Semi-Automatic Segmentation and Ultrasonic Characterization of Solid Breast Lesions
This work addresses breast cancer diagnosis by reducing subjectivity, but it is incremental as it builds on existing methods for segmentation and feature analysis.
The study tackled the problem of characterizing solid breast lesions for early cancer detection by using empirical mode decomposition for semi-automatic segmentation and evaluating sonographic features like echogenicity and heterogeneity, with some features providing good results for differentiation.
Characterization of breast lesions is an essential prerequisite to detect breast cancer in an early stage. Automatic segmentation makes this categorization method robust by freeing it from subjectivity and human error. Both spectral and morphometric features are successfully used for differentiating between benign and malignant breast lesions. In this thesis, we used empirical mode decomposition method for semi-automatic segmentation. Sonographic features like ehcogenicity, heterogeneity, FNPA, margin definition, Hurst coefficient, compactness, roundness, aspect ratio, convexity, solidity, form factor were calculated to be used as our characterization parameters. All of these parameters did not give desired comparative results. But some of them namely echogenicity, heterogeneity, margin definition, aspect ratio and convexity gave good results and were used for characterization.