PuSH - Publication Server of Helmholtz Zentrum München

Stein, J. ; di Folco, M. ; Schnabel, J.A.

Influence of Prompting Strategies on Segment Anything Model (SAM) for Short-axis Cardiac MRI Segmentation.

In: (Bildverarbeitung für die Medizin 2024). Switzerland: Springer Vieweg Verlag, 2024. 54-59 (Inf. aktuell)
DOI
The segment anything model (SAM) has recently emerged as a significant breakthrough in foundation models, demonstrating remarkable zero-shot performance in object segmentation tasks. While SAM is designed for generalization, it exhibits limitations in handling specific medical imaging tasks that require fine-structure segmentation or precise boundaries. In this paper, we focus on the task of cardiac magnetic resonance imaging (cMRI) short-axis view segmentation using the SAM foundation model. We conduct a comprehensive investigation of the impact of different prompting strategies (including bounding boxes, positive points, negative points, and their combinations) on segmentation performance. We evaluate on two public datasets using the baseline model and models fine-tuned with varying amounts of annotated data, ranging from a limited number of volumes to a fully annotated dataset. Our findings indicate that prompting strategies significantly influence segmentation performance. Combining positive points with either bounding boxes or negative points shows substantial benefits, but little to no benefit when combined simultaneously. We further observe that fine-tuning SAM with a few annotated volumes improves segmentation performance when properly prompted. Specifically, fine-tuning with bounding boxes has a positive impact, while fine-tuning without bounding boxes leads to worse results compared to baseline.
Altmetric
Additional Metrics?
[➜Log in]
Edit extra informations Login
Publication type Article: Conference contribution
Corresponding Author
ISSN (print) / ISBN 1431-472X
e-ISSN 1431-472X
Conference Title Bildverarbeitung für die Medizin 2024
Journal Informatik aktuell
Quellenangaben Volume: , Issue: , Pages: 54-59 Article Number: , Supplement: ,
Publisher Springer Vieweg Verlag
Publishing Place Switzerland
Non-patent literature Publications
Institute(s) Institute for Machine Learning in Biomed Imaging (IML)