Cerebellum is a rapidly developing and critical brain structure during the early postnatal stages. Accurate segmentation of the cerebellum into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is essential to characterize early cerebellum development. Compared with adult cerebellum, there are very few works proposed for infant cerebellum segmentation. Infant cerebellum MRIs exhibit extremely low tissue contrast and severe partial volume effects, posing a huge challenge for manual and automated segmentation of the cerebellum.
First, due to the low tissue contrast, the manual annotation is extremely challenging, especially for younger infant subjects (e.g., 6 months). Second, the collaborative use of multi-domain infant images (acquired from different imaging sites) makes the segmentation task more difficult. Third, there are often anatomical errors in the segmentation results. Therefore, by taking advantage of accurate manual labels from 24-month-old subjects, the aim of MICCAI Grand Challenge on Multi-domain Cross-time-point Infant Cerebellum MRI Segmentation 2022 (cSeg-2022) is to promote accurate segmentation algorithms on infant cerebellum MRIs from multiple domains.
News and updates
- The cSeg-2022 challenge is always open for registering your team and applying for training and testing datasets.
- Evaluation results are available at Evaluation & Results.
- When you are ready, please notify us and we will send you the testing dataset soon. You will have to submit the testing subjects’ segmentation results within 7 days.
- The training dataset is released on April 10, 2022. Please register your team first (register your team), then we will send the training dataset to you via email.
- Welcome to the cSeg-2022 challenge!
Registration: April 1, 2022
Training data release: April 10, 2022
Testing data release: July 1, 2022
Submission: July 1, 2022
Evaluation result release: August 1, 2022