Improved detection and characterisation of breast cancer using magnetic resonance imaging, and novel image analysis and pattern recognition techniques (2008-2010)

Breast magnetic resonance imaging is finding clinical application as an adjunct diagnostic procedure to ultrasound and mammography. A major limitation of MRI, however, is that although it has a high sensitivity to breast cancer, its specificity is poor; i.e. the chance of making a false-positive diagnosis is high. This research aims to improve the specificity (and the sensitivity) of the technique, and therefore its clinical utility, through the use of computerised image analysis techniques and the integration of morphologic, kinetic, and structural information. If successful this will not only lead to improved cancer detection, but also enhance clinical management of the disease.