Year: 2024
Type: preprint
Abstract: This work introduces a new framework, ProtoSAM, for one-shot medical image segmentation. It combines the use of prototypical networks, known for few-shot segmentation, with SAM - a natural image foundation model. The method proposed creates an initial coarse segmentation mask using the ALPnet prototypical network, augmented with a DINOv2 encoder. Following the extraction of an initial mask, prompts are extracted, such as points and bounding boxes, which are then input into the Segment Anything Model (SAM). State-of-the-art results are shown on several medical image datasets and demonstrate automated segmentation capabilities using a single image example (one shot) with no need for fine-tuning of the foundation model. Our code is available at: https://github.com/levayz/ProtoSAM
Source: arXiv (Cornell University)
Authors: Ayzenberg, Lev, Giryes, Raja, Greenspan, Hayit
Institutions: Tel Aviv University, Icahn School of Medicine at Mount Sinai
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funder: Israel Science Foundation
Award: G7920484399
OpenAlex ID: W4400600508