Impact of retraining and data partitions on the generalizability of a deep learning model in the task of COVID-19 classification on chest radiographs
Different data repartitions of the same dataset used to train a DL model demonstrated significantly different performance values that helped explain the discrepancy between Set A and Set B and further demonstrated the limitations of model generalizability.
Authors
- Samuel G. Armato (ORCID: https://orcid.org/0000-0002-5428-7997)
- Maryellen L. Giger (ORCID: https://orcid.org/0000-0001-5482-9728)
- Mena Shenouda
- Heather M. Whitney (ORCID: https://orcid.org/0000-0001-6450-8266)
Institutions
- University of Chicago (US)
- University of Chicago Medical Center (US)
Publication Details
- Journal
- Journal of Medical Imaging
- Published
- 2024-12-26
- DOI
- https://doi.org/10.1117/1.jmi.11.6.064503
- Primary Topic
- COVID-19 diagnosis using AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- C3.ai Digital Transformation Institute
- National Institutes of Health
- National Institute of Biomedical Imaging and Bioengineering