1. Can I use semi-automatic segmentation algorithms in this challenge?
The challenge aims at both semi-automatic and fully-automatic segmentation methods. Two types of method will be ranked separately.
2. Can I publish a paper based on the validation results?
Of course you can. Please cite the following papers when you use the data for publications:
[1] Xiahai Zhuang: Multivariate mixture model for myocardial segmentation combining multi-source images. IEEE Transactions on Pattern Analysis and Machine Intelligence (T PAMI), vol. 41, no. 12, 2933-2946, 2019. link code
[2] J Qiu, L Li, S Wang, K Zhang, Y Chen, S Yang, X Zhuang: MyoPS-Net: Myocardial Pathology Segmentation with Flexible Combination of Multi-Sequence CMR Images. Medical Image Analysis 84, 102694, 2023. link code
3. Can I only use the released 5 LGE CMR as training data?
Of course. You can segment the ventricles combining the complimentary information from three-sequence CMR images, or just using the target sequence LGE CMR for training. Different types of training will be evaluated separately.
4. Can I use our own training data?
No. You’re supposed to use the data we offered for a fair comparison and for benchmarking different algorithms.