Image Crawlers

Principle Investigator: Ghassan Hamarneh
MSc Student: Chris McIntosh

Image Crawlers, a new breed of Deformable Organisms, are equiped with 3D tubular medial-based bodies, a new repertoire of sensory modules (e.g. Hessain-based, hemispherical sensors), behavioral routines (e.g. grow, spawn children branch cralwers), and decision making strategies (e.g. branch detection, growth direction). They crawl along tubular and tree-like structures in medical images, segmenting boundaries, detecting and exploring bifurcations, and providing sophisticated, clinically-relevant structural analysis.


Segmenting branching vessels in a retinal angiogram using a 2D artery crawler

3D Vessel Crawlers that not only segment vascular trees but also provide immediate quantitative and qualitative analysis; including branching point detection, cross sectional areas, tree graphs of vessel topology, tortuosity  measurements, and much more.


3D Spinal cord crawlers that build upon work with vascular segmentation (using filters and geometries designed for elliptical cross sections) to provide fast segmentation and immediate quantitative and qualitative analysis.



C. McIntosh, G. Hamarneh, "Spinal Crawlers": Deformable Organisms for Spinal Cord Segmentation and Analysis", MICCAI, 2006: 808-815

C. McIntosh and G. Hamarneh, "Vessel Crawlers: 3D Physically-based Deformable Organisms for Segmentation and Analysis of Tubular Structures in Medical Images", IEEE Conference on Computer Vision and Pattern Recognition, 2006: 1084-1091.

G. Hamarneh, T. McInerney, D. Terzopoulos. “Deformable Organisms for Automatic Medical Image Analysis”. Medical Image Computing and Computer-Assisted Intervention, 2001, Lecture Notes in Computer Science, ISBN 3-540-42697-3, vol. 2208, pp. 66-75

Site by Faculty of Applied Science web team, Simon Fraser University