Detection, synthesis and compression in mammographic image analysis with a hierarchical image probability model

Proceedings of the Workshop on Mathematical Methods in Biomedical Image Analysis

Volumn , Issue , 2001, Pages 3-10

  Spence, Clay ^a   Parra, Lucas ^a   Sajda, Paul ^a  

^a SARNOFF CORPORATION   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; COMPUTER AIDED DIAGNOSIS; DATA ACQUISITION; ERROR CORRECTION; IMAGE COMPRESSION; MAMMOGRAPHY; MARKOV PROCESSES; MATHEMATICAL MODELS; PROBABILITY DENSITY FUNCTION; PROBABILITY DISTRIBUTIONS;

IMAGE SYNTHESIS;

IMAGE ANALYSIS;

EID: 0035698177     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (20)

1. Prediction of breast cancer malignancy using an artificial neural network
2. Automated feature analysis and classification of malignant and benign microcalcifications
3. Computerized detection of clustered microcalcifications in digital mammograms using a shift-invariant artificial neural network
4. Artificial convolution neural network for medical image pattern recognition
5. Applications of multiresolution neural networks to mammography
6. Minimax entropy principle and its application to texture modeling
7. Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images
8. Classification of textures using Gaussian Markov random fields
9. Texture recognition using a non-parametric multi-scale statistical model
10. Flexible histograms: A multiresolution target discrimination model
11. Likelihood calculation for a class of multiscale stochastic models, with application to texture discrimination
12. Wavelet-based statistical signal processing using hidden markov models
13. Multiscale Bayesian segmentation using a trainable context model
14. Learning in graphical models
15. Two-year evaluation of a prototype clinical mammographic workstation for computer-aided diagnosis
16. Information theory and neural nets
17. Current problems in ROC analysis
18. Multi-modal volume registration by maximization of mutual information