TY  - JOUR
T1  - Automated segmentation of pediatric neuroblastoma on multi-modal MRI: Results of the SPPIN challenge at MICCAI 2023, MDPI Bioengineering, 2025
A1  - Buser, Myrthe
A1  - Simons, Dominique C.
A1  - Fitski, Matthijs
A1  - Wijnen, Marc H. W. A.
A1  - Littooij, Annemieke S.
A1  - ter Brugge, Annemiek H.
A1  - Vos, Iris N.
A1  - Janse, Markus H. A.
A1  - de Boer, Mathijs
A1  - Sato, Junya
A1  - Kido, Shoji
A1  - Kondo, Satoshi
A1  - Wodzinski, Marek
A1  - Müller, Henning
A1  - Ye, Jin
A1  - He, Junjun
A1  - Kirchhoff, Yannick
A1  - Rokkus, Maximilian R.
A1  - Haokai, Gao
A1  - Fernandez-Paton, Matias
A1  - Viaga-Canuto, Diana
A1  - Ellis, David G.
A1  - Aizenberg, Michele R.
A1  - van der Velden, Bas H. M.
A1  - Kuijf, Hugo
A1  - de Luca, Alberto
A1  - van der Steeg, Alida F. W.
JA  - MDPI Bioengineering, nov. 25
Y1  - 2025
M2  - doi: https://doi.org/10.3390/bioengineering12111157
N2  - Introduction: Surgery plays an important role within the treatment for neuroblastoma, a 
common pediatric cancer. This requires careful planning, often via magnetic resonance 
imaging (MRI)-based anatomical 3D models. However, creating these models is often timeconsuming and user dependent. We organized the Surgical Planning in PedIatric 
Neuroblastoma (SPPIN) challenge, to stimulate developments on this topic, and set a 
benchmark for fully automatic segmentation of neuroblastoma on multi-model MRI. 
Methods: The challenge started with a training phase, where teams received 78 sets of MRI 
scans from 34 patients, consisting of both diagnostic and post-chemotherapy MRI scans. 
Then, in the preliminary test phase, the team algorithms could be tested on 7 scans belonging 
to 3 patients. The final test phase, consisting of 18 MRI sets from 9 patients, determined the 
ranking of the teams. Ranking was based on the Dice similarity coefficient (Dice score), the 
95th percentile of the Hausdorff distance (HD95) and the volumetric similarity (VS). The 
SPPIN challenge was hosted at MICCAI 2023 as a one-time event.
Results: The final leaderboard consisted of 9 teams. The highest-ranking team achieved a 
median Dice score 0.82, a median HD95 of 7.69 mm and a VS of 0.91, utilizing a large, pretrained network called STU-Net. A significant difference for the segmentation results 
between diagnostic and post-chemotherapy MRI scans was observed (Dice = 0.89 vs Dice = 
0.59, P = 0.01) for the highest-ranking team.
Conclusion: SPPIN is the first medical segmentation challenge in extracranial pediatric 
oncology. The highest-ranking team used a large pre-trained network, suggesting that pretraining can be of use in small, heterogenous datasets. Although the results of the highestranking team were high for most patients, segmentation especially in small, pre-treated 
tumors was insufficient. Therefore, more reliable segmentation methods are needed to create 
clinically applicable models to aid surgical planning in pediatric neuroblastoma.
ER  -