A model for optimization of spectral shape in digital mammography

Abstract

X-ray mammography is the most sensitive imaging modality available for the detection of breast cancer. The highest performance can only be achieved, however, if the complete imaging system is optimized. The development of digital mammography offers an opportunity to obtain improved sensitivity in mammography. In such systems, the decoupling of the recording and display processes allows each component of the imaging system to be optimized separately. In this paper we describe a method for optimizing the recording process for digital mammographic techniques. Our method uses an energy transport model of the propagation of signal and noise through the imaging system. The computations make use of experimentally determined data wherever possible so that the number of assumptions in the model can be minimized. The model predicts the signal-to-noise ratio for a constant dose to the breast, and therefore allows comparison and optimization both for different x-ray spectra and for different imaging tasks. The major energy-dependent components of the model have been verified, and good agreement is demonstrated between predictions by the model of both contrast and SNR and experimentally measured values. Calculations for a particular imaging task, detection of a 200-microns cubic calcification in a 6-cm, 50% adipose-50% glandular breast, illustrate application of the model for optimization of spectral shape.