Automatic segmentation of enhancing breast tissue in dynamic contrast-enhanced MR images
Paper i proceeding, 2007

We present a novel method for the segmentation of enhancing breast tissue, suspicious of malignancy, in dynamic contrast-enhanced (DCE) MR images. The method is based on seeded region growing and merging using criteria based on both the original image intensity values and the fitted parameters of a novel empiric parametric model of contrast enhancement. We present the results of the application of the method to DCE-MRI data sets originating from breast MRI examinations of 24 subjects (10 cases of benign and 14 cases of malignant enhancement). The results show that the segmentation method has 100% sensitivity for the detection of suspicious regions independently identified by a radiologist. The results suggest that the method has potential both as a tool to assist the clinician with the task of locating suspicious tissue and as input to a computer assisted diagnostic system for generating quantitative features for automatic classification of suspicious tissue.

Författare

Yaniv Gal

Andrew Mehnert

Chalmers, Signaler och system

Andrew Bradley

Kerry McMahon

Stuart Crozier

Publicerad i

Proc. 2007 Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (DICTA)

s. 124-129
0-7695-3067-2 (ISBN)

Kategorisering

Styrkeområden

Livsvetenskaper och teknik (2010-2018)

Ämneskategorier (SSIF 2011)

Datorseende och robotik (autonoma system)

Medicinsk bildbehandling

Identifikatorer

DOI

10.1109/DICTA.2007.119

ISBN

0-7695-3067-2

Mer information

Skapat

2017-10-07