skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Method and apparatus for detecting a desired behavior in digital image data

Patent ·
OSTI ID:870973
 [1]
+ Show Author Affiliations
  1. (11755 Shadow Dr., Dublin, CA 94568)

A method for detecting stellate lesions in digitized mammographic image data includes the steps of prestoring a plurality of reference images, calculating a plurality of features for each of the pixels of the reference images, and creating a binary decision tree from features of randomly sampled pixels from each of the reference images. Once the binary decision tree has been created, a plurality of features, preferably including an ALOE feature (analysis of local oriented edges), are calculated for each of the pixels of the digitized mammographic data. Each of these plurality of features of each pixel are input into the binary decision tree and a probability is determined, for each of the pixels, corresponding to the likelihood of the presence of a stellate lesion, to create a probability image. Finally, the probability image is spacially filtered to enforce local consensus among neighboring pixels and the spacially filtered image is output.

Research Organization:
Sandia National Laboratories (SNL), Albuquerque, NM, and Livermore, CA (United States)
DOE Contract Number:
AC04-76
Assignee:
Kegelmeyer, Jr., W. Philip (11755 Shadow Dr., Dublin, CA 94568)
Patent Number(s):
US 5633948
OSTI ID:
870973
Country of Publication:
United States
Language:
English

References (13)

Automated visual quality evaluation of CVD film conference March 1992
Classification of breast tissue by texture analysis journal June 1992
Investigation of methods for the computerized detection and analysis of mammographic masses conference July 1990
Automatic computer detection of clustered calcifications in digital mammograms journal August 1990
Image feature analysis and computer-aided diagnosis in digital radiography. I. Automated detection of microcalcifications in mammography: Image feature analysis. I. Microcalcification detection journal July 1987
An approach to automated detection of tumors in mammograms journal January 1990
An iterative growing and pruning algorithm for classification tree design
  • Gelfand, S. B.; Ravishankar, C. S.; Delp, E. J.
  • IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 13, Issue 2 https://doi.org/10.1109/34.67645
journal January 1991
Computerized quantification of breast duct patterns. journal June 1982
Computer-assisted analysis of mammographic clustered calcifications journal May 1989
On techniques for detecting circumscribed masses in mammograms journal January 1989
Mammogram Inspection by Computer journal April 1979
Automated detection of breast tumors using the asymmetry approach journal June 1991
Algorithm for the detection of fine clustered calcifications on film mammograms. journal November 1988

Similar Records

Related Subjects

method
apparatus
detecting
desired
behavior
digital
image
data
stellate
lesions
digitized
mammographic
steps
prestoring
plurality
reference
images
calculating
features
pixels
creating
binary
decision
tree
randomly
sampled
created
preferably
including
aloe
feature
analysis
local
oriented
edges
calculated
pixel
input
probability
determined
corresponding
likelihood
presence
lesion
create
finally
spacially
filtered
enforce
consensus
neighboring
output
reference image
reference images
image data
digital image
digitized mammographic
preferably including
stellate lesion
stellate lesions
desired behavior
detecting stellate
mammographic image
/382/