Can I use pretrained model publish on 2 Mar 2023 ?

Thanks

Hi, I am not sure I understand your question correctly.

I if you have your own pretrained model that you would like to finetune on HanSeg data, you are free to do as long it satisfies the following rule: Participants competing for prizes may use pre-trained AI models based on computer vision and/or medical imaging datasets (e.g. ImageNet, Medical Segmentation Decathlon). They may also use external datasets to train their AI algorithms. However, such data and/or models must be published under a permissive license (within 3 months of the Preliminary Development Phase deadline) to give all other participants a fair chance at competing on equal footing. They must also clearly state the use of external data in their submission, using the algorithm name [e.g. "HaN-Seg Model (trained w/ private data)"], algorithm page and/or a supporting publication/URL. (You can find out more about the challenge rules here.)

If you are asking about using my dummy submission called Test2 that I created on March 22nd - it would not make sense to use that model, because it was created just as a test to check if Grand Challenge Algorithm submission is working as expected and was not actually trained on any data.

Best, Gasper