TriSAM: Tri-Plane SAM for zero-shot cortical blood vessel segmentation in VEM images

TL;DR

This paper introduces BvEM, a new benchmark dataset for cortical blood vessel segmentation in vEM images across three species, and proposes TriSAM, a zero-shot 3D segmentation method leveraging SAM without training.

Contribution

The paper provides the first public benchmark for vEM blood vessel segmentation and introduces TriSAM, a novel zero-shot 3D segmentation approach based on SAM with a multi-seed tracking framework.

Findings

TriSAM outperforms existing methods on the BvEM benchmark.

BvEM includes high-quality annotations for three mammalian species.

TriSAM achieves accurate 3D segmentation without model training.

Abstract

While imaging techniques at macro and mesoscales have garnered substantial attention and resources, microscale Volume Electron Microscopy (vEM) imaging, capable of revealing intricate vascular details, has lacked the necessary benchmarking infrastructure. In this paper, we address a significant gap in this field of neuroimaging by introducing the first-in-class public benchmark, BvEM, designed specifically for cortical blood vessel segmentation in vEM images. Our BvEM benchmark is based on vEM image volumes from three mammals: adult mouse, macaque, and human. We standardized the resolution, addressed imaging variations, and meticulously annotated blood vessels through semi-automatic, manual, and quality control processes, ensuring high-quality 3D segmentation. Furthermore, we developed a zero-shot cortical blood vessel segmentation method named TriSAM, which leverages the powerful segmentation model SAM for 3D segmentation. To extend SAM from 2D to 3D volume segmentation, TriSAM employs a multi-seed tracking framework, leveraging the reliability of certain image planes for tracking while using others to identify potential turning points. This approach effectively achieves long-term 3D blood vessel segmentation without model training or fine-tuning. Experimental results show that TriSAM achieved superior performances on the BvEM benchmark across three species. Our dataset, code, and model are available online at \url{https://jia-wan.github.io/bvem}.