Generating synthetic computed tomography for radiotherapy: SynthRAD2023 challenge report. - UNICANCER
Article Dans Une Revue Medical Image Analysis Année : 2024

Generating synthetic computed tomography for radiotherapy: SynthRAD2023 challenge report.

1 TU/e - Eindhoven University of Technology [Eindhoven]
2 UMCU - University Medical Center [Utrecht]
3 University of Groningen [Groningen]
4 UMCG - University Medical Center Groningen [Groningen]
5 MUMC - Maastricht University Medical Centre
6 LMU - Ludwig Maximilian University [Munich] = Ludwig Maximilians Universität München
7 Radboud University Medical Center [Nijmegen]
8 WUR - Wageningen University and Research [Wageningen]
9 Amsterdam UMC - Amsterdam University Medical Center
10 UvA - University of Amsterdam [Amsterdam] = Universiteit van Amsterdam
11 Southern Medical University [Guangzhou]
12 BIT - Beijing Institute of Technology
13 ShanghaiTech University [Shanghai]
14 Fudan University [Shanghai]
15 FAU - Friedrich-Alexander Universität Erlangen-Nürnberg = University of Erlangen-Nuremberg
16 Indiana University [Bloomington]
17 Elekta Inc. [Maryland Heights]
18 Infervision Technology
19 Shantou University [Shantou, China]
20 Chercheur indépendant
21 Vanderbilt University [Nashville]
22 The Australian e-Health Research centre
23 USC - University of Southern California
24 UKA - Universitätsklinikum RWTH Aachen - University Hospital Aachen [Aachen, Germany]
25 PSI - Paul Scherrer Institute
26 D-INFK - Department of Computer Science [ETH Zürich]
27 LTSI - Laboratoire Traitement du Signal et de l'Image
28 CRLCC - CRLCC Eugène Marquis
29 University of Manchester [Manchester]
30 Muroran Institute of Technology
31 Niigata University
32 UCPH - University of Copenhagen = Københavns Universitet
33 SBU - Stony Brook University [SUNY]
34 NIMH - National Institute of Mental Health
35 TU Delft - Delft University of Technology
Zhihao Zhang
  • Fonction : Auteur
Long Wang
  • Fonction : Auteur
Lu Bai
  • Fonction : Auteur
Shaobin Wang
  • Fonction : Auteur
Derk Mus
  • Fonction : Auteur
Bram Kooiman
  • Fonction : Auteur
Satoshi Kasai
  • Fonction : Auteur
Zijie Chen
  • Fonction : Auteur
Enpei Wang
  • Fonction : Auteur

Résumé

Radiation therapy plays a crucial role in cancer treatment, necessitating precise delivery of radiation to tumors while sparing healthy tissues over multiple days. Computed tomography (CT) is integral for treatment planning, offering electron density data crucial for accurate dose calculations. However, accurately representing patient anatomy is challenging, especially in adaptive radiotherapy, where CT is not acquired daily. Magnetic resonance imaging (MRI) provides superior soft-tissue contrast. Still, it lacks electron density information, while cone beam CT (CBCT) lacks direct electron density calibration and is mainly used for patient positioning. Adopting MRI-only or CBCT-based adaptive radiotherapy eliminates the need for CT planning but presents challenges. Synthetic CT (sCT) generation techniques aim to address these challenges by using image synthesis to bridge the gap between MRI, CBCT, and CT. The SynthRAD2023 challenge was organized to compare synthetic CT generation methods using multi-center ground truth data from 1080 patients, divided into two tasks: (1) MRI-to-CT and (2) CBCT-to-CT. The evaluation included image similarity and dose-based metrics from proton and photon plans. The challenge attracted significant participation, with 617 registrations and 22/17 valid submissions for tasks 1/2. Top-performing teams achieved high structural similarity indices (≥0.87/0.90) and gamma pass rates for photon (≥98.1%/99.0%) and proton (≥97.3%/97.0%) plans. However, no significant correlation was found between image similarity metrics and dose accuracy, emphasizing the need for dose evaluation when assessing the clinical applicability of sCT. SynthRAD2023 facilitated the investigation and benchmarking of sCT generation techniques, providing insights for developing MRI-only and CBCT-based adaptive radiotherapy. It showcased the growing capacity of deep learning to produce high-quality sCT, reducing reliance on conventional CT for treatment planning.
Fichier principal
Vignette du fichier
1-s2.0-S1361841524002019-main.pdf (2.18 Mo) Télécharger le fichier
1-s2.0-S1361841524002019-mmc1.pdf (260.77 Ko) Télécharger le fichier
1-s2.0-S1361841524002019-mmc2.pdf (3.11 Mo) Télécharger le fichier
Origine Publication financée par une institution

Dates et versions

hal-04700425 , version 1 (17-09-2024)

Licence

Identifiants

Citer

Evi Huijben, Maarten Terpstra, Arthur Jr Galapon, Suraj Pai, Adrian Thummerer, et al.. Generating synthetic computed tomography for radiotherapy: SynthRAD2023 challenge report.. Medical Image Analysis, 2024, 97, pp.103276. ⟨10.1016/j.media.2024.103276⟩. ⟨hal-04700425⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

More