On generalisability of segment anything model for nuclear instance segmentation in histology images
Year: 2024
Type: preprint
Abstract: Pre-trained on a large and diverse dataset, the segment anything model (SAM) is the first promptable foundation model in computer vision aiming at object segmentation tasks. In this work, we evaluate SAM for the task of nuclear instance segmentation performance with zero-shot learning and finetuning. We compare SAM with other representative methods in nuclear instance segmentation, especially in the context of model generalisability. To achieve automatic nuclear instance segmentation, we propose using a nuclei detection model to provide bounding boxes or central points of nu-clei as visual prompts for SAM in generating nuclear instance masks from histology images.
Source: arXiv (Cornell University)
Authors: Xu, Kesi, Goetz, Lea, Rajpoot, Nasir
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4391273002