MONAI
MONAI copied to clipboard
AI Toolkit for Healthcare Imaging
**Describe the bug** During our experiments, we found that the ThreadDataLoader loading order made a difference when using the shuffling strategy related to numworkers **To Reproduce** ```python import torch from...
Hello! **Is your feature request related to a problem? Please describe.** When using different shapes (i.e. predicting a downsampled segmentation map or an upsampled, high resolution image) it is often...
UNET++ ustilizes skip connections to exploit multi-scale features for image segmentation. it added dense skip connection adn deep supervision to the original UNET https://arxiv.org/pdf/1912.05074.pdf please add this network to the...
### Discussed in https://github.com/Project-MONAI/MONAI/discussions/3463 Originally posted by **ebrahimebrahim** December 9, 2021 I experienced some numerically unstable training while using LNCC loss to train a registration network. Exploding gradients, clipping them...
**Is your feature request related to a problem? Please describe.** ```py from monai.bundle import ConfigParser config = {"training": "$monai.handlers"} parser = ConfigParser(config=config) parser.get_parsed_content("training") ``` when ignite is not installed, the...
**Is your feature request related to a problem? Please describe.** Need for the Cohen's kappa (and its weighted variant) as additional metric for whole image classification **Describe the solution you'd...
**Describe the bug** When the images in a pipeline entry have different sizes, then the RandAffined does not work properly. The resulting images no longer match. **To Reproduce** Steps to...
Multiple feature requests have described common use cases of metadata handling and computational backends for pre-/post-processing transformations. ### The proposed solution We agreed that these features are essential MONAI core...
It would nice to have several improvements to caching of data on disk and in memory. For caching on disk with **PersistentDataset**, - the first epoch takes a long time,...
**Is your feature request related to a problem? Please describe.** The positive likelihood ratio is a relevant counting metric to add (used for evaluation of whole image classification for instance)...