Parameter-Efficient Adaptation of Fetal Ultrasound Foundation Models for Low-Resource Clinical Settings: A Cross-Backbone Benchmark with Calibration and Cross-Population Evaluation — Code and Results
Code and derived result files reproducing the experiments, tables, and figures in the paper submitted to Biomedical Signal Processing and Control. Includes benchmark scripts for four foundation-model backbones, result CSVs, confusion matrices, bootstrap confidence intervals, and figure-generation code. Public image datasets and pre-trained weights are linked in the README, not redistributed
Authors
- Rajesh H. Kulkarni
- Srujan Raj Kondameedi
- Sreenith Madabuushi
- Sri Abhay Kumar Badam
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-10-27
- DOI
- https://doi.org/10.5281/zenodo.23682671
- Primary Topic
- Domain Adaptation and Few-Shot Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00