Yufan He

@johnson111788 Hi thanks for the finding. There is a racing condition when InvertD is used along with ThreadDataLoader. The error can be reproduced when the preprocesssing/inversing workload is large and...

> > Thanks for the update, looks good to me. I have another question regarding the extra metric in the training config, seems it'n not used, do we need include...

Hi: Thanks for the question. We are working on the next release of vista3d which are trained on large cohort of MRI datasets + CT. When you say universal segmentation,...

Using synthetic data is the only way to go. The ongoing effort of MAISI https://developer.nvidia.com/blog/addressing-medical-imaging-limitations-with-synthetic-data-generation/ is one solution. Beside this, large intensity augmentation is also worth a try. https://github.com/BBillot/SynthSeg