3D automatic anatomy recognition based on iterative graph-cut-ASM
Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Image-Guided Procedures, volume 7625, article 76251T
Abstract
An abstract is not available in the lab archive. View the paper at its source.
This 2010 SPIE conference paper presents an iterative graph-cut active shape model for delineating anatomy in three-dimensional medical images, combining image-based segmentation with statistical shape information.
Summary
The paper proposes iterative graph-cut-ASM (IGCASM), a method for delineating anatomical structures in 3D medical images. It integrates statistical shape information from an active shape model with graph-cut image segmentation. The authors report preliminary testing on clinical abdominal CT images and describe the work as an extension of their earlier 2D approach. The conference paper is a preliminary report; its findings should not be conflated with the authors’ later, expanded journal study.
Cite this work
Xinjian Chen, Jayaram K. Udupa, Ulas Bagci, Abass Alavi, Drew A. Torigian (2010). 3D automatic anatomy recognition based on iterative graph-cut-ASM. Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Image-Guided Procedures, volume 7625, article 76251T https://doi.org/10.1117/12.844551
BibTeX