. ; Maspero, M. ; Kurz, C. ; Tarifa, A. S. B. ; He, K. ; Zhu, S. ; Song, Y. ; Li, G. ; Hu, J. ; Knispel, F. ; Gatidis, S. ; Chu, H. ; Guo, J. ; Nielsen, M. ; Sentker, T. ; Boussot, V. ; Hémon, C. ; Ni, J. ; Georgas, K. ; Vagenas, T. P. ; Matsopoulos, G. K. ; Landry, G.DKFZ*

2026
Elsevier Science Amsterdam [u.a.]

Abstract: Magnetic resonance imaging (MRI)-guided radiotherapy (MRIgRT) integrates MRI with linear accelerators (MRI-linacs), enabling real-time motion management based on temporally resolved 2D MRI (cine-MRI). Current systems rely on template matching or deformable image registration for radiotherapy target (typically the gross tumor volume) localization, which allows beam gating. Further advances in localization could support more precise and efficient delivery methods. https://trackrad2025.grand-challenge.org/ was organized to provide a common dataset to benchmark algorithms for MRIgRT target tracking in 2D+t cine-MRI. Participants propagated target segmentation masks from an initialization frame across subsequent frames. The dataset comprised sagittal cine-MRI scans of 585 cancer patients undergoing radiotherapy at 0.35 T and 1.5 T MRI-linacs at six different institutions, with expert-annotated targets in 108 sequences. Target sites included the thorax (179 cases), abdomen (266 cases), and pelvis (140 cases). A total of 477 unlabeled and 50 labeled cases were provided for training purposes, 58 cases were kept private for preliminary testing (8) and final evaluation (50). The algorithms submitted by participants were executed on the challenge platform and assessed using metrics in three categories: geometric accuracy, surrogate dose accuracy and execution speed. Rankings were derived via a Rank-Then-Mean scheme. TrackRAD2025 attracted 148 registrations from 28 countries, 100 preliminary submissions and 24 final submissions from 14 teams. The top five methods achieved mean Dice similarity coefficients >0.87 and Euclidean center distances <2.1 mm, comparable to interobserver variability. Leading top five solutions featured foundation models with (4) or without (1) finetuning. Field strength had minimal effect on performance and tracking worked better for the pelvis with reduced motion amplitude compared to the thorax and abdomen cases, which achieved equivalent performance. TrackRAD2025 established a benchmark for MRIgRT tracking on multi-institutional cine-MRI data, highlighting foundation models as promising for clinical translation.

Keyword(s): Deep learning ; MRI-guidance ; MRI-linac ; Motion management ; Respiratory motion

---

Contributing Institute(s):

1. DKTK Koordinierungsstelle München (MU01)

Research Program(s):

1. 899 - ohne Topic (POF4-899) (POF4-899)

Appears in the scientific report 2026

---

Database coverage:
; Clarivate Analytics Master Journal List ; Current Contents - Engineering, Computing and Technology ; Ebsco Academic Search ; Essential Science Indicators ; IF >= 10 ; JCR ; SCOPUS ; Science Citation Index Expanded ; Web of Science Core Collection

---