Darryl McClymont1, Andrew Mehnert1,
Adnan Trakic1, Dominic Kennedy2, Stuart Crozier1
1University of
This paper provides a method for extracting representative Apparent Diffusion Coefficients from Diffusion-weighted MRI for the purpose of improved classification of benign and malignant breast lesions. This is achieved without the need for manual segmentation of the diffusion weighted images, which reduces the variability between individuals. 26 breast lesions were analysed, with results indicating that the use of automatically selected apparent diffusion coefficients can provide valuable classification.