Custom Automatic Segmentation Models for Medicine and Biology based on FastSAM
FastSAM, a public image segmentation model trained on everyday images, is used to achieve a customizable and state-of-the-art segmentation model minimizing the training in two completely different scenarios. In one example we consider macroscopic X-ray images of the knee area. In the second example, images were acquired by microscopy of the volumetric zebrafish embryo retina with a much smaller spatial scale. In both cases, we analyze the minimum set of images required to segmentate keeping the state-of-the-art standards. The effect of filters on the pictures and the specificities of considering a 3D volume for the retina images are also analyzed.
Authors
- Javier Roca‐Pardiñas (ORCID: https://orcid.org/0000-0003-3107-4515)
- David G. Míguez (ORCID: https://orcid.org/0000-0001-8065-1142)
- Ignacio Rego‐Pérez (ORCID: https://orcid.org/0000-0003-1754-1164)
- N. Oreiro-Villar
- Alberto P. Muñuzuri (ORCID: https://orcid.org/0000-0002-0579-9347)
- Diego Pérez-Dones
- Santiago Paramés-Estévez (ORCID: https://orcid.org/0000-0003-0747-0761)
- F.J. Blanco (ORCID: https://orcid.org/0000-0002-0964-9215)
- Germán González Pazó
Institutions
- Universidade da Coruña (ES)
- Universidade de Santiago de Compostela (ES)
- Instituto de Investigación Biomédica de A Coruña (ES)
- Universidade de Vigo (ES)
- Universidad Autónoma de Madrid (ES)
Publication Details
- Journal
- WSEAS TRANSACTIONS ON BIOLOGY AND BIOMEDICINE
- Published
- 2024-12-13
- DOI
- https://doi.org/10.37394/23208.2024.21.38
- Primary Topic
- Advanced Neural Network Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00