Building a Stage 1 Computer Aided Detector for Breast Cancer using Genetic Programming Conor Ryan 1 , Krzysztof Krawiec 2 , Una-May O’Reilly 2 , Jeannie Fitzgerald 1 , and David Medernach 1 1 University of Limerick, Ireland Conor.Ryan@ul.ie|Jeannie.Fitzgerald@ul.ie|David.Medernach@ul.ie 2 CSAIL, MIT KKrawiec|UnaMay@csail.mit.edu Abstract. We describe a fully automated workflow for performing stage 1 breast cancer detection with GP as its cornerstone. Mammograms are by far the most widely used method for detecting breast cancer in women, and its use in national screening can have a dramatic impact on early detection and survival rates. With the increased availability of digital mammography, it is becoming increasingly more feasible to use auto- mated methods to help with detection. A stage 1 detector examines mammograms and highlights suspicious areas that require further investigation. A too conservative approach degenerates to marking every mammogram (or segment of) as suspicious, while missing a cancerous area can be disastrous. Our workflow positions us right at the data collection phase such that we generate textural features ourselves. These are fed through our system, which performs PCA on them before passing the most salient ones to GP to generate classifiers. The classifiers give results of 100% accuracy on true positives and a false positive per image rating of just 1.5, which is better than prior work. Not only this, but our system can use GP as part of a feedback loop, to both select and help generate further features. Key words: Genetic Programming, Classification, Mammography 1 Introduction In national mammography screening, radiologists quickly examine the mammo- grams of thousands of women to determine if there are early signs of a cancerous growth, or a lesion that requires more attention. It is essential to discover signs early, as survival is directly correlated with early detection [1]. In the event that a closer inspection is required, the woman must be re-called. This is very stress- ful to patients, and an overly conservative approach to screening can result in disillusionment with the process, with women becoming less inclined to partici- pate. This work aims to improve the early detection of true positives by evolving detectors which, although accurate, are not overly conservative.