Abstract

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 spatially filtered to enforce local consensus among neighboring pixels and the spatially filtered image is output.

Other References

• "Automated Visual Quality Evaluation of CVD Film" by W.P. Kegelmeyer, Jr. et al. reprinted from Applications of Artificial Intelligence X: Machine Vision and Robotics, 22-24 Apr. 1992, Orlando, Fl, vol. 1708
• "Mammogram Inspection by Computer" by W. Spiesberger, 1979 IEEE
• "Computerized Quantification of Breast Duct Patterns" by A. Shadagopan et al., Diagnostic Radiology, Jun. 1982, vol. 143, No. 3
• "Texture Classification Using Averages of Local Pattern Matches" by Pietikainen et al., 1982 IEEE
• "Automated Detection of Breast Tumors Using the Asymmetry Approach" by Lau et al., Computer and Biomedical Research 24, pp. 273-295 (1991)
• "On Techniques for Detecting Circumscribed Masses in Mammograms" by S. Lai et al., IEEE Transactions on Medical Imaging, vol. 8, No. 4, Dec. 1989
• "Toward Reliable Measurements of Breast Parenchymal Patterns" by C. Kimme-Smith et al., Proceedings, 6th Conference on Computer Applications in Radiology & Computer/Aided Analysis of Radiology Images, Jun. 18-21, 1979
• "Supervised Textured Image Segmentation Using Feature Smoothing and Probabilistic Relaxation Techniques" by Hsiao et al., IEEE Transaction on Pattern Analysis and Machine Intelligence, vol. II, No. 12, Dec. 1989
• "Investigation of Methods for the Computerized Detection and Analysis of Mammographic Masses" by M. Giger et al., SPIE vol. 1233 Medical Imaging IV: Image Processing (1990)
• "An Iterative Growing and Pruning Algorithm for Classification Tree Design" by S. Gelfand et al., IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, No. 2, Feb. 1991
• "A Computer Analysis of Mammographic Microcalcifications: Global Approach" by S. Fox et al., 1980 IEEE
• "Algorithm for the Detection of Fine Clustered Calcifications on Film Mammograms" by F. Fam et al., Radiology, vol. 169, No. 2, pp. 333-337
• "Image Feature Analysis and Computer-Aided Diagnosis in Digital Radiology" by H. Chan et al., Med. Phys. 14(4), Jul./Aug. 1987, pp. 538-548
• "Automatic Computer Detection of Clustered Calcifications in Digital Mammograms" by D.H. Davis et al., Phys. Med. Biol., 1990, vol. 35, No. 3, 1111-1118
• "An Approach to Automated Detection of Tumors in Mammograms" by Brzakovic et al., IEEE Transactions on Medical Imaging, vol. 9, No. 3, Sep. 1990
• "Breast Lesion Classification by Computer and Xeroradiograph" by L. Ackerman, Cancer, Oct. 1972, vol. 30, No. 4, pp. 1025-1035
• "Combining Cues for Mammographic Abnormalities" by S. Astley et al., Image and Vision Computing, vol. 10, No. 5, Jun. 1992
• "Computer-Assisted Analysis of Mammographic Clustered Calcifications" by Messrs. Freundlich, Hunter, Seeley, D'Orsi and Sadowsky; Clinical Radiology (1989), pp. 295-298
• "Classification of Breast Tissue by Texture Analysis" by P. Miller and S. Astley; Image and Vision Computing; vol. 10, No. 5, Jun. 1992; pp. 277-282