Using FastSAM for Creating Custom Automatic Segmentation Models for Medicine and Biology

• Santiago Parames-Estévez ^[1] ; Diego Pérez-Dones ^[2] ; Ignacio Rego-Pérez ^[5] ; Natividad Oreiro-Villar ^[5] ; Francisco J. Blanco ^[3] ; Javier Roca Pardinas ^[4] ; Germán Gonzalez Pazó ; David G. Míguez ^[2] ; Alberto P. Munuzuri ^[1]
  1. [1] Universidade de Santiago de Compostela

     Universidade de Santiago de Compostela

     Santiago de Compostela, España

     
  2. [2] Universidad Autónoma de Madrid

     Universidad Autónoma de Madrid

     Madrid, España

     
  3. [3] Universidade da Coruña

     Universidade da Coruña

     A Coruña, España

     
  4. [4] Universidade de Vigo

     Universidade de Vigo

     Vigo, España

     
  5. [5] Complexo Hospitalario Universitario de A Coruña

  Mostrar afiliaciones +
• Localización: Proceedings XoveTIC 2024: Impulsando el talento científico / coord. por Manuel Lagos Rodríguez, Tirso Varela Rodeiro, Javier Pereira-Loureiro, Manuel Penedo, 2024, págs. 237-243
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • FastSAM, a publicly available image segmentation model designed for general image segmentation, is turned into a highly adaptable and advanced segmentation tool that requires minimal training in two distinct scenarios. In the first case, we examine macroscopic X-ray images of the knee, in the second case, we focus on microscopic images of the zebra fish embryo retina, which have a significantly smaller spatial scale. We determine the minimum number of images needed to maintain state-of-the-art segmentation quality in each case. Finally, we evaluate the impact of image filtering and the unique considerations of segmenting 3D retinal volumes.