12 citations · 13 across the 2 of their papers we have counts for
3 papers
HistoEncoder: a digital pathology foundation model for prostate cancer
Joona Pohjonen, Abderrahim-Oussama Batouche, Antti Rannikko +4
Foundation models are trained on massive amounts of data to distinguish complex patterns and can be adapted to a wide range of downstream tasks with minimal computational resources…
Augment like there's no tomorrow: Consistently performing neural networks for medical imaging
Joona Pohjonen, Carolin Stürenberg, Atte Föhr +6
Deep neural networks have achieved impressive performance in a wide variety of medical imaging tasks. However, these models often fail on data not used during training, such as dat…
Spectral decoupling allows training transferable neural networks in medical imaging
Joona Pohjonen, Carolin Stürenberg, Antti Rannikko +2
Many current neural networks for medical imaging generalise poorly to data unseen during training. Such behaviour can be caused by networks overfitting easy-to-learn, or statistica…