One-class acoustic characterization applied to blood detection in IVUS

Authors:
Sean M. O'Malley;Morteza Naghavi;Ioannis A. Kakadiaris
Affiliations:
Computational Biomedicine Lab, University of Houston, Houston, TX;Association for Eradication of Heart Attack, Houston, TX;Computational Biomedicine Lab, University of Houston, Houston, TX
Venue:
MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention - Volume Part I
Year:
2007

Citing 1
Cited 3

Estimating the Support of a High-Dimensional Distribution

Neural Computation

An Inverse Scattering Algorithm for the Segmentation of the Luminal Border on Intravascular Ultrasound Data

MICCAI '09 Proceedings of the 12th International Conference on Medical Image Computing and Computer-Assisted Intervention: Part II
Challenges and Opportunities for Extracting Cardiovascular Risk Biomarkers from Imaging Data

CIARP '09 Proceedings of the 14th Iberoamerican Conference on Pattern Recognition: Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Towards extra-luminal blood detection from intravascular ultrasound radio frequency data

MICCAI'11 Proceedings of the 14th international conference on Medical image computing and computer-assisted intervention - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Intravascular ultrasound (IVUS) is an invasive imaging modality capable of providing cross-sectional images of the interior of a blood vessel in real time and at normal video framerates (10-30 frames/s). Low contrast between the features of interest in the IVUS imagery remains a confounding factor in IVUS analysis; it would be beneficial therefore to have a method capable of detecting certain physical features imaged under IVUS in an automated manner. We present such a method and apply it to the detection of blood. While blood detection algorithms are not new in this field, we deviate from traditional approaches to IVUS signal characterization in our use of 1-class learning. This eliminates certain problems surrounding the need to provide "foreground" and "background" (or, more generally, n-class) samples to a learner. Applied to the blood-detection problem on 40 MHz recordings made in vivo in swine, we are able to achieve ∼95% sensitivity with ∼90% specificity at a radial resolution of ∼600 µm.