Identifying tissue types in MR images of the prostate
Philip D. Allen, Lynsey Hamlet, James T. Graham, Charles E. Hutchinson · Research Explorer (The University of Manchester) · 2005
In this paper we present an initial exploration of the use of image texture measures to distinguish glandular and stromal Benign Prostatic Hyperplasia (BPH). Using image entropy and grey-level granulometry we show that quantitative texture measures can be found that correspond to visual classification of images into “granular” and “smooth” appearance, which have previously been associated with these classes. Some texture measures also correspond with the ratio of the volumes of the prostate’s central gland and peripheral zone, which is also considered to be indicative of the severity of BPH.