Medical Segmentation Decathlon Datasets
Michela Antonelli and Annika Reinke and Spyridon Bakas

@article{,
title= {Medical Segmentation Decathlon Datasets},
year= {2022},
keywords= {},
author= {Michela Antonelli and Annika Reinke and Spyridon Bakas and others},
abstract= {https://i.imgur.com/QqgA5n4.jpg

With recent advances in machine learning, semantic segmentation algorithms are becoming increasingly general purpose and translatable to unseen tasks. Many key algorithmic advances in the field of medical imaging are commonly validated on a small number of tasks, limiting our understanding of the generalisability of the proposed contributions. A model which works out-of-the-box on many tasks, in the spirit of AutoML, would have a tremendous impact on healthcare. The field of medical imaging is also missing a fully open source and comprehensive benchmark for general purpose algorithmic validation and testing covering a large span of challenges, such as: small data, unbalanced labels, large-ranging object scales, multi-class labels, and multimodal imaging, etc. This challenge and dataset aims to provide such resource thorugh the open sourcing of large medical imaging datasets on several highly different tasks, and by standardising the analysis and validation process. 

```
4.6M    ./Task06_Lung/labelsTr
5.7G    ./Task06_Lung/imagesTr
2.9G    ./Task06_Lung/imagesTs
8.6G    ./Task06_Lung
240K    ./Task05_Prostate/labelsTr
150M    ./Task05_Prostate/imagesTr
79M     ./Task05_Prostate/imagesTs
229M    ./Task05_Prostate
15M     ./Task01_BrainTumour/labelsTr
4.5G    ./Task01_BrainTumour/imagesTr
2.7G    ./Task01_BrainTumour/imagesTs
7.1G    ./Task01_BrainTumour
8.6M    ./Task07_Pancreas/labelsTr
7.6G    ./Task07_Pancreas/imagesTr
3.9G    ./Task07_Pancreas/imagesTs
12G     ./Task07_Pancreas
388K    ./Task02_Heart/labelsTr
249M    ./Task02_Heart/imagesTr
186M    ./Task02_Heart/imagesTs
435M    ./Task02_Heart
8.7M    ./Task08_HepaticVessel/labelsTr
5.8G    ./Task08_HepaticVessel/imagesTr
3.0G    ./Task08_HepaticVessel/imagesTs
8.8G    ./Task08_HepaticVessel
1.3M    ./Task09_Spleen/labelsTr
1.1G    ./Task09_Spleen/imagesTr
461M    ./Task09_Spleen/imagesTs
1.5G    ./Task09_Spleen
14M     ./Task10_Colon/labelsTr
4.0G    ./Task10_Colon/imagesTr
1.9G    ./Task10_Colon/imagesTs
5.9G    ./Task10_Colon
30M     ./Task03_Liver/labelsTr
19G     ./Task03_Liver/imagesTr
8.6G    ./Task03_Liver/imagesTs
27G     ./Task03_Liver
1.1M    ./Task04_Hippocampus/labelsTr
19M     ./Task04_Hippocampus/imagesTr
8.8M    ./Task04_Hippocampus/imagesTs
29M     ./Task04_Hippocampus
71G     .
```

Competition site: https://decathlon-10.grand-challenge.org/

**Reference:** Antonelli et al., The Medical Segmentation Decathlon. Nature Communications 2022. https://pubmed.ncbi.nlm.nih.gov/35840566/ (arXiv: https://arxiv.org/abs/2106.05735)},
terms= {},
license= {CC-BY-SA 4.0},
superseded= {},
url= {http://medicaldecathlon.com/}
}