Computational intelligence for the detection and classification of malignant lesions in screening mammography

Abstract

This report deals with the discussion of the findings obtained from the application of two computational intelligence methodologies for the detection of microcalcifications in screening mammography data. Genetic programming and inductive machine learning have been applied, in order to produce meaningful diagnostic rules for the medical staff. The data used in the experiments correspond to information acquired from two images of each breast of the patient, along with some associated patient information such as the age at time of study. Similar datasets have been previously used in an attempt to facilitate the development of computer algorithms to aid screening. Experienced screening radiologists have double-read the screening mammograms, they have weighted the malignancy ratings and averaged out the levels of suspiciousness assigned to each finding in the screenings. The diagnostic rules which were obtained from both genetic programming and machine learning have been evaluated in detail and then analyzed and discussed by collaborative medical experts, in parallel to findings from related literature. Results seem encouraging for further use and analysis by medical staff specializing in screening mammography.