PROCESS
Providing computing solutions for exascale challenges
CamNet
A deep learning platform for digital histopathology.
2
mentions
1
contributor
What CamNet can do for you
- Whole slide images are loaded and preprocessed with Otsu thresholding. Patches of normal and tumor tissue can be extracted in a parallel distributed fashion
- The patches can be extracted at different resolution levels with a random sampling scheme or uniform dense coverage can be selected
- Intermediate dabases of tissue patches are generated on the local storage
- State of the art convolutional neural networks can be trained/finetuned on the histopathology data
- Distributed training on multiple GPUs is also available
The software is organized into three layers. Layer I imp lements the extraction of patches of dimensions 224x224 pixels from the gigapixel slides of breast lymph nodes tissue. Patches are random sampled from the slide, in which areas of tumour were annotated by a physician. Patches belonging to a tumorous region are assigned a ‘tumor’ label (a Boolean variable equals to True). The extracted data are stored in an intermediate dataset with the corresponding labels. Layer II loads the intermediate dataset of patches and labels and trains a state - of - the - art deep conv olutional network to classify the two patch types. Different models can be chosen by a configuration parameter. Layer III focuses on network robustness and interpretability.
Tags
Programming Language
- Python
License
- MIT
Source code
Participating organizations
Projects with CamNet
Contributors
-
Mara GrazianiHaute École Spécialisée de Suisse Occidentale HES-SO Valais (HESSO)
Contact person
