Zobrazeno 1 - 10
of 199
pro vyhledávání: '"Walter, Hugo"'
Autor:
Fernandez, Virginia, Pinaya, Walter Hugo Lopez, Borges, Pedro, Graham, Mark S., Vercauteren, Tom, Cardoso, M. Jorge
Generative modelling and synthetic data can be a surrogate for real medical imaging datasets, whose scarcity and difficulty to share can be a nuisance when delivering accurate deep learning models for healthcare applications. In recent years, there h
Externí odkaz:
http://arxiv.org/abs/2311.04552
Autor:
Wang, Jueqi, Levman, Jacob, Pinaya, Walter Hugo Lopez, Tudosiu, Petru-Daniel, Cardoso, M. Jorge, Marinescu, Razvan
High-resolution (HR) MRI scans obtained from research-grade medical centers provide precise information about imaged tissues. However, routine clinical MRI scans are typically in low-resolution (LR) and vary greatly in contrast and spatial resolution
Externí odkaz:
http://arxiv.org/abs/2308.12465
Autor:
Graham, Mark S., Pinaya, Walter Hugo Lopez, Wright, Paul, Tudosiu, Petru-Daniel, Mah, Yee H., Teo, James T., Jäger, H. Rolf, Werring, David, Nachev, Parashkev, Ourselin, Sebastien, Cardoso, M. Jorge
Methods for out-of-distribution (OOD) detection that scale to 3D data are crucial components of any real-world clinical deep learning system. Classic denoising diffusion probabilistic models (DDPMs) have been recently proposed as a robust way to perf
Externí odkaz:
http://arxiv.org/abs/2307.03777
Autor:
Fernandez, Virginia, Sanchez, Pedro, Pinaya, Walter Hugo Lopez, Jacenków, Grzegorz, Tsaftaris, Sotirios A., Cardoso, Jorge
Knowledge distillation in neural networks refers to compressing a large model or dataset into a smaller version of itself. We introduce Privacy Distillation, a framework that allows a text-to-image generative model to teach another model without expo
Externí odkaz:
http://arxiv.org/abs/2306.01322
Autor:
Fernandez, Virginia, Pinaya, Walter Hugo Lopez, Borges, Pedro, Tudosiu, Petru-Daniel, Graham, Mark S, Vercauteren, Tom, Cardoso, M Jorge
In order to achieve good performance and generalisability, medical image segmentation models should be trained on sizeable datasets with sufficient variability. Due to ethics and governance restrictions, and the costs associated with labelling data,
Externí odkaz:
http://arxiv.org/abs/2209.08256