RT Journal Article
T1 Exploring the limits of foundation models in medical image segmentation: a case study with SAM and genetic algorithms
A1 Gutiérrez, Juan D.
A1 Lozano García, Nuria
A1 Delgado Muñoz, Emilio
A1 Rubio Largo, Álvaro
A1 Rodríguez Echeverría, Roberto
K1 Deep Learning
K1 Foundation Models
K1 Genetic Algorithms
K1 Image Segmentation
K1 Medical Imaging
K1 Zero-Shot Learning
AB This paper investigates the limits of foundation models in medical image segmentation, mainly focusing on SAM by Meta. While previous research demonstrated SAM’s potential for cost-efficient segmentation, this study explores its performance enhancement through integration with prompt enhancement optimization and genetic algorithms, aiming to minimize user input further. As a proof of concept, we apply this novel approach to lung segmentation tasks using public axial lung CT scans, frontal chest X-ray datasets, and spleen MRIs. Our findings reveal that the genetic algorithm optimization significantly improves SAM’s segmentation accuracy, bringing it closer to the state-of-the-art performance achieved by specifically trained models. In particular, when compared with our previous approach, this technique reaches a 94.85 % Jaccard Index (+3.77 delta) and a 97.17 % Dice Score (+2.50 delta) for lung CT scans, a 93.39 % Jaccard Index (+5.95 delta) and a 96.57 %Dice Score (+3.38 delta) for chest X-rays, and a 91.00 % Jaccard Index (+6.51 delta) and a 95.07 % Dice Score (+4.12 delta) for spleen MRIs. Notably, this improvement is achieved without retraining or modifying SAM’s architecture. However, our analysis also identifies an inherent limitation in this optimization approach, revealing a performance ceiling that cannot be surpassed despite further genetic algorithm iterations. The implications of these findings emphasize the potential of combining foundation models with non-intrusive optimization techniques for cost-effective and accessible medical image segmentation. While dataset-related limitations may affect generalizability, validating the approach across broader clinical scenarios remains essential. Future work should explore applications to additional organs, diverse datasets, and the integration of expert-in-the-loop strategies to enhance clinical utility
PB UNIR
SN 1989-1660
YR 2026
FD 2026-02-24
LK https://hdl.handle.net/10347/46141
UL https://hdl.handle.net/10347/46141
LA eng
NO Gutiérrez, J. D., Lozano-García, N., Delgado, E., Rubio-Largo, Álvaro, and Rodriguez-Echeverria, R. (2026). Exploring the Limits of Foundation Models in Medical Image Segmentation: A Case Study With SAM and Genetic Algorithms. International Journal of Interactive Multimedia and Artificial Intelligence, 1–14. https://doi.org/10.9781/ijimai.2026.2223
NO This work was supported in part by Grant CPP2021-008491 funded by MICIU/AEI/10.13039/50100011033 and by the European Union NextGeneration EU/PRTR, in part by the AEI (State Research Agency, Spain), the MCIN (Ministry of Science and Innovation, Spain), and the ERDF (European Regional Development Fund, EU), as part of the project PID2022-137275NA-I00 (X-BIO project) funded by MCIN/AEI/10.13039/501100011033 and by "ERDF A way of making Europe"
DS Minerva
RD 24 abr 2026