Artificially enlarged training set in image segmentation

Authors:
Tuomas Tölli;Juha Koikkalainen;Kirsi Lauerma;Jyrki Lötjönen
Affiliations:
Laboratory of Biomedical Engineering, Helsinki University of Technology, HUT, Finland;VTT Information Technology, Tampere, Finland;Helsinki Medical Imaging Center, University of Helsinki, HUS, Finland;VTT Information Technology, Tampere, Finland
Venue:
MICCAI'06 Proceedings of the 9th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I
Year:
2006

Citing 3
Cited 1

Numerical recipes in C (2nd ed.): the art of scientific computing

Numerical recipes in C (2nd ed.): the art of scientific computing
Active shape models—their training and application

Computer Vision and Image Understanding
A novel 3d partitioned active shape model for segmentation of brain MR images

MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I

Statistical Deformation Models of Breast Compressions from Biomechanical Simulations

IWDM '08 Proceedings of the 9th international workshop on Digital Mammography

Quantified Score

Hi-index	0.00

Visualization

Abstract

Due to small training sets, statistical shape models constrain often too much the deformation in medical image segmentation. Hence, an artificial enlargement of the training set has been proposed as a solution for the problem. In this paper, the error sources in the statistical shape model based segmentation were analyzed and the optimization processes were improved. The method was evaluated with 3D cardiac MR volume data. The enlargement method based on non-rigid movement produced good results – with 250 artificial modes, the average error for four-chamber model was 2.11 mm when evaluated using 25 subjects.