Paper: Bayesian inference for model-based segmentation of computed radiographs of the hand

Authors:
Tod S. Levitt;Marcus W. Hedgcock, Jr.;John W. Dye;Scott E. Johnston;Vera M. Shadle;Dmitry Vosky
Affiliations:
National Center for Computed Imaging, San Francisco VA Medical Center, Radiology 114B, 4150 Clement Street, San Francisco, CA 94121-1598, USA and University of California at San Francisco, Departm ...;National Center for Computed Imaging, San Francisco VA Medical Center, Radiology 114B, 4150 Clement Street, San Francisco, CA 94121-1598, USA and University of California at San Francisco, Departm ...;Teknekron, 530 Lytton Ave., Ste. 301, Palo Alto, CA USA;United Programmers, 1999 Green St., Ste. 106, San Francisco, CA USA;National Center for Computed Imaging, San Francisco VA Medical Center, Radiology 114B, 4150 Clement Street, San Francisco, CA 94121-1598, USA;National Center for Computed Imaging, San Francisco VA Medical Center, Radiology 114B, 4150 Clement Street, San Francisco, CA 94121-1598, USA
Venue:
Artificial Intelligence in Medicine
Year:
1993

Citing 8
Cited 0

Model-based image matching using location

Model-based image matching using location
Evaluating influence diagrams

Operations Research
The computational complexity of probabilistic inference using Bayesian belief networks (research note)

Artificial Intelligence
Perceptual Organization and Visual Recognition

Perceptual Organization and Visual Recognition
Digital Radiography: Selected Topics

Digital Radiography: Selected Topics
Computer Vision

Computer Vision
Utility-based control for computer vision

UAI '88 Proceedings of the Fourth Annual Conference on Uncertainty in Artificial Intelligence
Model-Based Influence Diagrams for Machine Vision

UAI '89 Proceedings of the Fifth Annual Conference on Uncertainty in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a method for medical image understanding by computer that uses model-based, hierarchical Bayesian inference to accurately segment imaged anatomy. A first application is a prototype system that automatically segments and measures symptoms of arthridities in hand radiographs. This is potentially useful in radiological diagnosis and tracking of arthridities. Key steps of the model-based, Bayesian inference approach are: (1) prediction of imagery features from 3D models of anatomy, parameterized by population statistics, (2) local image feature extraction in predicted sub-regions, and (3) the use of a probabilistic calculus to accrue results of image processing and image feature matching procedures in support or denial of hypotheses about the imaged anatomy. The prototype system for hand radiograph analysis accurately segments normal and somewhat degenerated hand anatomy. Results are shown of the ability of the automated system to 'fail soft', recognizing when segmentation is inadequate for accurate measurement. This self evaluation capability improves reliability of measurements for potential clinical use.