Year: 2024
Type: conference-paper
Abstract: Image segmentation remains a pivotal component in medical image analysis, aiding in the extraction of critical information for precise diagnostic practices. With the advent of deep learning, automated image segmentation methods have risen to prominence, showcasing exceptional proficiency in processing medical imagery. Motivated by the Segment Anything Model (SAM)—a foundational model renowned for its remarkable precision and robust generalization capabilities in segmenting 2D natural images—we introduce SAM3D, an innovative adaptation tailored for 3D volumetric medical image analysis. Unlike current SAM-based methods that segment volumetric data by converting the volume into separate 2D slices for individual analysis, our SAM3D model processes the entire 3D volume image in a unified approach. Extensive experiments are conducted on multiple medical image datasets to demonstrate that our network attains competitive results compared with other state-of-the-art methods in 3D medical segmentation tasks while being significantly efficient in terms of parameters. Code and checkpoints are available at https://github.com/UARK-AICV/SAM3D.
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: RII Track-2 FEC: Artificial Intelligence on Sustainable Energy Infrastructure Network (AI SUSTEIN) and Beyond towards Industries of the Future, RII Track-1: Data Analytics that are Robust and Trusted (DART): From Smart Curation to Socially Aware Decision Making, G4711139145, NSF Convergence Accelerator Track J: Data-driven Agriculture to Bridge Small Farms to Regional Food Supply Chains (L02619644), EFRI BRAID: Unsupervised Continual Learning with Hierarchical Timescales and Plasticity Mechanisms, RII Track 2 FEC: Multi-Scale Integrative Approach to Digital Health: Collaborative Research and Education in Smart Health in West Virginia and Arkansas, G8135294144
OpenAlex ID: W4401751609