Segmentation of human functional tissue units in support of a Human Reference Atlas.
The Human BioMolecular Atlas Program (HuBMAP) aims to compile a Human Reference Atlas (HRA) for the healthy adult body at the cellular level. Functional tissue units (FTUs), relevant for HRA construction, are of pathobiological significance. Manual segmentation of FTUs does not scale; highly accurate and performant, open-source machine-learning algorithms are needed. We designed and hosted a Kaggle competition that focused on development of such algorithms and 1200 teams from 60 countries participated. We present the competition outcomes and an expanded analysis of the winning algorithms on additional kidney and colon tissue data, and conduct a pilot study to understand spatial location and density of FTUs across the kidney. The top algorithm from the competition, Tom, outperforms other algorithms in the expanded study, while using fewer computational resources. Tom was added to the HuBMAP infrastructure to run kidney FTU segmentation at scale-showcasing the value of Kaggle competitions for advancing research.
Duke Scholars
Altmetric Attention Stats
Dimensions Citation Stats
Published In
DOI
EISSN
ISSN
Publication Date
Volume
Issue
Start / End Page
Related Subject Headings
- Pilot Projects
- Magnetic Resonance Imaging
- Machine Learning
- Humans
- Algorithms
- Adult
- 32 Biomedical and clinical sciences
- 31 Biological sciences
Citation
Published In
DOI
EISSN
ISSN
Publication Date
Volume
Issue
Start / End Page
Related Subject Headings
- Pilot Projects
- Magnetic Resonance Imaging
- Machine Learning
- Humans
- Algorithms
- Adult
- 32 Biomedical and clinical sciences
- 31 Biological sciences