RT Journal Article
T1 No More Training: SAM’s Zero-Shot Transfer Capabilities for Cost-Efficient Medical Image Segmentation
A1 Gutiérrez, Juan D.
A1 Rodriguez-Echeverria, Roberto
A1 Delgado, Emilio
A1 Suero-Rodrigo, Miguel Ángel
A1 Sánchez-Figueroa, Fernando
K1 Image segmentation
K1 Lung
K1 X-ray imaging
K1 Computed tomography
K1 Medical diagnostic imaging
K1 Training
K1 Task analysis
K1 Image segmentation
K1 Deep learning
K1 Zero-shot learning
K1 Medical imaging
K1 Semantic segmentation
AB Semantic segmentation of medical images presents an enormous potential for diagnosis and surgery. However, achieving precise results involves designing and training complex Deep Learning (DL) models specifically for this task, which is only available to some. SAM is a model developed by Meta capable of segmenting objects present in virtually any type of image. This paper showcases SAM’s robustness and exceptional performance in medical image segmentation, even in the absence of direct training on these image types (lung Computed Tomographies (CTs) and chest X-rays, in particular). Additionally, it achieves this impressive outcome while requiring minimal user intervention. Although the dataset used to train SAM does not contain a single sample of both medical image types, processing a popular dataset comprised of 20 volumes with a total of 3520 slices using the ViT-L version of the model yields an average Jaccard index of 91.45% and an average Dice score of 94.95% . The same version of the model achieves a 93.19% Dice score and a 87.45% Jaccard index when segmenting a frequently-used chest X-ray dataset. The values obtained are above the 70% mark recommended in the literature, and close to state-of-the art models developed specifically for medical segmentation. These results are achieved without user interaction by providing the model with positive prompts based on the masks of the dataset used and a negative prompt located in the center of bounding box that contains the masks.
PB IEEE
SN 2169-3536
YR 2024
FD 2024-01-11
LK https://hdl.handle.net/10347/41028
UL https://hdl.handle.net/10347/41028
LA eng
NO J. D. Gutiérrez, R. Rodriguez-Echeverria, E. Delgado, M. Á. S. Rodrigo and F. Sánchez-Figueroa, "No More Training: SAM’s Zero-Shot Transfer Capabilities for Cost-Efficient Medical Image Segmentation," in IEEE Access, vol. 12, pp. 24205-24216, 2024, doi: 10.1109/ACCESS.2024.3353142
NO This work was supported in part by MCIN/AEI/10.13039/50100011033 under Grant CPP2021-008491, and in part by the European Union NextGenerationEU/PRTR.
DS Minerva
RD 24 abr 2026