{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T15:58:44Z","timestamp":1785427124605,"version":"3.56.0"},"reference-count":0,"publisher":"Universidad Internacional de La Rioja","issue":"7","license":[{"start":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T00:00:00Z","timestamp":1771891200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJIMAI"],"abstract":"<jats:p>This paper investigates the limits of foundation models in medical image segmentation, mainly focusing on SAM by Meta. While previous research demonstrated SAM\u2019s 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\u2019s 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\u2009% Jaccard Index (+3.77 delta) and a 97.17\u2009% Dice Score (+2.50 delta) for lung CT scans, a 93.39\u2009% Jaccard Index (+5.95 delta) and a 96.57 %Dice Score (+3.38 delta) for chest X-rays, and a 91.00\u2009% Jaccard Index (+6.51 delta) and a 95.07\u2009% Dice Score (+4.12 delta) for spleen MRIs. Notably, this improvement is achieved without retraining or modifying SAM\u2019s 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.<\/jats:p>","DOI":"10.9781\/ijimai.2026.2223","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:36:53Z","timestamp":1771951013000},"page":"16-29","source":"Crossref","is-referenced-by-count":0,"title":["Exploring the Limits of Foundation Models in Medical Image Segmentation: A Case Study With SAM and Genetic Algorithms"],"prefix":"10.9781","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1024-6202","authenticated-orcid":false,"given":"Juan D.","family":"Guti\u00e9rrez","sequence":"first","affiliation":[{"id":[{"id":"https:\/\/ror.org\/030eybx10","id-type":"ROR","asserted-by":"publisher"}],"name":"University of Santiago de Compostela"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0240-9445","authenticated-orcid":false,"given":"Nuria","family":"Lozano-Garc\u00eda","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/0174shg90","id-type":"ROR","asserted-by":"publisher"}],"name":"University of Extremadura"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9144-0698","authenticated-orcid":false,"given":"Emilio","family":"Delgado","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/0174shg90","id-type":"ROR","asserted-by":"publisher"}],"name":"University of Extremadura"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2999-4304","authenticated-orcid":false,"given":"\u00c1lvaro","family":"Rubio-Largo","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/0174shg90","id-type":"ROR","asserted-by":"publisher"}],"name":"University of Extremadura"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6545-0913","authenticated-orcid":false,"given":"Roberto","family":"Rodriguez-Echeverria","sequence":"additional","affiliation":[{"id":[{"id":"https:\/\/ror.org\/0174shg90","id-type":"ROR","asserted-by":"publisher"}],"name":"University of Extremadura"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4744","published-online":{"date-parts":[[2026,2,24]]},"container-title":["International Journal of Interactive Multimedia and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.ijimai.org\/index.php\/ijimai\/article\/download\/2223\/3779","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.ijimai.org\/index.php\/ijimai\/article\/download\/2223\/3779","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:06:11Z","timestamp":1781741171000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijimai.org\/index.php\/ijimai\/article\/view\/2223"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,24]]},"references-count":0,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.9781\/ijimai.2026.2223","relation":{},"ISSN":["1989-1660"],"issn-type":[{"value":"1989-1660","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,24]]}}}