UCL logo

UCL Discovery

UCL home » Library Services » Electronic resources » UCL Discovery

Classification improvement by segmentation refinement: Application to contrast-enhanced MR-mammography

Tanner, C; Khazen, M; Kessar, P; Leach, MO; Hawkes, DJ; (2004) Classification improvement by segmentation refinement: Application to contrast-enhanced MR-mammography. In: (pp. pp. 184-191).

Full text not available from this repository.

Abstract

In this study we investigated whether automatic refinement of manually segmented MR breast lesions improves the discrimination of benign and malignant breast lesions. A constrained maximum a-posteriori scheme was employed to extract the most probable lesion for a user-provided coarse manual segmentation. Standard shape, texture and contrast enhancement features were derived from both the manual and the refined segmentations for 10 benign and 16 malignant lesions and their discrimination ability was compared. The refined segmentations were more consistent than the manual segmentations from a radiologist and a non-expert. The automatic refinement was robust to inaccuracies of the manual segmentation. Classification accuracy improved on average from 69% to 82% after segmentation refinement. © Springer-Verlag Berlin Heidelberg 2004.

Type: Proceedings paper
Title: Classification improvement by segmentation refinement: Application to contrast-enhanced MR-mammography
URI: http://discovery.ucl.ac.uk/id/eprint/165233
Downloads since deposit
0Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item