Y. Lee, D-Y. Tsai, and M. Sekiya (Japan)
medical imaging, computer-aided diagnosis, mammogram, micro calcification, fuzzy reasoning, genetic algorithm.
The purpose of this study is to develop a computerized scheme for the discrimination between benign and malignant clustered microcalcifications that would aid radiologists in interpreting mammograms. In our scheme, microcalcifications are detected in regions of interest (ROIs) by using morphological filter. Then, four feature values including the total number, mean area, mean circularity and mean minimum distance of microcalcifications are calculated for classification. Gaussian-distributed membership functions used for fuzzy reasoning are determined from means and standard deviations of these feature values. Finally, fuzzy reasoning using the genetic-algorithm optimized membership functions is employed to classify clustered microcalcifications in ROI. Our scheme is applied to 20 mammographic images with microcalcifications in the Mammographic Image Analysis Society database, containing 13 benign and 12 malignant ROIs. Of the images 10 each benign and malignant ROIs are used for learning in fuzzy reasoning. The remaining 5 images are classified as benign or malignant cases by fuzzy reasoning. As a result, the average accuracy was approximately 81% (sensitivity: 85%, specificity: 77%).
Important Links:
Go Back
