2022 | Self supervised contrastive learning for digital histopathology.
https://malmic.ca/wp-content/themes/osmosis/images/empty/thumbnail.jpg 150 150 MaLMIC - Machine Learning in Medical Imaging Consortium MaLMIC - Machine Learning in Medical Imaging Consortium https://malmic.ca/wp-content/themes/osmosis/images/empty/thumbnail.jpgShort Description: We apply a contrastive self-supervised method to digital histopathology. A large-scale study with 57 histopathology datasets without labels was conducted. Our study focuses on differences between natural-scene and histopathology images. We find combining multiple multi-organ datasets improves task performances. Using more pretraining data has diminishing returns after around 50,000 images.
Modality: Optical/Microscopy
Organ: Prostate, Breast, Colorectal
Disease: Cancer