Microcalcifications can be one of the earliest signs of breast cancer. Unfo
rtunately, their appearance in mammograms can be mimicked by dust and dirt
entering the imaging process and this has been shown previously to lead to
false positives. We use a model of the imaging process and, in particular,
the blurring functions inherent within it to detect the film-screen artifac
ts caused by dust and dirt and, thus, reduce false-positives. A crucial fac
et of the work is the choice of the correct image representation upon which
to perform the image processing. After extensive testing, our algorithm ha
s identified no microcalcifications as being artifacts and has an artifact
detection rate of approaching 96%.