HaN-Seg: The head and neck organ-at-risk CT and MR segmentation challenge
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
HaN-Seg : The head and neck organ-at-risk CT and MR segmentation challenge. / Podobnik, Gašper; Ibragimov, Bulat; Tappeiner, Elias; Lee, Chanwoong; Kim, Jin Sung; Mesbah, Zacharia; Modzelewski, Romain; Ma, Yihao; Yang, Fan; Rudecki, Mikołaj; Wodziński, Marek; Peterlin, Primož; Strojan, Primož; Vrtovec, Tomaž.
I: Radiotherapy and Oncology, Bind 198, 110410, 09.2024.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - HaN-Seg
T2 - The head and neck organ-at-risk CT and MR segmentation challenge
AU - Podobnik, Gašper
AU - Ibragimov, Bulat
AU - Tappeiner, Elias
AU - Lee, Chanwoong
AU - Kim, Jin Sung
AU - Mesbah, Zacharia
AU - Modzelewski, Romain
AU - Ma, Yihao
AU - Yang, Fan
AU - Rudecki, Mikołaj
AU - Wodziński, Marek
AU - Peterlin, Primož
AU - Strojan, Primož
AU - Vrtovec, Tomaž
N1 - Publisher Copyright: © 2024 The Authors
PY - 2024/9
Y1 - 2024/9
N2 - Background and purpose: To promote the development of auto-segmentation methods for head and neck (HaN) radiation treatment (RT) planning that exploit the information of computed tomography (CT) and magnetic resonance (MR) imaging modalities, we organized HaN-Seg: The Head and Neck Organ-at-Risk CT and MR Segmentation Challenge. Materials and methods: The challenge task was to automatically segment 30 organs-at-risk (OARs) of the HaN region in 14 withheld test cases given the availability of 42 publicly available training cases. Each case consisted of one contrast-enhanced CT and one T1-weighted MR image of the HaN region of the same patient, with up to 30 corresponding reference OAR delineation masks. The performance was evaluated in terms of the Dice similarity coefficient (DSC) and 95-percentile Hausdorff distance (HD95), and statistical ranking was applied for each metric by pairwise comparison of the submitted methods using the Wilcoxon signed-rank test. Results: While 23 teams registered for the challenge, only seven submitted their methods for the final phase. The top-performing team achieved a DSC of 76.9 % and a HD95 of 3.5 mm. All participating teams utilized architectures based on U-Net, with the winning team leveraging rigid MR to CT registration combined with network entry-level concatenation of both modalities. Conclusion: This challenge simulated a real-world clinical scenario by providing non-registered MR and CT images with varying fields-of-view and voxel sizes. Remarkably, the top-performing teams achieved segmentation performance surpassing the inter-observer agreement on the same dataset. These results set a benchmark for future research on this publicly available dataset and on paired multi-modal image segmentation in general.
AB - Background and purpose: To promote the development of auto-segmentation methods for head and neck (HaN) radiation treatment (RT) planning that exploit the information of computed tomography (CT) and magnetic resonance (MR) imaging modalities, we organized HaN-Seg: The Head and Neck Organ-at-Risk CT and MR Segmentation Challenge. Materials and methods: The challenge task was to automatically segment 30 organs-at-risk (OARs) of the HaN region in 14 withheld test cases given the availability of 42 publicly available training cases. Each case consisted of one contrast-enhanced CT and one T1-weighted MR image of the HaN region of the same patient, with up to 30 corresponding reference OAR delineation masks. The performance was evaluated in terms of the Dice similarity coefficient (DSC) and 95-percentile Hausdorff distance (HD95), and statistical ranking was applied for each metric by pairwise comparison of the submitted methods using the Wilcoxon signed-rank test. Results: While 23 teams registered for the challenge, only seven submitted their methods for the final phase. The top-performing team achieved a DSC of 76.9 % and a HD95 of 3.5 mm. All participating teams utilized architectures based on U-Net, with the winning team leveraging rigid MR to CT registration combined with network entry-level concatenation of both modalities. Conclusion: This challenge simulated a real-world clinical scenario by providing non-registered MR and CT images with varying fields-of-view and voxel sizes. Remarkably, the top-performing teams achieved segmentation performance surpassing the inter-observer agreement on the same dataset. These results set a benchmark for future research on this publicly available dataset and on paired multi-modal image segmentation in general.
KW - Computational challenge
KW - Computed tomography
KW - Deep learning
KW - Head and neck cancer
KW - Magnetic resonance
KW - Organs-at-risk
KW - Radiotherapy
KW - Segmentation
U2 - 10.1016/j.radonc.2024.110410
DO - 10.1016/j.radonc.2024.110410
M3 - Journal article
C2 - 38917883
AN - SCOPUS:85198522504
VL - 198
JO - Radiotherapy & Oncology
JF - Radiotherapy & Oncology
SN - 0167-8140
M1 - 110410
ER -
ID: 399170664