Breast cancer is the major cause of death amongst women in the 35 to 55 age group. Mammography is the only feasible imaging modality for screening large numbers of women. With the present screening policy, there are three million mammograms to be analysed each year in the UK; there is therefore a need (as yet unmet) for an automated analysis system which could highlight areas of interest. In the first instance, the areas of interest might simply be any mass-like structures and this is indeed the approach reported on in this paper. Mammography is typical of many problems in medicine: the class of real interest is under-represented in the database of available examples and hence its prior probability will be very low. As a result of this, there are very few examples of abnormalities in any of the existing databases. If a neural network classifier is trained using the standard approach of minimising the mean-squared error (MSE) at the output, the under-represented class will be ignored. We have been exploring an alternative approach in which we attempt to learn a description of normality using the large number of available mammograms which do not show any evidence of mass-like structures. The idea is then to test for novelty against this description in order to try and identify candidate masses in previously unseen images analysis and interpretation and present a sample of the results which we have so far obtained on a standard database.