원문정보
초록
영어
This paper presents a new classification approach for detection of microcalcification clusters in digital mammograms. The proposed microcalcification detection method is done in two stages. In the first stage, features are extracted to discriminate between textures representing clusters of microcalcifications and texture representing normal tissue. The original mammogram image is decomposed using wavelet decomposition and gabor features are extracted from the original image Region of Interest (ROI). With these features individual microcalcification clusters is detected. In the second stage, the ability of these features in detecting microcalcification is done using Backpropagation Neural Network (BPNN). The proposed classification approach is applied to a database of 322 dense mammographic images, originating from the MIAS database. Results shows that the proposed BPNN approach gives a satisfactory detection performance.
목차
1. Introduction
2. Materials
2.1 A Database of Mammograms and preprocessing
3. Methodology for detecting microcalcification
3.1 Integer Wavelet Transform
3.2 Gabor Features Extraction
3.3 Neural Network classification
3.4 Proposed Backpropagation Learning
4. Classification of soft tissue lesions/masses in mammograms and performance evaluation
5. Conclusion
6. References