Adapt or specialize? A comprehensive evaluation of adapted SAM versus task-specific CNNs for fetal abdominal segmentation
Zero-shot SAM variants performed poorly, particularly on small or low-contrast structures. In contrast, adapted SAM models consistently outperformed CNNs, reaching DSC scores up to 0.90 (liver) and 0.80 (artery). Prompt-based interaction enables semi-automated, human-in-the-loop workflows, supporting clinical applicability.
Authors
- Alessandro Pietro La Camera
- Enrico G. Caiani (ORCID: https://orcid.org/0000-0002-1770-6486)
- Maria Chiara Fiorentino (ORCID: https://orcid.org/0000-0002-7397-803X)
- L. Fédérici (ORCID: https://orcid.org/0009-0003-5919-3484)
Institutions
- Marche Polytechnic University (IT)
- Politecnico di Milano (IT)
Publication Details
- Journal
- Computer Methods and Programs in Biomedicine
- Published
- 2025-11-26
- DOI
- https://doi.org/10.1016/j.cmpb.2025.109178
- Primary Topic
- Fetal and Pediatric Neurological Disorders
- Type
- article
- Field-Weighted Citation Impact
- 0.00