Foundation model for cancer imaging biomarkers
Brigham and Women's Hospital · Harvard University · +7 more institutions
Abstract
Foundation models in deep learning are characterized by a single large-scale model trained on vast amounts of data serving as the foundation for various downstream tasks. Foundation models are generally trained using self-supervised learning and excel in reducing the demand for training samples in downstream applications. This is especially important in medicine, where large labelled datasets are often scarce. Here, we developed a foundation model for cancer imaging biomarker discovery by training a convolutional encoder through self-supervised learning using a comprehensive dataset of 11,467 radiographic lesions. The foundation model was evaluated in distinct and clinically relevant applications of cancer…
Citation impact
- FWCI
- 61.92
- Percentile
- 100%
- References
- 54
Authors
11- SPSuraj Pai
Brigham and Women's Hospital, Harvard University, Maastricht University, Dana-Farber Cancer Institute, Dana-Farber Brigham Cancer Center, Artificial Intelligence in Medicine (Canada), Mass General Brigham
- DBDennis Bontempi
Brigham and Women's Hospital, Harvard University, Maastricht University, Dana-Farber Cancer Institute, Dana-Farber Brigham Cancer Center, Artificial Intelligence in Medicine (Canada), Mass General Brigham
- IHIbrahim Hadžić
Brigham and Women's Hospital, Harvard University, Maastricht University, Dana-Farber Cancer Institute, Dana-Farber Brigham Cancer Center, Artificial Intelligence in Medicine (Canada), Mass General Brigham
- VPVasco Prudente
Brigham and Women's Hospital, Harvard University, Maastricht University, Dana-Farber Cancer Institute, Dana-Farber Brigham Cancer Center, Artificial Intelligence in Medicine (Canada), Mass General Brigham
- MSMateo Sokač
Aarhus University, Aarhus University Hospital
Topics & keywords
- Foundation (evidence)
- Medicine
- Cancer
- Medical physics
- Oncology
- Internal medicine
- History
- Archaeology